CN113627419B - Region of interest evaluation method, device, equipment and medium - Google Patents
Region of interest evaluation method, device, equipment and medium Download PDFInfo
- Publication number
- CN113627419B CN113627419B CN202010381698.1A CN202010381698A CN113627419B CN 113627419 B CN113627419 B CN 113627419B CN 202010381698 A CN202010381698 A CN 202010381698A CN 113627419 B CN113627419 B CN 113627419B
- Authority
- CN
- China
- Prior art keywords
- image
- region
- interest
- evaluation
- evaluated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application discloses a method, a device, equipment and a medium for evaluating an interest area, and relates to the technology of electronic maps. Wherein the method comprises the following steps: determining an image to be evaluated of the region of interest; determining an image evaluation result of the image to be evaluated in at least one dimension; and evaluating the region of interest according to an image evaluation result of the image to be evaluated in at least one dimension. Compared with manual evaluation of the region of interest, the embodiment of the application can improve the objectivity of the region of interest evaluation and improve the efficiency of the region of interest evaluation.
Description
Technical Field
The embodiment of the application relates to a computer technology, in particular to an electronic map technology, and particularly relates to a method, a device, equipment and a medium for evaluating an interest area.
Background
In recent years, with the improvement of living standard of people and the convenience of travel modes, the number of times of travel for people is increasing. The mobile map navigation application and the travel application play an increasingly important role in the aspect Of selecting a travel Interest Area (AOI) by a user, namely a physical entity in a map. These applications can provide the user with an auxiliary decision reference by displaying information of the region of interest, such as region evaluation, region surrounding environment and the like, and provide great convenience for the travel planning of the user.
At present, the scoring of the region of interest is mainly based on a few professional appreciators, and the evaluation is carried out through field investigation, so that the objectivity of the evaluation result is poor, and the evaluation efficiency is low.
Disclosure of Invention
The embodiment of the application discloses a method, a device, equipment and a medium for evaluating an interest region, which are used for improving the objectivity of the evaluation of the interest region and improving the efficiency of the evaluation of the interest region.
In a first aspect, an embodiment of the present application discloses a method for evaluating a region of interest, including:
determining an image to be evaluated of the region of interest;
Determining an image evaluation result of the image to be evaluated under at least one dimension;
And evaluating the region of interest according to an image evaluation result of the image to be evaluated in the at least one dimension.
In a second aspect, an embodiment of the present application further discloses a region of interest evaluation apparatus, including:
The image to be evaluated determining module is used for determining an image to be evaluated of the region of interest;
The image evaluation result determining module is used for determining an image evaluation result of the image to be evaluated in at least one dimension;
and the interest area evaluation module is used for evaluating the interest area according to the image evaluation result of the image to be evaluated in the at least one dimension.
In a third aspect, an embodiment of the present application further discloses an electronic device, including:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the region of interest assessment method according to any one of the embodiments of the present application.
In a fourth aspect, embodiments of the present application also disclose a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform a region of interest assessment method according to any of the embodiments of the present application.
According to the technical scheme provided by the embodiment of the application, the region of interest is evaluated by utilizing the image evaluation result of the image to be evaluated of the region of interest under at least one dimension, so that the problems of poor objectivity and low evaluation efficiency of the existing region of interest evaluation are solved, the objectivity and accuracy of the region of interest evaluation are improved, and the efficiency of the region of interest evaluation is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.
Drawings
The drawings are included to provide a better understanding of the present application and are not to be construed as limiting the application. Wherein:
FIG. 1 is a flow chart of a method of region of interest assessment disclosed in accordance with an embodiment of the present application;
FIG. 2 is a flow chart of another disclosed region of interest evaluation method in accordance with an embodiment of the present application;
FIG. 3 is a flow chart of another disclosed region of interest evaluation method in accordance with an embodiment of the present application;
FIG. 4 is a schematic diagram of an evaluation architecture for a region of interest disclosed in accordance with an embodiment of the present application;
FIG. 5 is a flow chart of another disclosed region of interest evaluation method in accordance with an embodiment of the present application;
FIG. 6 is a schematic diagram showing an interface of the region of interest evaluation results according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a region of interest evaluation device according to an embodiment of the present application;
Fig. 8 is a block diagram of an electronic device disclosed in accordance with an embodiment of the application.
Detailed Description
Exemplary embodiments of the present application will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present application are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a flowchart of a method for evaluating a region of interest according to an embodiment of the present application, where the embodiment of the present application may be applied to a case of evaluating a region of interest in a map, the method may be performed by a region of interest evaluation device, and the device may be implemented by using software and/or hardware, and may be integrated on any electronic device having computing capabilities, such as a server or the like.
As shown in fig. 1, the method for evaluating an interest area disclosed in the embodiment of the present application may include:
S101, determining an image to be evaluated of the region of interest.
The region of interest may be any regional physical entity on the map, such as a scenic spot, a block, a mall, etc.; the image to be evaluated comprises any image that can be used to evaluate the region of interest. The image to be evaluated can be acquired by a professional acquisition personnel under the conditions of different acquisition angles, different acquisition distances and the like by utilizing an acquisition device, can be acquired by a map user in a mode of acquiring the image and uploading the image to a background server, and can be acquired by mining network image data, and the embodiment of the application is not particularly limited.
Optionally, the image to be evaluated of the region of interest includes a street view image, and the street view image includes two parts of contents: the image and the positioning information corresponding to the image are positioning information, such as GPS coordinate information, when the acquisition equipment acquires the street view image; further, determining an image to be evaluated of the region of interest includes: and determining an image to be evaluated of the region of interest according to the position relation between the positioning information carried by the acquired street view image and the region of interest. Namely, in a large number of collected street view images, when the position relation between positioning information and the region of interest meets a position condition, the street view images are considered to belong to images to be evaluated of the region of interest, wherein the position condition comprises, but is not limited to: the positioning information carried in the street view image is in the preset area range of the region of interest, or the distance between the positioning information carried in the street view image and the designated position in the region of interest is smaller than a distance threshold value, and the distance threshold value can be adaptively set. By adopting the street view images, the images can be classified according to the positioning information, and the region of interest to which the images belong can be determined efficiently.
