CN113807139B - Method and device for determining the number of crop plants - Google Patents
Method and device for determining the number of crop plants Download PDFInfo
- Publication number
- CN113807139B CN113807139B CN202010538242.1A CN202010538242A CN113807139B CN 113807139 B CN113807139 B CN 113807139B CN 202010538242 A CN202010538242 A CN 202010538242A CN 113807139 B CN113807139 B CN 113807139B
- Authority
- CN
- China
- Prior art keywords
- crop
- connected domain
- determining
- plants
- image
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Abstract
本发明公开了一种作物株数的确定方法、确定装置。其中，该方法包括：获取目标区域的作物图像；确定作物图像中各个种植行区域中的作物连通域集合；将作物连通域集合中各个作物连通域的特征信息输入至连通域分级模型进行分析，得到作物连通域集合中各个作物连通域所属的级别，其中，不同的级别对应不同的植株数，连通域分级模型是通过多组数据训练得到的，每组数据均包括：样本连通域图像以及用于标记样本连通域所属级别的标签；基于级别确定各个种植行区域中的植株数；基于各个种植行区域中的植株数确定目标区域内的植株总数。本发明解决了人工进行计数造成的计数不准确、效率低下的技术问题。
The present invention discloses a method and device for determining the number of crop plants. The method comprises: obtaining a crop image of a target area; determining a set of crop connected domains in each planting row area in the crop image; inputting feature information of each crop connected domain in the crop connected domain set into a connected domain grading model for analysis to obtain the level to which each crop connected domain in the crop connected domain set belongs, wherein different levels correspond to different numbers of plants, and the connected domain grading model is obtained by training multiple groups of data, each group of data comprising: a sample connected domain image and a label for marking the level to which the sample connected domain belongs; determining the number of plants in each planting row area based on the level; and determining the total number of plants in the target area based on the number of plants in each planting row area. The present invention solves the technical problems of inaccurate counting and low efficiency caused by manual counting.
Description
Technical Field
The invention relates to the field of crop identification, in particular to a method and a device for determining the number of plants of crops.
Background
In the prior art, when the number of farmland crop plants is counted, a large amount of manual work is generally needed to do basic statistics or unmanned aerial vehicle inspection is adopted, statistics and estimation are carried out through photos shot by the unmanned aerial vehicle, but the two modes have the problems of time and labor consumption, more human errors and lower statistics accuracy.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the invention provides a method and a device for determining the plant number of crops, which at least solve the technical problems of inaccurate counting and low efficiency caused by manual counting.
According to one aspect of the embodiment of the invention, a method for determining the plant number of crops is provided, which comprises the steps of obtaining a crop image of a target area, determining a crop connected domain set in each planting row area in the crop image, inputting characteristic information of each crop connected domain in the crop connected domain set into a connected domain grading model for analysis to obtain the grade of each crop connected domain in the crop connected domain set, wherein different grades correspond to different plant numbers, the connected domain grading model is obtained through training through multiple groups of data, each group of data comprises a sample connected domain image and a label for marking the grade of the sample connected domain, determining the plant number in each planting row area based on the grade, and determining the total number of plants in the target area based on the plant number in each planting row area.
Optionally, before characteristic information of each crop connected domain in the crop connected domain set is input into a connected domain classification model for analysis, the method comprises the steps of obtaining a sample image, determining the crop connected domain in each planting row area in the sample image, classifying the crop connected domain according to a preset classification rule to obtain a classification result, and marking the crop connected domain based on the classification result to obtain multiple groups of data.
Optionally, grading the crop connected domain according to a preset grading rule to obtain a grading result, wherein the grading result comprises the steps of determining the number of good pixel points of the crop connected domain, determining a value range to which the number of pixel points belongs, determining a grade corresponding to the value range, and taking the determined grade as the grading result.
The method comprises the steps of extracting a vegetation region from a crop image, generating a first binary image corresponding to the vegetation region, determining a main direction of each planting line in a target region based on the vegetation connected region obtained by screening the connected region in the vegetation region, generating an external rectangle of the first binary image based on the length of each planting line in the main direction in the target region, establishing a coordinate system based on the width of the rectangle as an ordinate and the length direction as an abscissa, determining the number of non-vegetation pixels in the main direction, generating a curve for indicating the number distribution situation of the non-vegetation pixels in the coordinate system based on the number of the non-vegetation pixels, and cutting out the first binary image to obtain the planting line region according to the peak and the peak of the curve and the straight line in the straight line set corresponding to the main direction, wherein the straight line in the straight line set is used for indicating the position point set of the non-vegetation pixels between adjacent planting lines.
Optionally, determining the main direction of each planting row in the target area comprises carrying out Hough transformation on the first binarized image, outputting a list of polar coordinate system parameter pairs of the first binarized image in Hough space through a Hough space accumulator, and determining the main direction of the crop planting row based on the angle parameters in the list of the polar coordinate system parameter pairs, wherein the list of the polar coordinate system parameter pairs comprises at least one polar coordinate system parameter pair, and each polar coordinate system parameter pair comprises an angle and a radius.
Optionally, when the number of polar coordinate parameter pairs in the polar coordinate system parameter pair list is greater than a predetermined value, the polar coordinate angle in the first position in the polar coordinate system parameter pair list is used as the main direction of the crop planting row, or when the number of polar coordinate parameter pairs in the polar coordinate system parameter pair list is less than a predetermined value, the polar coordinate angle in the first position in the polar coordinate system parameter pair list is used as the main direction of the crop planting row.
