CN110705427A - Extraction processing method and device for remote sensing image target area - Google Patents
Extraction processing method and device for remote sensing image target area Download PDFInfo
- Publication number
- CN110705427A CN110705427A CN201910913977.5A CN201910913977A CN110705427A CN 110705427 A CN110705427 A CN 110705427A CN 201910913977 A CN201910913977 A CN 201910913977A CN 110705427 A CN110705427 A CN 110705427A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- sensing image
- image
- target area
- extracting
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method and a device for extracting and processing a target area of a remote sensing image, wherein the method comprises the following steps: acquiring an image edge part of a current remote sensing image; setting a rolling ball with a preset size in the current remote sensing image, and enabling the rolling ball to randomly roll in the current remote sensing image according to the edge part of the image; and acquiring a plurality of connected areas which are rolled by the rolling ball randomly, obtaining a target area according to the plurality of connected areas, and extracting the target area. According to the embodiment of the invention, the rolling ball is arranged to randomly roll in the current remote sensing image to obtain the plurality of connected areas, and the target area is obtained through the plurality of connected areas for automatic extraction, so that manual operation is saved, automatic extraction is realized, and the extraction precision and the extraction efficiency are improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for extracting and processing a target area of a remote sensing image.
Background
In order to improve the use efficiency of the satellite, the information hiding technology can be used for realizing the hierarchical authorization use, namely, the information is hidden to different degrees according to different authorities of users, so that the use efficiency of the satellite is improved. The information hiding technology is to hide secret information in another or decompose and hide the secret information in common information of a plurality of surfaces by utilizing the sensory redundancy of human sense organs to digital signals. The method is different from the traditional cryptosystem in that the content and the existence of the information are hidden, and the two can be matched with each other in practical application, namely the information is encrypted and then hidden, so that the method is a more effective method for ensuring the information safety.
Information hiding in remote sensing images belongs to the category of steganography of information hiding science. Steganography is an important branch of information hiding, and studies on how to hide confidential information. In view of the fact that the remote sensing image is greatly different from a common image and has wide application prospect, the information hiding technology of the remote sensing image has important practical value and research significance.
Before information hiding, a target region needs to be extracted firstly, the prior art usually adopts a manual extraction mode or an automatic crude extraction mode, needs a large amount of manual intervention, and the extraction precision is far from the ideal precision.
Disclosure of Invention
Because the existing method has the problems, the embodiment of the invention provides a method and a device for extracting and processing a target region of a remote sensing image.
In a first aspect, an embodiment of the present invention provides an extraction processing method for a target area of a remote sensing image, including:
acquiring an image edge part of a current remote sensing image;
setting a rolling ball with a preset size in the current remote sensing image, and enabling the rolling ball to randomly roll in the current remote sensing image according to the edge part of the image;
and acquiring a plurality of connected areas which are rolled by the rolling ball randomly, obtaining a target area according to the plurality of connected areas, and extracting the target area.
Optionally, the method for extracting and processing the remote sensing image target region further includes:
and extracting repeated extraction areas in the current remote sensing image by adopting a contour band diagram method according to the target area.
Optionally, the extracting the repeated extraction area in the current remote sensing image according to the target area by using a contour band diagram method specifically includes:
generating a first contour band diagram of the edge part of the image with direction information and a second contour band diagram of the target area according to an edge expansion algorithm;
and matching the first contour band diagram with the first contour band diagram according to image convolution to obtain a repeated extraction area similar to the target area, and extracting the repeated extraction area.
Optionally, the image edge portion comprises: the outer edge part of the display area of the current remote sensing image or the edge part formed by the dragging track of the mouse.
In a second aspect, an embodiment of the present invention further provides an apparatus for extracting and processing a target region of a remote sensing image, including:
the edge acquisition module is used for acquiring the image edge part of the current remote sensing image;
the rolling ball rolling module is used for setting a rolling ball with a preset size in the current remote sensing image and enabling the rolling ball to randomly roll in the current remote sensing image according to the edge part of the image;
and the area extraction module is used for acquiring a plurality of connected areas which are rolled by the rolling ball randomly, obtaining a target area according to the plurality of connected areas, and extracting the target area.