S102, determining an image evaluation result of the image to be evaluated in at least one dimension.
In the embodiment of the application, any available image processing technology can be utilized to perform identification processing on the image to be evaluated, so that the image to be evaluated is evaluated from at least one dimension. For example, the evaluation result of the image to be evaluated may be determined using a pre-trained evaluation model for evaluating the image.
The evaluation dimension of the image to be evaluated can be used for characterizing the region of interest from different angles, so that a map user can obtain more reference information about the region of interest when searching the region of interest. The evaluation dimension may include, but is not limited to, a beauty of the region of interest, a specific color of the region of interest, a scenic spot level to which the region of interest corresponds, a building style in the region of interest (including, but not limited to, a distinguishing style by region and a distinguishing style by year, etc.), a commercial bloom level of the region of interest, and a number of types of shops in the region of interest, among other consideration dimensions that may be used to evaluate the region of interest.
Correspondingly, the image evaluation result of the image to be evaluated under at least one dimension comprises: an image aesthetic degree evaluation result and an image characteristic degree evaluation result. The image aesthetic degree evaluation result is used for representing the region of interest from the perspective of the physical environment, such as the environment neatness degree, the environment beauty degree and the like of the region of interest, wherein the physical environment comprises a natural environment and an artificially created environment; the image specific color assessment results are used to characterize the region of interest from a human folk-custom perspective, e.g., the extent to which the current region of interest is distinct from other regions of interest in ethnic style and form. The image evaluation results of the image to be evaluated in at least one dimension may further include a scenic spot level evaluation result, a building style evaluation result, a business busyness evaluation result, a number of types of shops evaluation result, and the like.
For any region of interest, a large number of images to be evaluated can be collected for image evaluation, for example, a street view image data set I i＝{Ii,1,Ii,2,Ii,3..degree } corresponding to the region of interest a i, and each street view image in the set can have an image evaluation result in at least one dimension. The image evaluation result may be represented in the form of a specific score or evaluation grade, etc., and the embodiment of the application is not particularly limited. Taking the evaluation dimension-the aesthetic measure as an example, the aesthetic measure can be divided into 5 grades or grades, b= {0,1,2,3,4}, and each grade corresponds to an image aesthetic measure evaluation result; similarly, taking the specific color as an example, the specific color may be divided into 5 levels or grades, and c= {0,1,2,3,4}, where each grade corresponds to an image specific color evaluation result.
S103, evaluating the region of interest according to an image evaluation result of the image to be evaluated in at least one dimension.
Because each region of interest can comprise a large number of images to be evaluated, for each evaluation dimension, the image evaluation results of the images to be evaluated can be comprehensively considered, and the region evaluation results of the region of interest under the evaluation dimension are determined, for example, in the images to be evaluated of a certain region of interest, most of the image aesthetic degree evaluation results are excellent, and then the region evaluation results of the region of interest in the aspect of aesthetic degree can be determined to be excellent; further, after determining the region evaluation results of the region of interest under each evaluation dimension, the region evaluation results of each dimension can be comprehensively considered, and the comprehensive evaluation results of the region of interest can be determined.
According to the technical scheme provided by the embodiment of the application, the region of interest is evaluated by utilizing the image evaluation result of the image to be evaluated of the region of interest under at least one dimension, and the objectivity of the image evaluation result ensures the evaluation objectivity of the region of interest because the image evaluation result does not depend on artificial subjective evaluation, so that the problem of poor evaluation objectivity of the existing region of interest is solved, and the objectivity and accuracy of the region of interest evaluation are improved; moreover, the region of interest is evaluated based on the image evaluation result, and the field investigation and evaluation by related personnel are not needed, so that the labor and time cost is reduced, the efficiency of the region of interest evaluation is improved, the problem of low efficiency of the existing region of interest evaluation is solved, and the timeliness of the region of interest evaluation is also ensured; meanwhile, the multidimensional image evaluation result also ensures the multidimensional degree of the evaluation of the region of interest, solves the problem of single evaluation dimension of the existing region of interest, and enriches the evaluation dimension of the region of interest by only considering the standard scenic spot grade corresponding to the region of interest.
Fig. 2 is a flowchart of another method for evaluating a region of interest according to an embodiment of the present application, which is further optimized and expanded based on the above technical solution, and may be combined with the above various alternative embodiments. As shown in fig. 2, the method may include:
s201, determining an image to be evaluated of the region of interest.
S202, determining an image evaluation result of the image to be evaluated in at least one dimension by using the image evaluation model.
The image evaluation model is obtained by training based on a sample image of a sample region of interest and a labeling evaluation result of the sample image in at least one dimension. In the embodiment of the present application, samples involved in model training are obtained by using large-scale random images and a large number of user labels, for example, a sample region of interest set may be denoted as a, any sample region of interest a i∈A＝{A1,A2,A3, a sample image set corresponding to any sample region of interest a i may be denoted as I i＝{Ii,1,Ii,2,Ii,3. The labeling evaluation result of each sample image can be expressed in the form of specific score or evaluation grade, and the embodiment of the application is not particularly limited.
For the labeling evaluation result (or called a labeling classification value) of each sample image in each dimension, multiple people can be adopted for labeling at the same time, then the target labeling evaluation result of each sample image in each dimension is determined according to the number of people corresponding to each labeling evaluation result, for example, the labeling evaluation result with the largest number of labeling people is used as the target labeling evaluation result, and then the target labeling evaluation result is used in the model training process. Compared with the traditional mode, the method can learn the relation between the image and the image evaluation result of each dimension based on the big data thought, so that the subsequent image evaluation is more objective and accords with the evaluation standard of the user, and can improve the objectivity of the sample image labeling evaluation result used for model training based on the big data thought, ensure the confidence level of the image evaluation model and lay a foundation for obtaining objective and accurate interest region evaluation result subsequently.