Optionally, before the first one-value image is cut to obtain the planting row region according to the peak vertex of the curve and the straight lines in the straight line set corresponding to the main direction, smoothing the curve to obtain a smoothed target curve, and shifting the straight line set when the smoothed target curve comprises non-vegetation pixels, so that the target curve does not comprise the non-vegetation pixels.
Optionally, determining the crop connected domain set in each planting row area in the crop image comprises inputting the crop image into a crop identification model for analysis to obtain the crop connected domain set.
Optionally, the crop identification model and the connected domain classification model are the same machine learning model.
Optionally, acquiring the crop image of the target area includes receiving the crop image of the target area taken by the drone.
According to one aspect of the embodiment of the invention, another method for determining the plant number of crops is provided, which comprises the steps of obtaining a crop image of a target area, inputting the crop image into a machine learning model for analysis to obtain a crop connected domain set in each planting row area in the crop image and the grade of each crop connected domain in the crop connected domain set, wherein different grades correspond to different plant numbers, determining the plant number in each planting row area based on the grade, and determining the total plant number in the target area based on the plant number in each planting row area.
According to one aspect of the embodiment of the invention, another method for determining the plant number of crops is provided, which comprises the steps of obtaining a crop image of a target area, determining a crop connected domain set in each planting row area in the crop image, determining the level of each crop connected domain in the crop connected domain set, wherein different levels correspond to different plant numbers, determining the plant number corresponding to the levels based on the levels, determining the plant number in each planting row area based on the plant number, and determining the total number of plants in the target area based on the plant number in each planting row area.
According to another aspect of the embodiment of the invention, a calculation device for the plant number of crops is provided, which comprises an acquisition module, a first determination module and a second determination module, wherein the acquisition module is used for acquiring a crop image of a target area, the first determination module is used for determining a crop connected domain set in each planting row area in the crop image, characteristic information of each crop connected domain in the crop connected domain set is input into a connected domain classification model for analysis to obtain the grade of each crop connected domain in the crop connected domain set, different grades correspond to different plant numbers, the connected domain classification model is obtained through training of multiple groups of data, each group of data comprises a sample connected domain image and a label for marking the grade of the sample connected domain, the second determination module is used for determining the plant number in each planting row area based on the grade, and the calculation module is used for determining the total number of plants in the target area based on the plant number in each planting row area.
According to another aspect of the embodiment of the invention, an unmanned aerial vehicle is further provided, which comprises an image acquisition device and a processor, wherein the image acquisition device is used for acquiring a crop image of a target area, the processor is connected with the image acquisition device and used for determining a crop connected domain set in each planting row area in the crop image, characteristic information of each crop connected domain in the crop connected domain set is input into a connected domain grading model for analysis to obtain the grade of each crop connected domain in the crop connected domain set, different grades correspond to different plant numbers, the connected domain grading model is obtained through training of multiple groups of data, each group of data comprises a sample connected domain image and a label used for marking the grade of the sample connected domain, the plant number in each planting row area is determined based on the grade, and the total number of plants in the target area is determined based on the plant number in each planting row area.
According to another aspect of the embodiment of the invention, a spraying operation method is provided, which comprises the steps of determining the total number of plants in a target area by any one of crop plant number determining methods executed by spraying equipment, and determining the spraying dosage in the target area by the spraying equipment according to the total number of plants in the target area.
According to another aspect of the embodiment of the invention, a yield measuring and calculating method is provided, and the yield measuring and calculating method comprises the steps of adopting any one of the crop plant number determining methods to determine the total number of plants in a target area, and determining the total yield of the target area through the yield of the plants in the unit number of the target area and the total number of plants in the target area.
According to another aspect of the embodiment of the present invention, there is provided a nonvolatile storage medium including a stored program, wherein the apparatus in which the nonvolatile storage medium is controlled to execute any one of the determination methods of crop plants when the program runs.
According to another aspect of the embodiment of the present invention, there is provided a processor for running a program, wherein the program executes any one of the methods for determining the number of crop plants.
In the embodiment of the invention, a crop image of a target area is acquired by adopting a mode of identifying the crop image based on a deep learning model, a crop connected domain set in each planting row area in the crop image is determined, characteristic information of each crop connected domain in the crop connected domain set is input into a connected domain grading model for analysis, and the grades of each crop connected domain in the crop connected domain set are obtained, wherein different grades correspond to different plant numbers, the connected domain grading model is obtained through training of multiple groups of data, each group of data comprises a sample connected domain image and a label for marking the grade of the sample connected domain, the plant number in each planting row area is determined based on the grade, and the total number of plants in the target area is determined based on the plant number in each planting row area, so that the aim of calculating the plant number of the crops is fulfilled, the technical effect of quickly and efficiently obtaining the total number of the crop plants is achieved, and the technical problems of inaccurate counting and low efficiency caused by manual counting are solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a flow chart of a method for determining the number of plants in a crop plant according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a coordinate system established in accordance with an alternative embodiment of the present invention;
FIG. 3 is a schematic diagram of a frame for obtaining an image of a row of plants area in accordance with an alternative embodiment of the present invention;
FIG. 4 is a schematic diagram of a framework for smoothing curves according to an alternative embodiment of the present invention;
FIG. 5 is a flow chart of another method for determining plant number of crops according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a device for calculating the number of plants of a crop in accordance with an embodiment of the present invention;
fig. 7 is a schematic structural view of a unmanned aerial vehicle according to an embodiment of the present invention;
FIG. 8 is a flow chart of another method for determining plant number of crops according to an embodiment of the present invention;
Fig. 9 is a schematic diagram of an alternative statistical principle of the plant number of the crop according to the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to an embodiment of the present invention, there is provided an embodiment of a method of determining the number of crop plants, it being noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order different from that herein.