Optionally, the apparatus further comprises:
and the repeated extraction module is used for extracting a repeated extraction area in the current remote sensing image by adopting a contour band diagram method according to the target area.
Optionally, the repeated extraction module is specifically configured to:
generating a first contour band diagram of the edge part of the image with direction information and a second contour band diagram of the target area according to an edge expansion algorithm;
and matching the first contour band diagram with the first contour band diagram according to image convolution to obtain a repeated extraction area similar to the target area, and extracting the repeated extraction area.
Optionally, the image edge portion comprises: the outer edge part of the display area of the current remote sensing image or the edge part formed by the dragging track of the mouse.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, which when called by the processor are capable of performing the above-described methods.
In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium storing a computer program, which causes the computer to execute the above method.
According to the technical scheme, the rolling ball is arranged to randomly roll in the current remote sensing image to obtain the plurality of connected areas, and the target area is obtained through the plurality of connected areas to be automatically extracted, so that manual operation is saved, automatic extraction is realized, and extraction precision and extraction efficiency are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for extracting and processing a target region of a remote sensing image according to an embodiment of the present invention;
FIG. 2 is a schematic view illustrating a process of applying a selected area by a brush according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating operations of determining whether to set an edge boundary according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating the result of setting an edge boundary according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus for extracting and processing a target region of a remote sensing image according to an embodiment of the present invention;
fig. 6 is a logic block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
Fig. 1 shows a schematic flow chart of an extraction processing method for a remote sensing image target area provided by this embodiment, and includes:
s101, obtaining an image edge part of the current remote sensing image.
Wherein the image edge portion includes: the outer edge part of the display area of the current remote sensing image or the edge part formed by the dragging track of the mouse.
Specifically, by enlarging or reducing the image, the current display area contains the target area extracted, and the outer edge part of the display area of the current remote sensing image is acquired as the image edge part for subsequent calculation and processing.
Or, in order to improve the efficiency of the current region extraction, a primary extraction region of the target region is obtained by operating the mouse, that is, an edge portion formed by a dragging track of the mouse is used as an image edge portion for subsequent calculation and processing.
S102, setting a rolling ball with a preset size in the current remote sensing image, and enabling the rolling ball to randomly roll in the current remote sensing image according to the edge part of the image.
The rolling ball is a rolling ball model realized by a computer technology, the size of the rolling ball corresponding to the rolling ball model is determined according to specific requirements, for example, the length of a target area is 10cm, and the size of the rolling ball can be set to be 0.5 cm.
Specifically, the ball is randomly scrolled in an area determined by the edge portion of the image according to a random algorithm, and the area through which it scrolls is recorded.
S103, obtaining a plurality of connected areas which are rolled by the rolling ball randomly, obtaining a target area according to the plurality of connected areas, and extracting the target area.
Specifically, when the rolling ball passes through the boundary of a certain object in the image, the rolling ball is limited in the movement condition and cannot cross the boundary, so that the connected region formed after the region rolled by the rolling ball is recorded can be used for extracting the current object. Because the area corresponding to the target object may have a plurality of connected areas, the connected areas corresponding to the target object are combined to obtain the target area corresponding to the target object. For example, the rolling ball extracts two communication areas of the roof and the house body respectively, the two communication areas are combined to obtain a target area of the whole house, and the target area is extracted, namely the area corresponding to the house is extracted.
The robust segmentation is carried out on the image by adopting a rolling ball algorithm, the image edge part of the image is firstly calculated, then a rolling ball with a certain size is put into the image, and each communication area where the rolling ball travels is a segmented communication area of the image. The biggest advantage of the rolling-ball algorithm is its robustness, if the extracted edge (the dividing line of two regions) is partially broken, the traditional connectivity-based method will erroneously merge two neighboring regions into one, which the rolling-ball algorithm can avoid.