Optionally, determining, by using the image evaluation model, an image evaluation result of the image to be evaluated in at least one dimension includes: and determining image evaluation results of the images to be evaluated under different dimensions by using an image evaluation model trained in advance based on multi-task learning. Multitasking (Multi-TASK LEARNING) is a machine learning method that learns multiple related tasks together based on a shared representation (Shared Representation). In the model training process, a sample image can be used as input, and a labeling evaluation result of the sample image under at least one dimension is used as output at the same time, so that a multi-task image evaluation model is obtained through training based on any available neural network structure. By using an image evaluation model based on the multitasking learning training, the efficiency of image evaluation can be improved.
Furthermore, determining an image evaluation result of the image to be evaluated in at least one dimension using the image evaluation model may further include: and respectively determining image evaluation results of the images to be evaluated in different dimensions by utilizing an image evaluation model which is independently trained for each dimension. In the process of training the model for each dimension independently, a sample image can be used as input, the annotation evaluation result of the sample image in each dimension is used as output, and the image evaluation model in each dimension is obtained through training based on any available neural network model.
The image evaluation model in the embodiment of the application comprises a deep neural network image classification model based on a convolutional neural network, and the neural network model can be selected from, but not limited to, VGG (Visual Geometry Group Network) models, resNet (Residual Network) models, inception models and the like.
S203, evaluating the region of interest according to an image evaluation result of the image to be evaluated in at least one dimension.
According to the technical scheme provided by the embodiment of the application, firstly, the image evaluation model is utilized to determine the image evaluation result of the image to be evaluated under at least one dimension, so that the automatic scoring of the image to be evaluated is realized, the efficiency of image evaluation is improved, the accuracy of the image evaluation result is ensured, and then the region of interest is evaluated by utilizing the image evaluation result. The image evaluation result does not depend on artificial subjective evaluation, so that the objectivity of the image evaluation result ensures the evaluation objectivity of the region of interest; the efficiency of image evaluation is improved, timeliness and evaluation efficiency of the evaluation of the region of interest are guaranteed, and further the problems of poor objectivity and low evaluation efficiency of the conventional evaluation of the region of interest are solved; the multidimensional image evaluation result also ensures the multidimensional degree of the evaluation of the region of interest, solves the problem of single evaluation dimension of the existing region of interest, and enriches the evaluation dimension of the region of interest.
Fig. 3 is a flowchart of another method for evaluating a region of interest according to an embodiment of the present application, which is further optimized and expanded based on the above technical solution, and may be combined with the above various alternative embodiments. Specifically, the embodiment of the present application will be exemplarily described below taking an example in which the image evaluation model is a neural network model trained in advance based on multitasking learning. As shown in fig. 3, the method may include:
s301, determining an image to be evaluated of the region of interest.
S302, extracting image features of the image to be evaluated by utilizing a feature extraction network in the image evaluation model.
S303, determining image evaluation results of the image to be evaluated under different dimensions by using prediction networks corresponding to different dimensions in the image evaluation model based on the image characteristics.
The feature extraction network may be a convolutional neural network, and the prediction network corresponding to different dimensions may include a multi-layer fully connected network, that is, in the model training process, model training operations may be performed based on the convolutional neural network and the multi-layer fully connected network corresponding to a plurality of dimensions (two or more).
Optionally, in the image evaluation model pre-trained based on the multi-task learning, the objective function is related to weights of network branches in the image evaluation model and loss functions of prediction networks corresponding to different dimensions in the image evaluation model. By way of example, the objective function L in the image evaluation model may be expressed using the following formula:
wherein W represents a weight matrix of a feature extraction network in the image evaluation model, W m and W n represent weight matrices of prediction networks corresponding to different dimensions in the image evaluation model, the total number of W m and W n corresponds to the number of dimensions of the image evaluation, lambda represents a model parameter or superparameter, lambda can be an empirical value or adaptively adjusted during model training, I represents image data of a sample image of an input model, Y m and Y n represent labeling evaluation results of the sample image under different dimensions in a model training process, L m(W,Wm,I,Ym) and L n(W,Wn,I,Yn) represent loss functions of a prediction network corresponding to the different dimensions, and I W I 2、||Wm||2、||Wn||2 respectively represent two norms of a corresponding weight matrix. Specifically, L m(W,Wm,I,Ym) and L n(W,Wn,I,Yn) may be respectively softmax cross entropy loss functions, taking L m(W,Wm,I,Ym) as an example, and the functional form may be expressed as follows:
Where N represents the number of sample images input, K represents the number of predicted classifications of the image evaluation result in the current dimension, f j represents the value of the jth classification in the predicted vector f representing the image evaluation result of the ith sample image in the current dimension, Representing the value representing the actual classification in the image evaluation prediction vector f for the i-th sample image in the current dimension. For a specific description of the softmax cross entropy loss function, reference may be made to the description of the principles of the prior art, and the embodiments of the present application are not described in detail.
According to the embodiment of the application, the objective function in the image evaluation model is customized in the multi-task model training process, the loss function of the prediction network of each dimension and the weight of each network branch are comprehensively considered, the model training accuracy is ensured, and the accuracy of the evaluation result of the image to be evaluated in each dimension is ensured.
S304, evaluating the region of interest according to image evaluation results of the image to be evaluated under different dimensions.