Fig. 1 is a method for determining the number of plants of a crop according to an embodiment of the present invention, as shown in fig. 1, the method includes the steps of:
step S102, acquiring a crop image of a target area;
Step S104, determining a crop connected domain set in each planting row area in the crop image;
Step S106, inputting characteristic information of each crop connected domain in the crop connected domain set into a connected domain classification model for analysis to obtain the grade of each crop connected domain in the crop connected domain set, wherein different grades correspond to different plant numbers, the connected domain classification model is obtained through training of multiple groups of data, and each group of data comprises a sample connected domain image and a label for marking the grade of the sample connected domain;
step S108, determining the number of plants in each planting row area based on the level;
step S110, determining the total number of plants in the target area based on the number of plants in each planting row area.
In the method for determining the plant number of the crops, firstly, a crop image of a target area is obtained, then a crop connected domain set in each planting row area in the crop image is determined, secondly, characteristic information of each crop connected domain in the crop connected domain set is input into a connected domain grading model for analysis, and the grade of each crop connected domain in the crop connected domain set is obtained, wherein different grades correspond to different plant numbers, the connected domain grading model is obtained through training of multiple groups of data, each group of data comprises a sample connected domain image and a label for marking the grade of the sample connected domain, then the plant number in each planting row area is determined based on the grade, finally, the total plant number in the target area is determined based on the plant number in each planting row area, and the purpose of calculating the plant number of the crops is achieved, so that the technical effect of quickly and efficiently obtaining the total plant number of the crops is achieved, and the technical problems of inaccurate counting and low efficiency caused by manual counting are solved.
The crop image is a photograph to be counted, wherein the number of plants in each planting line area is determined based on the level, the number of crop connected domains in each planting line area can be determined first, then the level to which each crop connected domain belongs is determined, then the number of plants in each crop connected domain is determined based on the level, and finally the number of plants in each planting line area is determined based on the number of plants.
In an optional embodiment of the application, before characteristic information of each crop connected domain in a crop connected domain set is input into a connected domain classification model for analysis, the method comprises the steps of obtaining a sample image, determining the crop connected domain in each planting row area in the sample image, classifying the crop connected domain according to a preset classification rule to obtain a classification result, and marking the crop connected domain based on the classification result to obtain multiple groups of data.
In some embodiments of the application, the crop connected domain is classified according to a preset classification rule to obtain a classification result, the number of good pixels of the crop connected domain can be determined, the value range to which the number of pixels belongs is determined, the level corresponding to the value range is determined, and the determined level is used as the classification result.
Specifically, the classification rule is related to the area size of the crop connected domain, the type of the crop and the planting experience, and the growth period of the crop can be established according to different grades in the classification, for example, if the pixel point of the connected domain of a certain crop in the seedling stage is 200-250, the pixel point is marked as a medium grade, and the corresponding density is 3 seedlings in one hole.
In some embodiments of the present application, before determining a crop connected domain set in each planting row region in a crop image, a vegetation region may be extracted from the crop image, and a first binary image corresponding to the vegetation region is generated, where the first binary image is determined based on a vegetation connected domain obtained by screening the connected domain in the vegetation region, and in an optional embodiment of the present application, a vegetation region is extracted from the regional image, and a first binary image corresponding to the vegetation region is generated, a Green index of each pixel point in the regional image may be determined first, for each pixel point, a magnitude of the Green index and a magnitude of a Green threshold may be compared, whether a pixel point is a pixel point in the vegetation region is determined according to a comparison result, a pixel point in the vegetation region is counted, and a first binary image is determined based on a statistics result, specifically, an extra Green index (ExG Green) is taken as an example, exg=2×green-Red-Blue, a pixel value of three channels is G, R, B, the above pixel points may be obtained by comparing the magnitude of the Green index with a magnitude of the Green index, the pixel point is greater than or equal to a threshold value, and the Green index is also greater than or equal to a threshold is set by a magnitude of the figure of zero, and the Green index is equal to a value is equal to or less than a threshold is equal to a threshold value which may be obtained by setting a magnitude of the Green index, and a Green index is greater than is equal to a value.
In some embodiments of the application, methods of screening vegetation connected domains include, but are not limited to, methods of manually setting thresholds, statistical screening, shape screening, texture screening, and the like.
Specifically, for example, the vegetation connected domain is screened by a shape screening method, for example, a green truck is parked at the field edge, the crop is an apple tree with a shape similar to a circle, and the vehicle is determined not to belong to the vegetation connected domain after geometric analysis.
Specifically, for example, the crop area range is determined by counting all the connected domain areas through a statistical screening method, and the crop area range is determined through a mode, a dense interval and other methods, and the vegetation connected domain in the area range is left for screening, for example, the vegetation connected domain area interval is [20,50] (unit/m 2), then the vegetation connected domain conforming to the area interval is left, for example, the size mode of the vegetation connected domain area is 30m2, and then the connected domain with the area of 30 square meters can be left.
It should be noted that, in order to improve the accuracy of the screening, the screening method may be used in combination, for example, a vehicle parked at the field, which accords with the super green index of the vegetation connected domain, and the shape is similar to that of the object, and then the area interval may be further combined to determine whether the vehicle is the vegetation connected domain.