In order to balance the selection precision and the operation time, the embodiment supports the extraction of the sensitive content by using two methods of brush painting and boundary line setting.
For the brush smearing selection area, because the position and the size of the sensitive area in the remote sensing image are random, the image sensitive area is extracted by dragging a mouse to smear a local area of the image after a remote sensing image to be processed is loaded by adopting a brush-based image sensitive information interactive extraction method; meanwhile, the image can be enlarged or reduced through a mouse wheel, and the width of the brush can be controlled to be enlarged or reduced, wherein a circle shown in fig. 2 is the size of the brush, so that the sensitive content can be finely extracted. When a key area is extracted, the right side of the mouse is smeared to cancel the selected partial area until a satisfactory sensitive area position is obtained.
If the key area selected by painting the brush is not satisfactory, the boundary line of the sensitive area can be set by clicking the mouse, so that the sensitive area can be finely extracted, an edge boundary line is selected and set as shown in fig. 3, and the effect after the boundary line is set is shown in fig. 4. When the selected area meets the requirement, the primarily generated image completion result has no obvious deficiency, and a foundation can be laid for the subsequent fine completion.
According to the method, the rolling balls are arranged to randomly roll in the current remote sensing image to obtain the plurality of connected areas, and the target areas are obtained through the plurality of connected areas to automatically extract, so that manual operation is saved, automatic extraction is realized, and the extraction precision and the extraction efficiency are improved.
Further, on the basis of the above method embodiment, the method for extracting and processing the remote sensing image target area further includes:
and S104, extracting repeated extraction areas in the current remote sensing image by adopting a contour band diagram method according to the target area.
In order to accelerate the extraction speed, for the image with similar objects, a repeated extraction area similar to the target area in the current remote sensing image can be extracted through a contour band diagram method.
The traditional extraction of the remote sensing image target area basically completely depends on manual work, time and labor are wasted, the embodiment is combined with a matting method in the field of computer graphics in recent years, the interactive rapid extraction of the remote sensing image target area is realized, similar areas can be directly extracted, manpower is reduced, and efficiency is improved.
Further, on the basis of the above method embodiment, the S104 specifically includes:
s1041, generating a first contour band diagram of the image edge part with direction information and a second contour band diagram of the target area according to an edge expansion algorithm.
S1042, matching the first contour band diagram with the first contour band diagram according to image convolution to obtain a repeated extraction area similar to the target area, and extracting the repeated extraction area.
Specifically, when a repeated object in an image is extracted by adopting a contour band diagram method, firstly, the edge of the edge part of the image of the current remote sensing image is extracted, and then a contour band diagram with direction information is generated on the edge part of the image by utilizing an edge expansion algorithm, namely a first contour band diagram, wherein the first contour band diagram contains expanded edge direction information, and the edge part can be robustly matched by utilizing the first contour band diagram; for a selected template, such as a target region, its contour band diagram, i.e. the second contour band diagram, is also generated, and then matching is performed by conventional image convolution, and the whole process can be accelerated by FFT (Fast Fourier transform).
The extraction of the target area, which is used as the front end part of the information hiding system, can realize the quick extraction of the sensitive information area, and has important significance for the understanding and processing of the subsequent images. The embodiment mainly depends on an interactive mode to finish the efficient extraction of the image sensitive content, supports two methods of smearing by a brush and setting a boundary line to extract the sensitive content in order to balance the selection precision and the operation time, obtains an image result with separated backgrounds by using information obtained by image interaction through methods of edge extraction, image segmentation, similar structure searching and the like, and improves the efficiency of extracting the sensitive information area.
After the target area is extracted, the subsequent information hiding algorithm is different from the previous method of simply blurring a sensitive target, adding a mosaic or self-disordering an image. The target area provided by the embodiment is restored after being extracted, which is a local information hiding technology, the generated image is still clear and natural meaningful content, and the effect of 'no silver in this place for three hundred and two' is not generated in the original sensitive area of the image, so that the method has better hiding performance.