According to the technical scheme provided by the embodiment of the application, firstly, the image evaluation result of the image to be evaluated under at least one dimension is determined by utilizing the image evaluation model pre-trained based on multi-task learning, so that the automatic scoring of the image to be evaluated is realized, the efficiency of image evaluation is improved, the accuracy of the image evaluation result is ensured, and then the region of interest is evaluated by utilizing the image evaluation result. The image evaluation result does not depend on artificial subjective evaluation, so that the objectivity of the image evaluation result ensures the evaluation objectivity of the region of interest; the efficiency of image evaluation is improved, timeliness and evaluation efficiency of the evaluation of the region of interest are guaranteed, and further the problems of poor objectivity and low evaluation efficiency of the conventional evaluation of the region of interest are solved; the multidimensional image evaluation result also ensures the multidimensional degree of the evaluation of the region of interest, solves the problem of single evaluation dimension of the existing region of interest, and enriches the evaluation dimension of the region of interest.
Fig. 4 is a schematic diagram of an evaluation architecture of a region of interest according to an embodiment of the present application, specifically taking two dimensions of aesthetic evaluation and feature evaluation as an example, and illustrating the evaluation architecture according to the embodiment of the present application. As shown in fig. 4, the image to be evaluated may be a street view image, the image to be evaluated is input into an image evaluation model, the image to be evaluated is encoded by using a feature extraction network, namely a convolutional neural network, the image features are extracted, and then the image features are respectively input into an aesthetic degree prediction network and a characteristic degree prediction network to obtain an image aesthetic degree evaluation result and an image characteristic degree evaluation result of the image to be evaluated; furthermore, the beauty and the features of the region of interest can be evaluated based on the image beauty evaluation results and the image feature evaluation results of a plurality of images to be evaluated of the same region of interest. In a multitasking image assessment model for aesthetics and specific color, the objective function of the model can be expressed as follows:
Wherein W represents a weight matrix of a feature extraction network in the image evaluation model, W B and W C represent weight matrices of corresponding aesthetic degree prediction networks and characteristic degree prediction networks in the image evaluation model, lambda represents model parameters or superparameters, I represents image data of a sample image input in the model training process, Y B and Y C represent aesthetic degree annotation evaluation results and characteristic degree annotation evaluation results of the sample image respectively, and L B(W,WB,I,YB) and L C(W,WC,I,YC) represent loss functions of the corresponding aesthetic degree prediction networks and characteristic degree prediction networks. Specifically, L B(W,WB,I,YB) and L C(W,WC,I,YC) may be respectively softmax cross entropy loss functions, taking L B(W,WB,I,YB) as an example, and the functional form may be expressed as follows:
fig. 5 is a flowchart of another method for evaluating a region of interest according to an embodiment of the present application, which is further optimized and expanded based on the above technical solution, and may be combined with the above various alternative embodiments. As shown in fig. 5, the method may include:
s401, determining an image to be evaluated of the region of interest.
S402, determining an image evaluation result of the image to be evaluated in at least one dimension.
S403, determining a region evaluation result of the region of interest corresponding to at least one dimension according to the image evaluation result of the image to be evaluated in the at least one dimension.
S404, determining the comprehensive evaluation result of the region of interest according to the region evaluation result of the region of interest.
In the embodiment of the application, for any region of interest, a large number of images to be evaluated can be corresponding, each image to be evaluated has at least one dimension image evaluation result, for each dimension, the image evaluation results of the images to be evaluated in the dimension can be calculated according to a preset calculation strategy, the calculation result is taken as a region evaluation result of the region of interest in the dimension, for example, taking a preset calculation strategy as an average value, and the average value of the image evaluation results in the current dimension is taken as a region evaluation result of the region of interest in the dimension. After the region evaluation results of the region of interest under each dimension are obtained, the comprehensive evaluation results of the region of interest can be determined according to a preset comprehensive evaluation calculation strategy.
The preset comprehensive evaluation calculation strategy may be to calculate the comprehensive evaluation result of the region of interest by using a preset linear function or a preset nonlinear function related to the region evaluation result of each dimension, or calculate the comprehensive evaluation result of the region of interest according to the weight distribution of the preset region evaluation result (for example, the larger the evaluation result value or the higher the level, the larger the corresponding weight), or determine the comprehensive evaluation result of the region of interest by using a pre-trained comprehensive evaluation determination model. The comprehensive evaluation determination model is a pre-trained supervised learning model based on a supervised learning idea, and specifically, a large number of artificial comprehensive evaluation results of the region of interest and region evaluation results of the region of interest corresponding to each dimension can be utilized to perform model training to learn a fitting relation between the artificial comprehensive evaluation results and the region evaluation results of each dimension. After the comprehensive evaluation determination model is trained, the method can be directly used in the determination process of the comprehensive evaluation results of other interest areas.
Taking an image to be evaluated as a street view image, the evaluation dimension comprises attractiveness and specific chromaticity as examples, and an example of how to determine the comprehensive evaluation result of the region of interest is described. It is assumed that the image beauty assessment results (or referred to as the beauty score classification) of all street view images in the region of interest a i may be expressed as B i＝{Bi,1,Bi,2,Bi,3..and the image specific color assessment results (or referred to as the feature score classification) may be expressed as C i＝{Ci,1,Ci,2,Ci,3. The region evaluation result of the region of interest A i aiming at the aesthetic degree can be obtained by taking the mean valueRegional assessment results for specific chromaticity
Where n is the number of images in the street view image set of region of interest A i.
Further, the region of interest A i may be utilized to evaluate the results for the aesthetic regionsRegional assessment results for specific chromaticityThe comprehensive evaluation result S i of the comprehensive calculation interest area a i is calculated as follows:
The f (x) represents a comprehensive evaluation function, which may be a preset linear function or a preset nonlinear function, may be obtained through a weight distribution rule of a preset regional evaluation result, or may be obtained through training of the supervised learning model, which is not particularly limited in the embodiment of the present application.