FIG. 2 is a coordinate system established in accordance with an alternative embodiment of the present invention, as shown in FIG. 2, for generating an circumscribed rectangle of a first binarized image based on the length of each row of plants in the target area in the main direction, and establishing the coordinate system with the width direction of the rectangle as the ordinate and the length direction as the abscissa;
Fig. 3 is a schematic diagram of a frame for obtaining an image of a planting row area according to an alternative embodiment of the present invention, determining the number of non-vegetation pixels in a main direction, generating a curve 30 for indicating the number distribution situation of the non-vegetation pixels in a coordinate system based on the number of non-vegetation pixels, and cutting a first one-valued image to obtain the planting row area according to a peak vertex of the curve and a straight line 32 in a straight line set corresponding to the main direction, wherein the straight line in the straight line set is used for indicating a set of position points where the non-vegetation pixels are located between adjacent planting rows.
In an alternative embodiment of the application, the main directions of the planting rows in the target area are determined by carrying out Hough transformation on the first binarized image and outputting a list of polar coordinate system parameter pairs of the first binarized image in Hough space through a Hough space accumulator, and determining the main directions of the planting rows of the crops based on the angle parameters in the list of the polar coordinate system parameter pairs, wherein the list of the polar coordinate system parameter pairs comprises at least one polar coordinate system parameter pair, and each polar coordinate system parameter pair comprises an angle and a radius.
In some embodiments of the present application, when the number of polar coordinate parameter pairs in the polar coordinate system parameter pair list is greater than a predetermined value, the polar coordinate angle in the first position in the polar coordinate system parameter pair list is used as the main direction of the crop planting row, or when the number of polar coordinate parameter pairs in the polar coordinate system parameter pair list is less than a predetermined value, the polar coordinate angle in the first position in the polar coordinate system parameter pair list is used as the main direction of the crop planting row.
Fig. 4 is a schematic diagram of a frame for smoothing a curve according to an alternative embodiment of the present invention, before cutting a first one-valued image to obtain the planting row area according to the peak vertex of the curve and the straight lines in the straight line set corresponding to the main direction, the curve 40 may be smoothed to obtain a smoothed target curve 42, and when the smoothed target curve includes non-vegetation pixels, the straight line set is shifted so that the target curve does not include non-vegetation pixels.
It should be noted that, the smoothing method includes, but is not limited to, denoising after moving average, denoising after LOWESS smoothing, denoising after Univariate Spline fitting, denoising after savitzky_golay Filter smoothing, and denoising cases include, but are not limited to, correcting the value of the negative number after savitzky_golay Filter smoothing. When non-vegetation pixels are included in the curve before the smoothing process, the straight line set is shifted so as to enable the target curve not to contain the non-vegetation pixels, specifically, the straight line set can be shifted left and right in a certain neighborhood range if necessary, and the triggering condition of shifting can be that the horizontal axis point with zero accumulated value exists in the original accumulated curve in the neighborhood. The reason for the offset is that it is possible that after a peak has been smoothed, the distance is not the original true zero point, the translation is limited, a neighbor distance threshold (neighborhood) is set, and the neighborhood of the peak is searched for a point where the accumulated value of the accumulation curve before smoothing is zero. Furthermore, if the leftmost and rightmost border lines are missing, the border lines may be supplemented.
In an alternative embodiment of the application, determining the crop connected domain set in each planting row area in the crop image comprises inputting the crop image into a crop identification model for analysis to obtain the crop connected domain set.
In an alternative embodiment of the application, the crop identification model and the connected domain classification model are the same machine learning model.
In an alternative embodiment of the application, acquiring the crop image of the target area comprises receiving the crop image of the target area taken by the unmanned aerial vehicle.
Fig. 5 is another method for determining the number of plants of a crop according to an embodiment of the present invention, as shown in fig. 5, the method comprising the steps of:
step S502, acquiring a crop image of a target area;
step S504, determining a crop connected domain set in each planting row area in the crop image;
Step S506, determining the level of each crop connected domain in the crop connected domain set, wherein different levels correspond to different plant numbers;
Step S508, determining the number of plants corresponding to the level based on the level, and determining the number of plants in each planting row area based on the number of plants;
Step S510, determining the total number of plants in the target area based on the number of plants in each planting row area.
The method for determining the plant number of the crops comprises the steps of firstly obtaining a crop image of a target area, then determining a crop connected domain set in each planting row area in the crop image, secondly determining the level of each crop connected domain in the crop connected domain set, wherein different levels correspond to different plant numbers, then determining the plant number corresponding to the levels based on the levels, determining the plant number in each planting row area based on the plant number, and finally determining the plant total number in the target area based on the plant number in each planting row area, so that the aim of calculating the plant number of the crops is achieved, the technical effect of rapidly and efficiently obtaining the plant total number of the crops is achieved, and the technical problems of inaccurate counting and low efficiency caused by manual counting are solved.
Fig. 6 is a calculation device for the number of plants of a crop according to an embodiment of the present invention, the device including:
an acquisition module 60 for acquiring a crop image of a target area;
The first determining module 62 is configured to determine a set of crop connected domains in each planting row area in the crop image, input feature information of each crop connected domain in the set of crop connected domains to a connected domain classification model for analysis, and obtain a level to which each crop connected domain in the set of crop connected domains belongs, where different levels correspond to different plant numbers, the connected domain classification model is obtained through training multiple sets of data, and each set of data includes a sample connected domain and a label for marking the level to which the sample connected domain belongs;
a second determination module 64 for determining the number of plants in each row area based on the level;
A calculation module 66 for determining a total number of plants within the target area based on the number of plants in each row area.