Fig. 5 is a schematic structural diagram of an extraction processing device for a remote sensing image target area provided in this embodiment, where the device includes: an edge acquisition module 501, a rolling ball rolling module 502, and an area extraction module 503, wherein:
the edge obtaining module 501 is configured to obtain an image edge portion of a current remote sensing image;
the rolling ball rolling module 502 is used for setting a rolling ball with a preset size in the current remote sensing image and enabling the rolling ball to randomly roll in the current remote sensing image according to the edge part of the image;
the region extraction module 503 is configured to obtain a plurality of connected regions in which the rolling ball rolls randomly, obtain a target region according to the plurality of connected regions, and extract the target region.
Specifically, the edge obtaining module 501 obtains an image edge portion of a current remote sensing image; the rolling ball rolling module 502 sets a rolling ball with a preset size in the current remote sensing image, and enables the rolling ball to randomly roll in the current remote sensing image according to the edge part of the image; the region extraction module 503 obtains a plurality of connected regions in which the rolling ball rolls randomly, obtains a target region according to the plurality of connected regions, and extracts the target region.
According to the method, the rolling balls are arranged to randomly roll in the current remote sensing image to obtain the plurality of connected areas, and the target areas are obtained through the plurality of connected areas to automatically extract, so that manual operation is saved, automatic extraction is realized, and the extraction precision and the extraction efficiency are improved.
Further, on the basis of the above embodiment of the apparatus, the apparatus further comprises:
and the repeated extraction module is used for extracting a repeated extraction area in the current remote sensing image by adopting a contour band diagram method according to the target area.
Further, on the basis of the above apparatus embodiment, the repeated extraction module is specifically configured to:
generating a first contour band diagram of the edge part of the image with direction information and a second contour band diagram of the target area according to an edge expansion algorithm;
and matching the first contour band diagram with the first contour band diagram according to image convolution to obtain a repeated extraction area similar to the target area, and extracting the repeated extraction area.
Further, on the basis of the above-mentioned embodiment of the apparatus, the image edge portion includes: the outer edge part of the display area of the current remote sensing image or the edge part formed by the dragging track of the mouse.
The extraction processing device for the remote sensing image target area described in this embodiment may be used to implement the above method embodiments, and the principle and technical effect are similar, which are not described herein again.
Referring to fig. 6, the electronic device includes: a processor (processor)601, a memory (memory)602, and a bus 603;
wherein,
the processor 601 and the memory 602 communicate with each other through the bus 603;
the processor 601 is used for calling the program instructions in the memory 602 to execute the methods provided by the above-mentioned method embodiments.
The present embodiments disclose a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the methods provided by the above-described method embodiments.
The present embodiments provide a non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the methods provided by the method embodiments described above.
The above-described embodiments of the apparatus are merely illustrative, and 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 network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
It should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for extracting and processing a target area of a remote sensing image is characterized by comprising the following steps:
acquiring an image edge part of a current remote sensing image;
setting a rolling ball with a preset size in the current remote sensing image, and enabling the rolling ball to randomly roll in the current remote sensing image according to the edge part of the image;
and acquiring a plurality of connected areas which are rolled by the rolling ball randomly, obtaining a target area according to the plurality of connected areas, and extracting the target area.
2. The method for extracting and processing the target area of the remote sensing image according to claim 1, further comprising:
and extracting repeated extraction areas in the current remote sensing image by adopting a contour band diagram method according to the target area.
3. The method for extracting and processing the target area of the remote sensing image according to claim 2, wherein the extracting of the repeated extraction area in the current remote sensing image by adopting a contour band diagram method according to the target area specifically comprises:
generating a first contour band diagram of the edge part of the image with direction information and a second contour band diagram of the target area according to an edge expansion algorithm;
and matching the first contour band diagram with the first contour band diagram according to image convolution to obtain a repeated extraction area similar to the target area, and extracting the repeated extraction area.
4. The method for extracting and processing the target area of the remote sensing image according to claim 1, wherein the image edge part comprises: the outer edge part of the display area of the current remote sensing image or the edge part formed by the dragging track of the mouse.
5. An extraction processing device for a remote sensing image target area is characterized by comprising:
the edge acquisition module is used for acquiring the image edge part of the current remote sensing image;
the rolling ball rolling module is used for setting a rolling ball with a preset size in the current remote sensing image and enabling the rolling ball to randomly roll in the current remote sensing image according to the edge part of the image;
and the area extraction module is used for acquiring a plurality of connected areas which are rolled by the rolling ball randomly, obtaining a target area according to the plurality of connected areas, and extracting the target area.
6. The apparatus for extracting and processing a target region from a remote sensing image according to claim 5, further comprising:
and the repeated extraction module is used for extracting a repeated extraction area in the current remote sensing image by adopting a contour band diagram method according to the target area.
7. The device for extracting and processing the target area of the remote sensing image according to claim 6, wherein the repeated extraction module is specifically configured to:
generating a first contour band diagram of the edge part of the image with direction information and a second contour band diagram of the target area according to an edge expansion algorithm;
and matching the first contour band diagram with the first contour band diagram according to image convolution to obtain a repeated extraction area similar to the target area, and extracting the repeated extraction area.
8. The apparatus for extracting a target region from a remote sensing image according to claim 5, wherein the image edge portion includes: the outer edge part of the display area of the current remote sensing image or the edge part formed by the dragging track of the mouse.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of extracting a target region from a remotely sensed image as claimed in any one of claims 1 to 4 when executing the program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method for extracting a target region from a remote sensing image according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910913977.5A CN110705427A (en) | 2019-09-25 | 2019-09-25 | Extraction processing method and device for remote sensing image target area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910913977.5A CN110705427A (en) | 2019-09-25 | 2019-09-25 | Extraction processing method and device for remote sensing image target area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110705427A true CN110705427A (en) | 2020-01-17 |
Family
ID=69198032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910913977.5A Pending CN110705427A (en) | 2019-09-25 | 2019-09-25 | Extraction processing method and device for remote sensing image target area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705427A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251924A (en) * | 2008-03-18 | 2008-08-27 | 清华大学 | Rolling Ball Segmentation Algorithm Based on Mask |
| CN101694718A (en) * | 2009-10-13 | 2010-04-14 | 西安电子科技大学 | Method for detecting remote sensing image change based on interest areas |
| CN101833668A (en) * | 2010-04-23 | 2010-09-15 | 清华大学 | A Detection Method of Similar Units Based on Contour Band Graph |
| US20140180095A1 (en) * | 2011-10-17 | 2014-06-26 | Butterfly Network, Inc. | Transmissive imaging and related apparatus and methods |
| CN103996044A (en) * | 2014-05-29 | 2014-08-20 | 天津航天中为数据系统科技有限公司 | Method and device for extracting targets through remote sensing image |
| CN105550685A (en) * | 2015-12-11 | 2016-05-04 | 哈尔滨工业大学 | Visual attention mechanism based region-of-interest extraction method for large-format remote sensing image |
| CN106295639A (en) * | 2016-08-01 | 2017-01-04 | 乐视控股（北京）有限公司 | A kind of virtual reality terminal and the extracting method of target image and device |
| CN108109144A (en) * | 2017-12-29 | 2018-06-01 | 广州柏视医疗科技有限公司 | Teat placement automatic testing method in a kind of molybdenum target image |
| CN108121991A (en) * | 2018-01-06 | 2018-06-05 | 北京航空航天大学 | A kind of deep learning Ship Target Detection method based on the extraction of edge candidate region |
| CN109583369A (en) * | 2018-11-29 | 2019-04-05 | 北京邮电大学 | A target recognition method and device based on target area segmentation network |
| CN109977965A (en) * | 2019-02-28 | 2019-07-05 | 北方工业大学 | A method and device for determining detection targets in remote sensing airport images |