S405, according to the search requirement of a user on the region of interest, transmitting at least one result of the region evaluation result and the comprehensive evaluation result of the region of interest to a user terminal; the user terminal is used for displaying at least one result.
For example, when a user sends a search requirement about an interest area to a background server through a map-like application of a user terminal, the server responds to the search requirement of the user and simultaneously sends basic information of the interest area and at least one of an area evaluation result and a comprehensive evaluation result to the user terminal for display.
According to the technical scheme provided by the embodiment of the application, the region of interest is evaluated by utilizing the image evaluation result of the image to be evaluated of the region of interest under at least one dimension, and the objectivity of the image evaluation result ensures the evaluation objectivity of the region of interest because the image evaluation result does not depend on artificial subjective evaluation, so that the problem of poor evaluation objectivity of the existing region of interest is solved, and the objectivity and accuracy of the region of interest evaluation are improved; moreover, the region of interest is evaluated based on the image evaluation result, and the field investigation and evaluation by related personnel are not needed, so that the labor and time cost is reduced, the efficiency of the region of interest evaluation is improved, the problem of low efficiency of the existing region of interest evaluation is solved, and the timeliness of the region of interest evaluation is also ensured; meanwhile, the multidimensional image evaluation result also ensures the multidimensional degree of the evaluation of the region of interest, solves the problem of single evaluation dimension of the existing region of interest, and enriches the evaluation dimension of the region of interest; by sending at least one of the region evaluation result and the comprehensive evaluation result of the region of interest to the user terminal for display, the effect of providing richer auxiliary decision reference information for the user when the user searches the region of interest is achieved.
Fig. 6 is a schematic diagram showing an interface of a region of interest evaluation result according to an embodiment of the present application, and specifically illustrates an example of a beauty score, a feature score, and a comprehensive score of a region of interest, which should not be construed as a specific limitation of the embodiment of the present application. As shown in fig. 6, when a user enables a map-like application on the terminal to search for an area of interest "xxx scenic spot", and enters a search result presentation interface, the interface includes a map presentation area 61 and an area of interest information presentation area 62. The region of interest information display area 62 may include basic information such as the name of the region of interest, the distance from the current location of the user, and the administrative region to which the user belongs, and uses star marks to display the evaluation results of multiple dimensions of "xxx sceneries": the aesthetic degree score, the characteristic degree score and the comprehensive score realize the effect of providing rich auxiliary reference information about the interest areas for the user, and are convenient for the user to make decision-making selection among different interest areas.
In addition, the lowest end of the search result display interface can also comprise functional controls such as collection, search periphery, navigation, addition of travel and the like. Of course, the specific layout of the search result display interface can be completely changed according to the requirements of application development design, and the embodiment of the application is not particularly limited.
Fig. 7 is a schematic structural diagram of an apparatus for evaluating a region of interest according to an embodiment of the present application, where the embodiment of the present application may be suitable for use in evaluating a region of interest in a map, and the apparatus may be implemented in software and/or hardware and may be integrated on any electronic device having computing capabilities, such as a server or the like.
As shown in fig. 7, the region of interest evaluation apparatus 700 disclosed in the embodiment of the present application may include an image to be evaluated determining module 701, an image evaluation result determining module 702, and a region of interest evaluating module 703, wherein:
an image to be evaluated determining module 701, configured to determine an image to be evaluated of a region of interest;
An image evaluation result determination module 702, configured to determine an image evaluation result of an image to be evaluated in at least one dimension;
the region of interest evaluation module 703 is configured to evaluate the region of interest according to an image evaluation result of the image to be evaluated in at least one dimension.
Optionally, the image evaluation result of the image to be evaluated in at least one dimension includes: an image aesthetic degree evaluation result and an image specific color degree evaluation result;
The image aesthetic degree evaluation result is used for representing the region of interest from the perspective of the physical environment, and the image characteristic degree evaluation result is used for representing the region of interest from the perspective of the human folk custom.
Optionally, the image evaluation result determining module 702 includes:
the model evaluation unit is used for determining an image evaluation result of the image to be evaluated under at least one dimension by utilizing the image evaluation model;
the image evaluation model is obtained by training based on a sample image of a sample region of interest and a labeling evaluation result of the sample image in at least one dimension.
Optionally, the model evaluation unit is specifically configured to:
And determining image evaluation results of the images to be evaluated under different dimensions by using an image evaluation model trained in advance based on multi-task learning.
Optionally, the model evaluation unit includes:
The image feature extraction subunit is used for extracting image features of the image to be evaluated by utilizing a feature extraction network in the image evaluation model;
And the evaluation result determining subunit is used for determining image evaluation results of the image to be evaluated under different dimensions by utilizing prediction networks corresponding to different dimensions in the image evaluation model based on the image characteristics.
Optionally, in the image evaluation model pre-trained based on the multi-task learning, the objective function is related to weights of network branches in the image evaluation model and loss functions of prediction networks corresponding to different dimensions in the image evaluation model.
Alternatively, the objective function L is expressed by the following formula:
Wherein, W represents a weight matrix of a feature extraction network in the image evaluation model, W m and W n represent weight matrices of prediction networks corresponding to different dimensions in the image evaluation model, λ represents model parameters, Y m and Y n represent labeling evaluation results of sample images under different dimensions in the model training process, L m(W,Wm,I,Ym) and L n(W,Wn,I,Yn) represent loss functions of the prediction networks corresponding to different dimensions, and I represents image data of the sample images.
Optionally, the region of interest evaluation module 703 includes:
The region evaluation result determining unit is used for determining a region evaluation result of the region of interest corresponding to at least one dimension according to the image evaluation result of the image to be evaluated in the at least one dimension;
And the comprehensive evaluation result determining unit is used for determining the comprehensive evaluation result of the region of interest according to the region evaluation result of the region of interest.