The calculation device for the plant number of the crops is used for acquiring a crop image of a target area, a first determination module 62 for determining a set of crop connected domains in each planting row area in the crop image, inputting characteristic information of each crop connected domain in the set of crop connected domains into a connected domain grading model for analysis to obtain the grade of each crop connected domain in the set of crop connected domains, wherein different grades correspond to different plant numbers, the connected domain grading model is obtained through training of multiple groups of data, each group of data comprises a sample connected domain and a label for marking the grade of the sample connected domain, a second determination module 64 for determining the plant number in each planting row area based on the grade, and a calculation module 66 for determining the total number of plants in the target area based on the plant number in each planting row area, so that the aim of calculating the plant number of the crops is fulfilled, the technical effect of quickly and efficiently obtaining the total number of the crop plants is achieved, and the technical problems of inaccurate counting and low efficiency caused by manual counting are solved.
Fig. 7 is a unmanned aerial vehicle according to an embodiment of the present invention, as shown in fig. 7, the unmanned aerial vehicle including:
An image acquisition device 70 for acquiring a crop image of a target area;
The processor 72 is connected with the image acquisition device, and is used for determining a crop connected domain set in each planting row region in the crop image, inputting characteristic information of each crop connected domain in the crop connected domain set into the connected domain classification model for analysis to obtain the grade to which each crop connected domain in the crop connected domain set belongs, wherein different grades correspond to different plant numbers, the connected domain classification model is obtained through training of multiple groups of data, each group of data comprises a sample connected domain image and a label for marking the grade to which the sample connected domain belongs, determining the plant number in each planting row region based on the grade, and determining the total number of plants in the target region based on the plant number in each planting row region.
The unmanned aerial vehicle comprises an unmanned aerial vehicle image acquisition device 70 used for acquiring a crop image of a target area, a processor 72 connected with the image acquisition device and used for determining a crop connected domain set in each planting row area in the crop image, inputting characteristic information of each crop connected domain in the crop connected domain set into a connected domain grading model for analysis to obtain the grade of each crop connected domain in the crop connected domain set, wherein different grades correspond to different plant numbers, the connected domain grading model is obtained through multi-group data training, each group of data comprises a sample connected domain image and a label used for marking the grade of the sample connected domain, the plant number in each planting row area is determined based on the grade, the total number of plants in the target area is determined based on the plant number in each planting row area, the purpose of calculating the plant number of the crops is achieved, the technical effect of quickly and efficiently obtaining the total number of the crop plants is achieved, and the technical problems of inaccurate counting and low efficiency caused by manual counting are solved.
Fig. 8 is another method for determining the number of plants of a crop according to an embodiment of the present invention, as shown in fig. 8, the method comprising the steps of:
s802, acquiring a crop image of a target area;
S804, inputting the crop images into a machine learning model for analysis to obtain a crop connected domain set in each planting row area in the crop images and the levels of each crop connected domain in the crop connected domain set, wherein different levels correspond to different plant numbers;
S806, determining the number of plants in each planting row area based on the level;
s808, determining the total number of plants in the target area based on the number of plants in each planting row area.
In the embodiment, firstly, a crop image of a target area is acquired, then, the crop image is input into a machine learning model for analysis to obtain a crop connected domain set in each planting row area in the crop image and the grade of each crop connected domain in the crop connected domain set, wherein different grades correspond to different plant numbers, secondly, the plant number in each planting row area is determined based on the grade, and finally, the total plant number in the target area is determined based on the plant number in each planting row area, so that the aim of calculating the plant number of crops is achieved, the technical effect of rapidly and efficiently obtaining the total number of crop plants is achieved, and the technical problems of inaccurate counting and low efficiency caused by manual counting are solved.
Fig. 9 is a schematic diagram of an alternative statistical principle of the plant number of the crop according to the present invention, as shown in fig. 9, the statistical principle mainly includes the following steps:
Firstly, a large number of pictures of a farmland are shot down to form a farmland photo set, a region where vegetation is located in the pictures is extracted by utilizing an algorithm, all connected domains are screened, connected domains of the vegetation are left, a binary image of the vegetation is generated, a method of Hough detection straight lines is utilized to obtain a main direction of a planting row, then the main direction is taken as a width direction to generate an external rectangle of the binary image, the width (main direction) of the external rectangle is taken as an ordinate, the length direction is taken as an abscissa, the number of non-vegetation pixels in the main direction is accumulated to obtain an accumulated curve, the accumulated curve is subjected to smoothing treatment, peak peaks of the smoothed curve are calculated, the connected domains in the planting row regions of the binary image are cut according to a straight line set determined by the peak peaks and the main direction, finally, the connected domains in the planting row regions are subjected to condition screening one by one, and the connected domains meeting the condition are marked in a grading mode according to appointed characteristics, and a corresponding crop connected domain marking set is generated.
Secondly, training the training data set through a depth network to obtain a deep learning model, wherein the testing data set is used for tuning up parameters, selecting parameters corresponding to an effect optimal model, and the verification data set is used for measuring optimal performance, and finally obtaining a crop connected domain hierarchical counting model.
In order to perform the spraying operation more quickly and efficiently, according to another aspect of the embodiment of the present invention, there is also provided a spraying operation method, specifically, the above-mentioned method for determining the number of plants in the target area is performed by using the spraying apparatus, firstly, the total number of plants in the target area can be determined, then, the spraying apparatus determines the spraying dose in the target area according to the total number of plants in the target area, for example, when the spraying dose is 0.5 liter when the spraying dose is a pesticide, 1000 plants can be covered, and when the total number of plants in the target area is 10000 plants, the spraying apparatus should spray 5 liters according to the corresponding proportion.