-
2019
- 2019-09-25 CN CN201910913977.5A patent/CN110705427A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251924A (en) * | 2008-03-18 | 2008-08-27 | 清华大学 | Rolling Ball Segmentation Algorithm Based on Mask |
| CN101694718A (en) * | 2009-10-13 | 2010-04-14 | 西安电子科技大学 | Method for detecting remote sensing image change based on interest areas |
| CN101833668A (en) * | 2010-04-23 | 2010-09-15 | 清华大学 | A Detection Method of Similar Units Based on Contour Band Graph |
| US20140180095A1 (en) * | 2011-10-17 | 2014-06-26 | Butterfly Network, Inc. | Transmissive imaging and related apparatus and methods |
| CN103996044A (en) * | 2014-05-29 | 2014-08-20 | 天津航天中为数据系统科技有限公司 | Method and device for extracting targets through remote sensing image |
| CN105550685A (en) * | 2015-12-11 | 2016-05-04 | 哈尔滨工业大学 | Visual attention mechanism based region-of-interest extraction method for large-format remote sensing image |
| CN106295639A (en) * | 2016-08-01 | 2017-01-04 | 乐视控股（北京）有限公司 | A kind of virtual reality terminal and the extracting method of target image and device |
| CN108109144A (en) * | 2017-12-29 | 2018-06-01 | 广州柏视医疗科技有限公司 | Teat placement automatic testing method in a kind of molybdenum target image |
| CN108121991A (en) * | 2018-01-06 | 2018-06-05 | 北京航空航天大学 | A kind of deep learning Ship Target Detection method based on the extraction of edge candidate region |
| CN109583369A (en) * | 2018-11-29 | 2019-04-05 | 北京邮电大学 | A target recognition method and device based on target area segmentation network |
| CN109977965A (en) * | 2019-02-28 | 2019-07-05 | 北方工业大学 | A method and device for determining detection targets in remote sensing airport images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11170210B2 (en) | Gesture identification, control, and neural network training methods and apparatuses, and electronic devices | |
| CN110348496A (en) | A kind of method and system of facial image fusion | |
| CN106326872A (en) | Method for extracting gesture contour in augmented reality system | |
| CN110889374A (en) | Seal image processing method and device, computer and storage medium | |
| US10891801B2 (en) | Method and system for generating a user-customized computer-generated animation | |
| CN114782645A (en) | Virtual digital person making method, related equipment and readable storage medium | |
| CN118314267A (en) | A method for removing shadows from texture remapping process for 3D map reconstruction | |
| CN104463952A (en) | Human body scanning and modeling method | |
| CN116563702A (en) | Building graph extraction method, device, equipment and storage medium | |
| CN111191530A (en) | Method, device and equipment for town and bare land extraction based on sentinel remote sensing data | |
| CN114792285B (en) | Image processing method and processing device, electronic device and readable storage medium | |
| CN114723883A (en) | Three-dimensional scene reconstruction method, device, equipment and storage medium | |
| CN110705427A (en) | Extraction processing method and device for remote sensing image target area | |
| CN116167925A (en) | Image restoration method, device, electronic equipment and computer readable storage medium | |
| CN113077477A (en) | Image vectorization method and device and terminal equipment | |
| CN111652023B (en) | Mouth-type adjustment and live broadcast method and device, electronic equipment and storage medium | |
| CN105139341B (en) | A kind of GIF image edit methods and device | |
| CN115861110B (en) | Image processing method, device, electronic device and storage medium | |
| CN107133940A (en) | A kind of patterning process and terminal | |
| CN116403226A (en) | Unconstrained fold document image correction method, system, equipment and storage medium | |
| JP6700804B2 (en) | Information processing apparatus, information processing method, and program | |
| KR101715266B1 (en) | Line drawing method for 3d model using graphic accelerator and computer-readable recording medium storing for processing program using the same | |
| CN116128996A (en) | Floor plan processing method, device, electronic equipment and storage medium | |
| CN115457581A (en) | Table extraction method and device and computer equipment | |
| CN109872280B (en) | Denoising and simplifying method, device and system for three-dimensional plant leaf point cloud |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |
|
| RJ01 | Rejection of invention patent application after publication |