Optionally, the device disclosed in the embodiment of the present application further includes:
the evaluation result issuing module is used for sending at least one result of the region evaluation result and the comprehensive evaluation result of the region of interest to the user terminal according to the search requirement of the user on the region of interest after the comprehensive evaluation result determining unit executes the operation of determining the comprehensive evaluation result of the region of interest according to the region evaluation result of the region of interest;
the user terminal is used for displaying at least one result.
Optionally, the image to be evaluated comprises a street view image.
Optionally, the image to be evaluated determining module 701 is specifically configured to:
And determining an image to be evaluated of the region of interest according to the position relation between the positioning information carried by the acquired street view image and the region of interest.
The region of interest evaluation device 700 disclosed in the embodiment of the present application can execute any of the region of interest evaluation methods disclosed in the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. Reference is made to the description of any method embodiment of the application for details not described in this embodiment.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 8, fig. 8 is a block diagram of an electronic device for implementing the region of interest evaluation method in an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the embodiments of the application described and/or claimed herein.
As shown in fig. 8, the electronic device includes: one or more processors 801, memory 802, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the electronic device, including instructions stored in or on memory to display graphical information of a graphical user interface (GRAPHICAL USER INTERFACE, GUI) on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple electronic devices may be connected, each providing a portion of the necessary operations, e.g., as a server array, a set of blade servers, or a multiprocessor system. One processor 801 is illustrated in fig. 8.
Memory 802 is a non-transitory computer readable storage medium provided by embodiments of the present application. The memory stores instructions executable by the at least one processor to cause the at least one processor to perform the region of interest assessment method provided by the embodiments of the present application. The non-transitory computer-readable storage medium of the embodiment of the present application stores computer instructions for causing a computer to execute the region of interest evaluation method provided by the embodiment of the present application.
The memory 802 is used as a non-transitory computer readable storage medium, and may be used to store a non-transitory software program, a non-transitory computer executable program, and modules, such as program instructions/modules corresponding to the region of interest evaluation method in the embodiment of the present application, for example, the image to be evaluated determining module 701, the image evaluation result determining module 702, and the region of interest evaluating module 703 shown in fig. 7. The processor 801 executes various functional applications of the electronic device and data processing, i.e., implements the region of interest evaluation method in the above-described method embodiments, by running non-transitory software programs, instructions, and modules stored in the memory 802.
Memory 802 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of the electronic device, etc. In addition, memory 802 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 802 may optionally include memory remotely located with respect to processor 801, which may be connected via a network to the electronic device used to implement the region of interest assessment method of the present embodiment. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device for implementing the method for evaluating the interest area in the embodiment of the application can further comprise: an input device 803 and an output device 804. The processor 801, memory 802, input devices 803, and output devices 804 may be connected by a bus or other means, for example in fig. 8.
The input device 803 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the electronic device for implementing the region of interest assessment method in this embodiment, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointer stick, one or more mouse buttons, a track ball, a joystick, etc. input devices. The output means 804 may include a display device, auxiliary lighting means, such as a light emitting Diode (LIGHT EMITTING Diode), a haptic feedback means, and the like; haptic feedback devices such as vibration motors and the like. The display device may include, but is not limited to, a Liquid crystal display (Liquid CRYSTAL DISPLAY, LCD), an LED display, and a plasma display. In some implementations, the display device may be a touch screen.
Various implementations of the systems and techniques described here can be implemented in digital electronic circuitry, integrated circuitry, application SPECIFIC INTEGRATED Circuitry (ASIC), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
These computing programs, also referred to as programs, software applications, or code, include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device for providing machine instructions and/or data to a programmable processor, e.g., magnetic discs, optical disks, memory, programmable logic devices (Programmable Logic Device, PLD), including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device for displaying information to a user, for example, a Cathode Ray Tube (CRT) or an LCD monitor; and a keyboard and pointing device, such as a mouse or trackball, by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback; and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front-end component, e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here, or any combination of such background, middleware, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include: a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme provided by the embodiment of the application, the region of interest is evaluated by utilizing the image evaluation result of the image to be evaluated of the region of interest under at least one dimension, so that the problems of poor objectivity and low evaluation efficiency of the existing region of interest evaluation are solved, the objectivity of the region of interest evaluation is improved, and the efficiency of the region of interest evaluation is improved.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution disclosed in the present application can be achieved, and are not limited herein.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.
Claims (7)
1. A region of interest evaluation method, comprising:
determining an image to be evaluated of the region of interest;
extracting image features of the image to be evaluated by utilizing a feature extraction network in the image evaluation model;
based on the image characteristics, determining image evaluation results of the image to be evaluated under different dimensions by utilizing prediction networks corresponding to different dimensions in the image evaluation model; the feature extraction network in the image evaluation model is a convolutional neural network, and the prediction network corresponding to different dimensions comprises a plurality of layers of fully-connected networks; the image evaluation model is obtained by training based on a sample image of a sample interest area and labeling evaluation results of the sample image under different dimensions;
determining region evaluation results of the interest regions corresponding to the dimensions according to the image evaluation results of the image to be evaluated in different dimensions; the image evaluation result of the image to be evaluated comprises: image attractiveness evaluation results, image specific chromaticity evaluation results, scenic spot grade evaluation results, building style evaluation results, business luxury evaluation results and shop type quantity evaluation results; the image feature degree evaluation result refers to the degree that the current interest region is different from other interest regions in national style and form;
determining a comprehensive evaluation result of the region of interest according to the region evaluation result of the region of interest;
the determining the region evaluation result of each dimension corresponding to the region of interest comprises the following steps: for each dimension, calculating the image evaluation results of the multiple images to be evaluated in the dimension according to a preset calculation strategy as a mean value, and taking the calculation results as the region evaluation results of the region of interest in the dimension;
wherein, the determining the comprehensive evaluation result of the region of interest according to the region evaluation result of the region of interest includes: determining a comprehensive evaluation result of the region of interest according to a preset comprehensive evaluation calculation strategy according to the region evaluation result of the region of interest in each dimension;
In the image evaluation model trained in advance based on multitasking learning, the objective function L is expressed by the following formula:
Wherein W represents a weight matrix of a feature extraction network in the image evaluation model, W m and W n represent weight matrices of prediction networks corresponding to different dimensions in the image evaluation model, Y m and Y n represent labeling evaluation results of sample images under different dimensions in a model training process, L m(W,Wm,I,Ym) and L n(W,Wn,I,Yn) represent loss functions of the prediction networks corresponding to different dimensions, λ represents model parameters, and I represents image data of the sample images.