In order to more accurately estimate the yield of crops in a certain area, according to another aspect of the embodiment of the invention, a yield measuring method is provided, specifically, the total number of plants in the target area can be determined by adopting any one of the above-mentioned methods for determining the number of plants of crops, the total yield of the target area is determined by the unit number of plants in the target area and the total number of plants in the target area, for example, when the crops are corn, the average corn yield of each corn plant can be determined according to statistical calculation, then the total number of corn plants in a certain area is determined by adopting the above-mentioned method for determining the number of plants of crops, and then the average corn yield of each corn plant is multiplied by the total number of corn plants in the area, so that a more accurate yield value can be obtained.
According to another aspect of the embodiment of the present invention, there is provided a nonvolatile storage medium including a stored program, wherein the apparatus in which the nonvolatile storage medium is controlled to execute any one of the determination methods of crop plants when the program runs.
Specifically, the above-mentioned nonvolatile storage medium is used to store program instructions that perform the following functions, implementing the following functions:
The method comprises the steps of obtaining a crop image of a target area, determining a crop connected domain set in each planting row area in the crop image, inputting characteristic information of each crop connected domain in the crop connected domain set into a connected domain grading model for analysis to obtain the grade of each crop connected domain in the crop connected domain set, wherein different grades correspond to different plant numbers, the connected domain grading model is obtained through training of multiple groups of data, each group of data comprises a sample connected domain image and a label for marking the grade of the sample connected domain, determining the planting number in each planting row area based on the grade, and determining the total number of plants in the target area based on the plant number in each planting row area.
According to another aspect of the embodiment of the present invention, there is provided a processor for running a program, wherein the program executes any one of the methods for determining the number of crop plants.
Specifically, the above processor is configured to call program instructions in the memory, and implement the following functions:
The method comprises the steps of obtaining a crop image of a target area, determining a crop connected domain set in each planting row area in the crop image, inputting characteristic information of each crop connected domain in the crop connected domain set into a connected domain grading model for analysis to obtain the grade of each crop connected domain in the crop connected domain set, wherein different grades correspond to different plant numbers, the connected domain grading model is obtained through training of multiple groups of data, each group of data comprises a sample connected domain image and a label for marking the grade of the sample connected domain, determining the planting number in each planting row area based on the grade, and determining the total number of plants in the target area based on the plant number in each planting row area.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present invention, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, for example, may be a logic function division, and may be implemented in another manner, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. The storage medium includes a U disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, etc. which can store the program code.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.
Claims (17)
1. A method for determining the number of plants of a crop, comprising:
acquiring a crop image of a target area;
The method comprises the steps of extracting a vegetation region from a crop image, generating a first binarization image corresponding to the vegetation region, determining a main direction of each planting row in a target region based on a vegetation connected domain obtained by screening the connected domain in the vegetation region, generating an external rectangle of the first binarization image based on the length of each planting row in the main direction in the target region, establishing a coordinate system by taking the width of the rectangle as an ordinate and the length direction as an abscissa, determining the number of non-vegetation pixels in the main direction, generating a curve for indicating the number distribution situation of the non-vegetation pixels in the coordinate system based on the number of the non-vegetation pixels, and cutting the first binarization image to obtain a planting row region according to the peak and the vertex of the curve and a straight line in a straight line set corresponding to the main direction, wherein the straight line in the straight line set is used for indicating a position point set where the non-vegetation pixels are located between adjacent planting rows;
Determining a crop connected domain set in each planting row area in the crop image;
Inputting characteristic information of each crop connected domain in the crop connected domain set into a connected domain classification model for analysis to obtain the grade of each crop connected domain in the crop connected domain set, wherein different grades correspond to different plant numbers, the connected domain classification model is obtained through training of multiple groups of data, and each group of data comprises a sample connected domain image and a label for marking the grade of the sample connected domain;
determining the number of plants in each planting row area based on the level;
And determining the total number of plants in the target area based on the number of plants in each planting row area.
2. The method of claim 1, wherein determining characteristic information of each crop connected domain in the set of crop connected domains before inputting the characteristic information into a connected domain classification model for analysis comprises:
Acquiring a sample image;
Determining crop communication domains in each planting row area in the sample image;
Classifying the crop connected domain according to a preset classification rule to obtain a classification result;
And marking the crop connected domain based on the grading result to obtain the plurality of groups of data.
3. The method according to claim 2, wherein grading the crop connected domain according to a preset grading rule to obtain a grading result comprises:
Determining the number of pixel points of the crop communication domain;
determining a value range to which the number of the pixel points belongs;
and determining the level corresponding to the value range, and taking the determined level as the grading result.
4. The method of claim 1, wherein determining the main direction of each row of plants in the target area comprises:
and determining the main direction of the crop planting row based on the angle parameters in the polar coordinate system parameter pair list, wherein the polar coordinate system parameter pair list comprises at least one polar coordinate system parameter pair, and each polar coordinate system parameter pair comprises an angle and a radius.
5. The method according to claim 4, comprising:
When the number of the polar coordinate parameter pairs in the polar coordinate system parameter pair list is larger than a preset value, taking the polar coordinate angle at the first position in the polar coordinate system parameter pair list as the main direction of the crop planting row, or
And when the number of the polar coordinate parameter pairs in the polar coordinate system parameter pair list is smaller than a preset value, taking the polar coordinate angle at the first position in the polar coordinate system parameter pair list as the main direction of the crop planting row.