2. The method of claim 1, wherein after determining the comprehensive evaluation result of the region of interest based on the region evaluation result of the region of interest, the method further comprises:
According to the search requirement of the user on the region of interest, transmitting at least one result of the region evaluation result and the comprehensive evaluation result of the region of interest to a user terminal;
wherein the user terminal is configured to display the at least one result.
3. The method of claim 1, wherein the image to be evaluated comprises a street view image.
4. A method according to claim 3, wherein said determining an image to be evaluated of a region of interest comprises:
and determining an image to be evaluated of the region of interest according to the position relation between the positioning information carried by the acquired street view image and the region of interest.
5. A region of interest evaluation apparatus, comprising:
The image to be evaluated determining module is used for determining an image to be evaluated of the region of interest;
The image evaluation result determining module is used for determining an image evaluation result of the image to be evaluated in at least one dimension;
The interest area evaluation module is used for evaluating the interest area according to an image evaluation result of the image to be evaluated in the at least one dimension;
Wherein, the image evaluation result determining module includes:
The image feature extraction subunit is used for extracting image features of the image to be evaluated by utilizing a feature extraction network in the image evaluation model;
the evaluation result determining subunit is used for determining image evaluation results of the image to be evaluated under different dimensions by utilizing prediction networks corresponding to different dimensions in the image evaluation model based on the image characteristics; the feature extraction network in the image evaluation model is a convolutional neural network, and the prediction network corresponding to different dimensions comprises a plurality of layers of fully-connected networks; the image evaluation model is obtained by training based on a sample image of a sample interest area and labeling evaluation results of the sample image under different dimensions;
The region of interest evaluation module comprises:
The region evaluation result determining unit is used for determining the region evaluation result of each dimension corresponding to the region of interest according to the image evaluation results of the image to be evaluated in different dimensions, and comprises the following steps: for each dimension, calculating the image evaluation results of the multiple images to be evaluated in the dimension according to a preset calculation strategy as a mean value, and taking the calculation results as the region evaluation results of the region of interest in the dimension; the image evaluation result of the image to be evaluated comprises: image attractiveness evaluation results, image specific chromaticity evaluation results, scenic spot grade evaluation results, building style evaluation results, business luxury evaluation results and shop type quantity evaluation results; the image feature degree evaluation result refers to the degree that the current interest region is different from other interest regions in national style and form;
The comprehensive evaluation result determining unit is specifically used for determining a comprehensive evaluation result of the region of interest according to the region evaluation result of the region of interest in each dimension and a preset comprehensive evaluation calculation strategy;
In the image evaluation model trained in advance based on multitasking learning, the objective function L is expressed by the following formula:
Wherein W represents a weight matrix of a feature extraction network in the image evaluation model, W m and W n represent weight matrices of prediction networks corresponding to different dimensions in the image evaluation model, Y m and Y n represent labeling evaluation results of sample images under different dimensions in a model training process, L m(W,Wm,I,Ym) and L n(W,Wn,I,Yn) represent loss functions of the prediction networks corresponding to different dimensions, λ represents model parameters, and I represents image data of the sample images.
6. An electronic device, comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the region of interest assessment method of any one of claims 1-4.
7. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the region of interest assessment method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010381698.1A CN113627419B (en) | 2020-05-08 | 2020-05-08 | Region of interest evaluation method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010381698.1A CN113627419B (en) | 2020-05-08 | 2020-05-08 | Region of interest evaluation method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113627419A CN113627419A (en) | 2021-11-09 |
| CN113627419B true CN113627419B (en) | 2024-07-16 |
Family
ID=78377268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010381698.1A Active CN113627419B (en) | 2020-05-08 | 2020-05-08 | Region of interest evaluation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627419B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392007A (en) * | 2014-12-18 | 2015-03-04 | 西安电子科技大学宁波信息技术研究院 | Streetscape retrieval and identification method of intelligent mobile terminal |
| CN104933643A (en) * | 2015-06-26 | 2015-09-23 | 中国科学院计算技术研究所 | Scenic region information pushing method and device |
| WO2017166137A1 (en) * | 2016-03-30 | 2017-10-05 | 中国科学院自动化研究所 | Method for multi-task deep learning-based aesthetic quality assessment on natural image |
Family Cites Families (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011079442A1 (en) * | 2009-12-30 | 2011-07-07 | Nokia Corporation | Methods and apparatuses for facilitating content-based image retrieval |
| JP5565253B2 (en) * | 2010-10-04 | 2014-08-06 | 独立行政法人情報通信研究機構 | Tourist spot recommendation device and program |
| US20150206169A1 (en) * | 2014-01-17 | 2015-07-23 | Google Inc. | Systems and methods for extracting and generating images for display content |