6. The method of claim 1, wherein before cutting the first binarized image to obtain the plant row area according to the peak vertex of the curve and the straight lines in the straight line set corresponding to the main direction, the method further comprises:
performing smoothing treatment on the curve to obtain a target curve after the smoothing treatment;
when the target curve after the smoothing processing comprises non-vegetation pixels, the straight line set is shifted so that the target curve does not comprise the non-vegetation pixels.
7. The method of claim 1, wherein determining a set of crop connected domains in each row-of-plants region in the crop image comprises:
inputting the crop image into a crop identification model for analysis to obtain the crop connected domain set.
8. The method of claim 7, wherein the crop identification model and the connected domain classification model are the same machine learning model.
9. The method of any one of claims 1 to 8, wherein acquiring a crop image of the target area comprises:
And receiving crop images of the target area shot by the unmanned aerial vehicle.
10. A method for determining the number of plants of a crop, comprising:
acquiring a crop image of a target area;
The method comprises the steps of extracting a vegetation region from a crop image, generating a first binarization image corresponding to the vegetation region, determining a main direction of each planting row in a target region based on a vegetation connected domain obtained by screening the connected domain in the vegetation region, generating an external rectangle of the first binarization image based on the length of each planting row in the main direction in the target region, establishing a coordinate system by taking the width of the rectangle as an ordinate and the length direction as an abscissa, determining the number of non-vegetation pixels in the main direction, generating a curve for indicating the number distribution situation of the non-vegetation pixels in the coordinate system based on the number of the non-vegetation pixels, and cutting the first binarization image to obtain a planting row region according to the peak and the vertex of the curve and a straight line in a straight line set corresponding to the main direction, wherein the straight line in the straight line set is used for indicating a position point set where the non-vegetation pixels are located between adjacent planting rows;
Inputting the crop images into a machine learning model for analysis to obtain a crop connected domain set in each planting row area in the crop images and the levels of each crop connected domain in the crop connected domain set, wherein different levels correspond to different plant numbers;
determining the number of plants in each planting row area based on the level;
And determining the total number of plants in the target area based on the number of plants in each planting row area.
11. A method for determining the number of plants of a crop, comprising:
acquiring a crop image of a target area;
The method comprises the steps of extracting a vegetation region from a crop image, generating a first binarization image corresponding to the vegetation region, determining a main direction of each planting row in a target region based on a vegetation connected domain obtained by screening the connected domain in the vegetation region, generating an external rectangle of the first binarization image based on the length of each planting row in the main direction in the target region, establishing a coordinate system by taking the width of the rectangle as an ordinate and the length direction as an abscissa, determining the number of non-vegetation pixels in the main direction, generating a curve for indicating the number distribution situation of the non-vegetation pixels in the coordinate system based on the number of the non-vegetation pixels, and cutting the first binarization image to obtain a planting row region according to the peak and the vertex of the curve and a straight line in a straight line set corresponding to the main direction, wherein the straight line in the straight line set is used for indicating a position point set where the non-vegetation pixels are located between adjacent planting rows;
Determining a crop connected domain set in each planting row area in the crop image;
determining the level of each crop connected domain in the crop connected domain set, wherein different levels correspond to different plant numbers;
determining the number of plants corresponding to the level based on the level, and determining the number of plants in each planting row area based on the number of plants;
And determining the total number of plants in the target area based on the number of plants in each planting row area.
12. A device for calculating the number of plants of a crop, comprising:
The system comprises an acquisition module, a coordinate system, a first binarization image generation module and a second binarization module, wherein the acquisition module is used for acquiring a crop image of a target area, extracting a vegetation area from the crop image, generating a first binarization image corresponding to the vegetation area, the first binarization image is determined based on a vegetation connected domain obtained by screening the connected domain in the vegetation area, determining a main direction of each planting row in the target area, generating an external rectangle of the first binarization image based on the length of each planting row in the main direction in the target area, and establishing a coordinate system by taking the width of the rectangle as an ordinate and the length as an abscissa, determining the number of non-vegetation pixels in the main direction, and generating a curve for indicating the distribution condition of the number of the non-vegetation pixels in the coordinate system based on the number of the non-vegetation pixels, and cutting the first binarization image according to the peak top of the curve and straight lines in a straight line set corresponding to the main direction, wherein the straight lines in the straight line set are used for indicating a position point set between adjacent planting rows;
The first determining module is used for determining a crop connected domain set in each planting row area in the crop image, inputting characteristic information of each crop connected domain in the crop connected domain set into a connected domain division model for analysis to obtain the grade of each crop connected domain in the crop connected domain set, wherein different grades correspond to different plant numbers, the connected domain division model is obtained through training of multiple groups of data, and each group of data comprises a sample connected domain image and a label for marking the grade of the sample connected domain;
A second determining module for determining the number of plants in each planting row area based on the level;
and the calculation module is used for determining the total number of plants in the target area based on the number of plants in each planting row area.
13. An unmanned aerial vehicle, comprising:
The image acquisition device is used for acquiring crop images of the target area;
The processor is connected with the image acquisition device and is used for extracting a vegetation region from the crop image and generating a first binarization image corresponding to the vegetation region, wherein the first binarization image is determined based on a vegetation connected domain obtained by screening the connected domain in the vegetation region; determining the main direction of each planting row in the target area, generating an external rectangle of the first binarization image based on the length of each planting row in the main direction in the target area, establishing a coordinate system by taking the width of the rectangle as the ordinate and the length direction as the abscissa, determining the number of non-vegetation pixels in the main direction, generating a curve for indicating the number distribution condition of the non-vegetation pixels in the coordinate system based on the number of the non-vegetation pixels, cutting the first binarization image to obtain a planting row area according to the peak vertex of the curve and the straight line in the straight line set corresponding to the main direction, wherein the straight line in the straight line set is used for indicating the position point set of each adjacent planting row, the non-vegetation pixel is positioned in the crop connected domain set in the crop image, inputting the characteristic information of each crop connected domain in the crop connected domain set into a connected domain partition model for analysis, obtaining the corresponding levels of each crop connected domain in the crop connected domain set, wherein different corresponding levels are different levels, the connected domain data are used for obtaining a plurality of sets of training data connected domain data classification labels based on the number of each plant connected domain, the sample connected domain classification label is obtained in the sample connected domain classification image, and determining the total number of plants in the target area based on the number of plants in each planting row area.
14. A method of spraying operations comprising:
the spraying apparatus performs the method for determining the number of plants of the crop according to any one of claims 1 to 11, and determines the total number of plants in the target area;
And the spraying equipment determines the spraying dosage in the target area according to the total number of plants in the target area.
15. A method for yield measurement, comprising:
determining the total number of plants in the target area by the method for determining the number of plants of the crop according to any one of claims 1 to 11;
And determining the total yield of the target area through the yield of the unit number of plants in the target area and the total number of plants in the target area.
16. A non-volatile storage medium, characterized in that the storage medium comprises a stored program, wherein the program, when run, controls a device in which the storage medium is located to perform the method of determining the number of crop plants according to any one of claims 1 to 11.
17. A processor for running a program, wherein the program runs to perform the method of determining the number of crop plants according to any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010538242.1A CN113807139B (en) | 2020-06-12 | 2020-06-12 | Method and device for determining the number of crop plants |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010538242.1A CN113807139B (en) | 2020-06-12 | 2020-06-12 | Method and device for determining the number of crop plants |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113807139A CN113807139A (en) | 2021-12-17 |
| CN113807139B true CN113807139B (en) | 2025-03-07 |
Family
ID=78944150
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010538242.1A Active CN113807139B (en) | 2020-06-12 | 2020-06-12 | Method and device for determining the number of crop plants |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113807139B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427275B (en) * | 2015-10-29 | 2017-11-24 | 中国农业大学 | Crop field environment wheat head method of counting and device |
| WO2019041590A1 (en) * | 2017-08-31 | 2019-03-07 | 中国科学院微电子研究所 | Edge detection method using arbitrary angle |
| CN111259925B (en) * | 2020-01-08 | 2023-05-02 | 安徽大学 | K-means clustering and width mutation algorithm-based field wheat spike counting method |
-
2020
- 2020-06-12 CN CN202010538242.1A patent/CN113807139B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 基于机器视觉和GABP算法的播种检测研究;陈进;丁松;龚智强;练毅;;测控技术;20170918(09);18-21页摘要，章节2和图3-5，8，表1，章节3 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113807139A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiang et al. | Automated morphological traits extraction for sorghum plants via 3D point cloud data analysis | |
| US11275941B2 (en) | Crop models and biometrics | |
| CN109146948B (en) | Vision-based analysis method of crop growth phenotype parameter quantification and yield correlation | |
| Malambo et al. | Automated detection and measurement of individual sorghum panicles using density-based clustering of terrestrial lidar data | |
| Boogaard et al. | Robust node detection and tracking in fruit-vegetable crops using deep learning and multi-view imaging | |
| CN104598908B (en) | A kind of crops leaf diseases recognition methods | |
| Bai et al. | A fast and robust method for plant count in sunflower and maize at different seedling stages using high-resolution UAV RGB imagery | |
| Romeo et al. | Crop row detection in maize fields inspired on the human visual perception | |
| Sun et al. | High resolution 3D terrestrial LiDAR for cotton plant main stalk and node detection | |
| Zhou et al. | An integrated skeleton extraction and pruning method for spatial recognition of maize seedlings in MGV and UAV remote images | |
| US8577611B2 (en) | System and method for analyzing trees in LiDAR data using views | |
| CN113807138B (en) | Crop missing detection method and detection device | |
| Vázquez-Arellano et al. | Determination of stem position and height of reconstructed maize plants using a time-of-flight camera | |
| WO2025077309A1 (en) | Intelligent soil moisture content monitoring method based on remote sensing technology | |
| US8538695B2 (en) | System and method for analyzing trees in LiDAR data using views | |
| CN111598780A (en) | Terrain adaptive interpolation filtering method suitable for airborne LiDAR point cloud | |
| Song et al. | Non‐destructive automatic leaf area measurements by combining stereo and time‐of‐flight images | |
| CN103090946A (en) | Method and system for measuring single fruit tree yield | |
| CN102592118A (en) | Automatic detection method for time emergence of seedling of corns | |
| CN118279737A (en) | Weed detection method based on YOLOX deep learning | |
| Li et al. | Nondestructive detection of key phenotypes for the canopy of the watermelon plug seedlings based on deep learning | |
| CN119131700B (en) | A method and system for crop disease monitoring and damage assessment | |
| Martinez-Sanchez et al. | Skyline variations allow estimating distance to trees on landscape photos using semantic segmentation | |
| CN113011220A (en) | Spike number identification method and device, storage medium and processor | |
| Zeng et al. | Detecting and measuring fine roots in minirhizotron images using matched filtering and local entropy thresholding |
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 |