| KR102594094B1 (en) * | 2015-12-29 | 2023-10-26 | 에스케이플래닛 주식회사 | Method and Apparatus for Providing Recommended Contents |
| JP6608311B2 (en) * | 2016-03-08 | 2019-11-20 | 株式会社Ｎｔｔドコモ | Image evaluation apparatus and image evaluation program |
| CN107305561B (en) * | 2016-04-21 | 2021-02-02 | 斑马网络技术有限公司 | Image processing method, device, device and user interface system |
| WO2018117662A1 (en) * | 2016-12-22 | 2018-06-28 | Samsung Electronics Co., Ltd. | Apparatus and method for processing image |
| KR102407815B1 (en) * | 2016-12-22 | 2022-06-13 | 삼성전자주식회사 | Apparatus and method for processing image |
| WO2018192245A1 (en) * | 2017-04-19 | 2018-10-25 | 中国电子科技集团公司电子科学研究院 | Automatic scoring method for photo based on aesthetic assessment |
| CN107330455A (en) * | 2017-06-23 | 2017-11-07 | 云南大学 | Image evaluation method |
| CN107766417A (en) * | 2017-09-08 | 2018-03-06 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for being used to submit POI data |
| CN107481238A (en) * | 2017-09-20 | 2017-12-15 | 众安信息技术服务有限公司 | Image quality measure method and device |
| CN108417029B (en) * | 2018-02-11 | 2020-11-06 | 东南大学 | Urban road network travel time estimation method based on self-adaptive multitask deep learning |
| CN108648104A (en) * | 2018-04-25 | 2018-10-12 | 河南聚合科技有限公司 | A kind of tourism big data co-construction and sharing based on cloud platform |
| CN111024101A (en) * | 2018-10-10 | 2020-04-17 | 上海擎感智能科技有限公司 | Navigation path landscape evaluation method and system, storage medium and vehicle-mounted terminal |
| CN109522950B (en) * | 2018-11-09 | 2022-04-22 | 网易传媒科技（北京）有限公司 | Image scoring model training method and device and image scoring method and device |
| CN109801256B (en) * | 2018-12-15 | 2023-05-26 | 华南理工大学 | Image aesthetic quality assessment method based on region of interest and global features |
| CN109948278A (en) * | 2019-03-29 | 2019-06-28 | 山东建筑大学 | A method and system for evaluating the aesthetics of building design based on width learning |
| CN110189291A (en) * | 2019-04-09 | 2019-08-30 | 浙江大学 | A general no-reference image quality assessment method based on multi-task convolutional neural network |
| CN110119689A (en) * | 2019-04-18 | 2019-08-13 | 五邑大学 | A kind of face beauty prediction technique based on multitask transfer learning |
| CN110298687B (en) * | 2019-05-23 | 2021-04-16 | 香港理工大学深圳研究院 | Regional attraction assessment method and device |
| CN110223292B (en) * | 2019-06-20 | 2022-01-25 | 厦门美图之家科技有限公司 | Image evaluation method, device and computer readable storage medium |
| CN110348525B (en) * | 2019-07-15 | 2022-02-22 | 北京百度网讯科技有限公司 | Map interest point acquisition method, device, equipment and storage medium |
| CN110378410B (en) * | 2019-07-16 | 2022-08-09 | 北京字节跳动网络技术有限公司 | Multi-label scene classification method and device and electronic equipment |
| CN110414489A (en) * | 2019-08-21 | 2019-11-05 | 五邑大学 | A face beauty prediction method based on multi-task learning |
-
2020
- 2020-05-08 CN CN202010381698.1A patent/CN113627419B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392007A (en) * | 2014-12-18 | 2015-03-04 | 西安电子科技大学宁波信息技术研究院 | Streetscape retrieval and identification method of intelligent mobile terminal |
| CN104933643A (en) * | 2015-06-26 | 2015-09-23 | 中国科学院计算技术研究所 | Scenic region information pushing method and device |
| WO2017166137A1 (en) * | 2016-03-30 | 2017-10-05 | 中国科学院自动化研究所 | Method for multi-task deep learning-based aesthetic quality assessment on natural image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113627419A (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114491773B (en) | Building scheme generation method and device, computer equipment and storage medium | |
| US11630560B2 (en) | Map information display method and apparatus, electronic device, and computer storage medium | |
| WO2020098252A1 (en) | Route planning method, server, and computer storage medium | |
| CN113157829B (en) | Method, device, electronic device and storage medium for comparing names of points of interest | |
| WO2022134478A1 (en) | Route recommendation method and apparatus, electronic device, and storage medium | |
| CN111292549B (en) | Method for establishing route time consumption estimation model, method for estimating route time consumption and corresponding device | |
| CN110399445A (en) | A kind of processing method of point of interest, device and equipment | |
| CN110766081A (en) | Interface image detection method, model training method and related device | |
| Zhang et al. | Multi-level urban street representation with street-view imagery and hybrid semantic graph | |
| CN114111813B (en) | High-precision map element updating method and device, electronic equipment and storage medium | |
| EP4047447A1 (en) | Route recommendation method and apparatus, electronic device, and storage medium | |
| CN113822291B (en) | Image processing method, device, equipment and storage medium | |
| CN112508163B (en) | Method and device for displaying subgraph in neural network model and storage medium | |
| CN113627419B (en) | Region of interest evaluation method, device, equipment and medium | |
| CN112989219B (en) | Point-of-interest recommendation method and device, electronic equipment and storage medium | |
| Fol et al. | 3D dataset generation using virtual reality for forest biodiversity | |
| CN115063726B (en) | Video classification method and device, electronic device and computer readable storage medium | |
| CN113819913B (en) | A path planning method and device, computer equipment and storage medium | |
| CN112686159B (en) | Allergic plant distribution statistical method and device | |
| CN112541496B (en) | Method, device, equipment and computer storage medium for extracting POI (point of interest) names | |
| CN113449754B (en) | Label matching model training and displaying method, device, equipment and medium | |
| CN117935278A (en) | Method and device for generating interest point data, related equipment and storage medium | |
| Tian et al. | RETRACTED ARTICLE: 3D motion trajectory prediction based on optical image remote sensing data in sports training simulation | |
| CN116992167B (en) | Address searching method, system and computer readable storage medium | |
| CN120107696B (en) | Remote sensing image object classification model online incremental updating method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |