Regional change recognition method and system based on images collected by unmanned aerial vehicle

Abstract

The present invention discloses a method and system for identifying regional changes based on images collected by a drone. The method includes: controlling a drone to collect images within a preset area along a preset path at different times to obtain a first image and a second image of a real scene of the preset area that differ in time; performing feature comparison on the first and second images to identify at least one changed region within the preset area where the real scene has changed; determining the location information of the changed region, determining the sub-path to which each changed region belongs within the preset path based on the location information, and combining the sub-paths to obtain an identification path for the changed region; and controlling the drone according to the identification path to respectively collect changed images of the changed region and identify the changed images to identify the changed region. The present invention solves the problem of low efficiency in regional change identification in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV), and in particular to a method and system for identifying regional changes based on images collected by UAV. Background Art

[0002] Nowadays, drones are widely used in various fields. For example, by collecting images through drones and identifying the images, the current situation of an area in a certain time period can be efficiently obtained. Alternatively, by collecting images of an area at different times and analyzing the images, it can be determined whether the scene in the current area has changed.

[0003] In the existing technology, in order to identify more details of the area and ensure the accuracy of recognition, when collecting images, the drone is generally controlled to fly and collect according to the standard of collecting more details, including low flying speed, whether to stop and how long to stay, so as to improve the accuracy of recognition. However, in practice, since it is not known in advance which area will have an abnormality, the drone will fly according to the standard of collecting more details during the entire collection process, which leads to reduced recognition efficiency. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method and system for identifying regional changes based on images collected by drones, aiming to solve the problem of low efficiency in regional change identification in the prior art.

[0005] The present invention is achieved in that:

[0006] A method for identifying regional changes based on images collected by a drone, the method comprising:

[0007] Controlling the drone to collect images within a preset area along a preset path at different times to obtain a first image and a second image of a real scene of the preset area that are different in time;

[0008] Performing feature comparison on the first image and the second image to determine at least one changed area where the real scene within the preset area has changed;

[0009] Determining position information of the changed area, determining a sub-path to which each of the changed areas belongs in the preset path according to the position information, and combining the sub-paths to obtain an identification path of the changed area;

[0010] The UAV is controlled according to the identification path to respectively collect the change images of the change area and identify the change images to identify the change area.

[0011] Furthermore, in the above-mentioned method for identifying area changes based on images collected by a drone, the step of performing feature comparison on the first image and the second image to determine at least one changed area where the real scene within the preset area has changed includes:

[0012] Extracting key points from the first image and the second image respectively, and finding matching key point pairs in the first image and the second image using a feature matching algorithm;

[0013] Inconsistent feature points in the first image and the second image are screened out by comparing the key point pairs, and adjacent feature points are spatially clustered to form continuous regions to obtain the changed region.

[0014] Furthermore, in the above-mentioned method for identifying area changes based on images collected by a drone, wherein the preset path is an arcuate path, the arcuate path includes multiple sub-paths distributed horizontally and vertically, and the steps of determining, based on the position information, the sub-path to which each of the changed areas belongs in the preset path, and combining the sub-paths to obtain the identification path of the changed area include:

[0015] Respectively obtaining coordinate information of an outer boundary point of the preset area, position information of the changed area, and position information of the preset path;

[0016] Mapping the preset area, the changed area, and the preset path to a preset coordinate system according to the coordinate information of the outer boundary point of the preset area, the position information of the changed area, and the position information of the preset path;

[0017] determining the sub-path to which the changed area belongs based on positional relationship information of the changed area relative to the arcuate path;

[0018] The sub-paths are connected and combined in an arched manner in an initial order to obtain an identification path for the change area.

[0019] Furthermore, in the above-mentioned method for identifying area changes based on images collected by a drone, the step of determining the sub-path to which the changed area belongs based on the positional relationship information of the changed area relative to the arched path includes:

[0020] Obtaining a minimum bounding rectangle of each of the change regions, and determining whether the change region intersects with the subpath based on the minimum bounding rectangle;

[0021] If so, the intersecting sub-path and the two transverse sub-paths on both sides of the sub-path are used as the sub-paths;

[0022] If not, the lateral sub-paths on both sides of the change area are used as the branch paths.

[0023] Furthermore, in the above-mentioned method for identifying region changes based on images collected by a drone, the step of obtaining the minimum bounding rectangle of each of the changed regions includes:

[0024] Rotating the change region at set intervals within a preset angle range, and obtaining a circumscribed rectangle of each rotated change region;

[0025] Comparing the bounding rectangles obtained at all rotation angles, and determining a target bounding rectangle with the smallest area;

[0026] The target bounding rectangle is rotated in the opposite direction by the same angle to obtain the minimum bounding rectangle of the changed area.

[0027] Furthermore, the above-mentioned method for identifying regional changes based on images collected by drones further includes:

[0028] The distance spanned by the minimum circumscribed rectangle in the transverse direction is obtained, and a target sub-path is obtained by intercepting the sub-path according to the spanned distance, and the target sub-path is used as the final sub-path.

[0029] Furthermore, in the above-mentioned method for identifying regional changes based on images collected by a drone, after the step of using the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path as the sub-paths, the method further includes:

[0030] Obtain target areas formed by the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path, obtain the area of ​​the covering portion of the change area and the target area, and determine whether to remove the sub-path on one side according to the area.

[0031] Another object of the present invention is to provide a regional change recognition system based on images collected by drones, the system comprising:

[0032] An acquisition module is used to control the drone to acquire images within a preset area along a preset path at different times, thereby obtaining a first image and a second image of a real scene of the preset area that are different in time;

[0033] a comparison module, configured to perform feature comparison on the first image and the second image, thereby determining at least one changed region where the real scene within the preset region has changed;

[0034] a combining module, configured to determine position information of the changed area, determine a sub-path to which each changed area belongs in the preset path according to the position information, and combine the sub-paths to obtain an identification path of the changed area;

[0035] The recognition module is used to control the UAV according to the recognition path to respectively collect the change images of the change area and recognize the change images to identify the change area.

[0036] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps of any one of the methods described above.

[0037] Another object of the present invention is to provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-described methods when executing the program.

[0038] The present invention controls a drone to capture images within a preset area along a preset path at different times, thereby obtaining a first image and a second image of a real scene of the preset area that differ in time; performs feature comparison on the first image and the second image to identify at least one changed area within the preset area where the real scene has changed; determines the location information of the changed area, determines the sub-path to which each changed area belongs within the preset path based on the location information, and combines the sub-paths to obtain an identification path for the changed area; controls the drone according to the identification path to separately capture changed images of the changed area and identifies the changed images to identify the changed area. By pre-capturing and quickly locating the position of the changed area before performing precise capture, time is avoided from being wasted on areas where no significant changes have occurred, thereby improving efficiency while ensuring accuracy. This solves the problem of low efficiency in regional change recognition in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of a method for identifying regional changes based on images collected by a drone in a first embodiment of the present invention;

[0040] Figure 2 Schematic diagram of determining sub-paths in the method for identifying regional changes based on images collected by drones in the first embodiment of the present invention;

[0041] Figure 3 This is a structural block diagram of a region change recognition system based on drone-collected images in the third embodiment of the present invention.

[0042] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0043] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0044] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed types.

[0046] The following will explain in detail how to improve the efficiency of acquisition while ensuring the accuracy of recognition with reference to specific embodiments and drawings.

[0047] Example 1

[0048] See also Figure 1 , which shows a method for identifying regional changes based on images collected by a drone in a first embodiment of the present invention, and the method includes steps S10 to S13.

[0049] Step S10 , controlling the drone to collect images in a preset area along a preset path at different times, and obtaining a first image and a second image of a real scene of the preset area that are different in time.

[0050] Among them, in order to identify regional changes, it is necessary to collect images of the same area in different time periods. Specifically, the drone is controlled to collect images in the preset area according to the preset flight path in different time periods, so that the first image and the second image of the real scene of the preset area with time differences can be obtained. Specifically, the purpose of this step is to pre-collect the changes in the preset area. The position of the changed area can be quickly located through pre-collection. In specific implementation, the pre-collection standard can be controlled within a range that can roughly see whether there are obvious changes in the area, such as the flight speed, whether to stop, etc., wherein the preset path is a standard path planned when the image of the entire area can be fully collected during image collection.

[0051] Step S11 : performing feature comparison on the first image and the second image, thereby determining at least one changed region where the real scene within the preset region has changed.

[0052] Among them, the features of the first image and the second image are compared to determine the changed area of ​​the preset area. Specifically, the key points in the first image and the second image are extracted respectively. These key points usually represent the parts with stronger features in the image, and feature matching algorithms such as FLANN, BFMatcher, etc. are used to find matching key point pairs in the first image and the second image; each pair of matching key points usually represents similar or identical parts in the two images, and inconsistent feature points in the first image and the second image are screened out by comparing the key point pairs. These inconsistent feature points usually indicate changes between the two images, and adjacent feature points are spatially clustered using clustering algorithms such as DBSCAN, K-means, etc., and combined into continuous areas to obtain the changed area.

[0053] Step S12: determining the position information of the changed area, determining the sub-path to which each changed area belongs in the preset path according to the position information, and combining the sub-paths to obtain an identification path of the changed area.

[0054] It can be understood that after determining the location information of the changed area, its positional relationship with the preset path can be determined, so that it can be determined through which sub-path of the preset path it is collected. Therefore, after finding the corresponding sub-path, the sub-paths can be combined to determine the identification path of the changed area. The purpose of this is that after determining the identification path, it can be clear which section of the road needs to be accurately collected, so that the drone can be controlled accordingly.

[0055] Step S13: Control the UAV according to the identification path to respectively collect the change images of the change area and identify the change images to identify the change area.

[0056] Among them, after determining the identification path, the drone can be controlled to collect accurate data on the road section. Specifically, the flight parameters of accurate data are set, such as flight speed, whether to stop, stop time, number of shots, etc. During the specific implementation, the drone flight control software or SDK (software development kit) is used to write a flight control program to realize the autonomous flight and image acquisition of the drone; the changed images are identified, the identification results are analyzed, and the specific change information of the changed area is determined, such as the location, degree of change and type, etc.

[0057] It can be understood that by selecting the identification path through pre-collection, the distance of the path for precise collection can be reduced, thereby improving the efficiency of collection.

[0058] In summary, the region change identification method based on drone-collected images in the above-mentioned embodiment of the present invention controls the drone to collect images in a preset region along a preset path at different times, thereby obtaining a first image and a second image of a real scene of the preset region that are different in time; performs feature comparison on the first image and the second image to determine at least one changed region in the preset region where the real scene has changed; determines the position information of the changed region, determines the sub-path to which each changed region belongs in the preset path based on the position information, and combines the sub-paths to obtain an identification path for the changed region; controls the drone according to the identification path to respectively collect changed images of the changed region and identify the changed images to identify the changed region. By performing pre-collection first, the position of the changed region is quickly located and then accurately collected, thereby avoiding wasting time on regions that have not undergone significant changes, thereby improving efficiency while ensuring accuracy. This solves the problem of low efficiency in region change identification in the prior art.

[0059] Example 2

[0060] This embodiment also proposes a method for identifying regional changes based on images collected by drones. The method for identifying regional changes based on images collected by drones proposed in this embodiment differs from the method for identifying regional changes based on images collected by drones proposed in the first embodiment in that:

[0061] The preset path is an arcuate path, and the arcuate path includes multiple sub-paths distributed horizontally and vertically. The steps of determining, based on the position information, the sub-path to which each of the change areas belongs in the preset path, and combining the sub-paths to obtain the identification path of the change area include:

[0062] Respectively obtaining coordinate information of an outer boundary point of the preset area, position information of the changed area, and position information of the preset path;

[0063] Mapping the preset area, the changed area, and the preset path to a preset coordinate system according to the coordinate information of the outer boundary point of the preset area, the position information of the changed area, and the position information of the preset path;

[0064] determining the sub-path to which the changed area belongs based on positional relationship information of the changed area relative to the arcuate path;

[0065] The sub-paths are connected and combined in an arched manner in an initial order to obtain an identification path for the change area.

[0066] Specifically, in practice, when performing area recognition, the area to be recognized is generally set as a regular rectangular area, and the area image is collected through an arched path, wherein the arched path includes multiple sub-paths distributed horizontally and vertically. According to the position information and path information of the change area and the preset area collected during pre-collection, they are mapped to the preset coordinate system, and then according to the position relationship information of the change area relative to the arched path, the sub-path to which the change area belongs is determined, that is, it is determined which part of the preset path the change area is collected by. After determining the sub-path, the original sub-paths can be combined and connected in an arched manner in the order of the original sub-paths to obtain an identification path, and identification is performed through the path. wherein, by adopting the same combination method as the original path, the accuracy of data collection can be improved. Specifically, as one embodiment of the sub-path of the present invention, the step of determining the sub-path to which the change area belongs includes:

[0067] Obtaining a minimum bounding rectangle of the changing area. Specifically, rotating the changing area within a preset angle range at set intervals, and obtaining the bounding rectangle of each rotated changing area, comparing the bounding rectangles obtained at all rotation angles, and determining a target bounding rectangle with the smallest area therefrom, rotating the target bounding rectangle in the opposite direction by the same angle to obtain the minimum bounding rectangle of the changing area, and determining whether the bounding rectangle intersects with the subpath. If the bounding rectangle does not intersect with the subpath and is located between two adjacent subpaths, the two subpaths are taken as the sub-paths to which they belong. If the bounding rectangle intersects with the subpath, the changing area spans multiple areas, and the intersecting subpath and two lateral subpaths located outside the changing area and on both sides of the subpath are taken as sub-paths. In addition, in some optional embodiments of the present invention, the method further includes:

[0068] The distance spanned by the minimum circumscribed rectangle in the transverse direction is obtained, and a target sub-path is obtained by intercepting the sub-path according to the spanned distance, and the target sub-path is used as the final sub-path.

[0069] Among them, since the change area does not span the entire sub-path in most cases, there are some paths without change areas on the sub-path. Therefore, this path can be removed to obtain the target sub-path, and the collection is performed through the target sub-path, that is, after determining the sub-path, only the path part containing the change area on the sub-path is intercepted.

[0070] In addition, in some optional embodiments of the present invention, after the step of using the intersecting sub-path and the two transverse sub-paths on both sides of the sub-path as the sub-path, the step further includes:

[0071] Obtain target areas formed by the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path, obtain the area of ​​the covering portion of the change area and the target area, and determine whether to remove the sub-path on one side according to the area.

[0072] In practice, it is possible that the changed area intersects with the sub-path, but its proportion is small. Therefore, in order to avoid redundant path collection, the size of the coverage area of ​​the changed area and the target area is obtained, and whether the sub-path needs to be used as a sub-path is determined based on the size of the area. For example, when the covered area is small, it means that there are fewer unchanged areas in the area, which can be compensated by collecting adjacent sub-paths with large coverage areas. Therefore, the sub-paths with small coverage areas are removed.

[0073] Specifically, such as Figure 2 As shown, after mapping to the coordinate system, the preset area S, the change area Q, and the preset paths L1-L9 are obtained. Based on the location of the change area, if the bounding rectangle does not intersect with the sub-path and is located between two adjacent sub-paths L3-L4, then these two sub-paths L3-L4 are considered as their sub-paths, and the sub-paths L3-L4 to which they belong are determined. If the bounding rectangle intersects with sub-path L8, then the change area spans multiple areas. The intersecting sub-path L8 and the two transverse sub-paths L7 and L9 on either side of the sub-path outside the change area are considered as sub-paths L7-L9. Therefore, when performing precise data collection, multiple sub-paths are eliminated, thereby improving collection efficiency. Similarly, the target path can simply intercept the corresponding portion based on the existing determined path.

[0074] In summary, the region change identification method based on drone-collected images in the above-mentioned embodiment of the present invention controls the drone to collect images in a preset region along a preset path at different times, thereby obtaining a first image and a second image of a real scene of the preset region that are different in time; performs feature comparison on the first image and the second image to determine at least one changed region in the preset region where the real scene has changed; determines the position information of the changed region, determines the sub-path to which each changed region belongs in the preset path based on the position information, and combines the sub-paths to obtain an identification path for the changed region; controls the drone according to the identification path to respectively collect changed images of the changed region and identify the changed images to identify the changed region. By performing pre-collection first, the position of the changed region is quickly located and then accurately collected, thereby avoiding wasting time on regions that have not undergone significant changes, thereby improving efficiency while ensuring accuracy. This solves the problem of low efficiency in region change identification in the prior art.

[0075] Example 3

[0076] See also Figure 3 , shown is a regional change recognition system based on drone-collected images proposed in a third embodiment of the present invention, the system comprising:

[0077] The acquisition module 100 is used to control the drone to acquire images in a preset area along a preset path at different times, thereby obtaining a first image and a second image of a real scene of the preset area that are different in time;

[0078] A comparison module 200 is configured to perform feature comparison on the first image and the second image, thereby determining at least one changed region where the real scene within the preset region has changed;

[0079] a combining module 300 for determining position information of the changed area, determining a sub-path to which each changed area belongs in the preset path based on the position information, and combining the sub-paths to obtain an identification path for the changed area;

[0080] The identification module 400 is used to control the UAV according to the identification path to respectively collect the change images of the change area and identify the change images to identify the change area.

[0081] Furthermore, in the above-mentioned area change recognition system based on drone-collected images, the step of performing feature comparison on the first image and the second image to determine at least one changed area where the real scene within the preset area has changed includes:

[0082] Extracting key points from the first image and the second image respectively, and finding matching key point pairs in the first image and the second image using a feature matching algorithm;

[0083] Inconsistent feature points in the first image and the second image are screened out by comparing the key point pairs, and adjacent feature points are spatially clustered to form continuous regions to obtain the changed region.

[0084] Furthermore, in the above-mentioned area change identification system based on drone-collected images, wherein the preset path is an arcuate path, the arcuate path includes multiple sub-paths distributed horizontally and vertically, and the steps of determining the sub-path to which each changed area belongs in the preset path based on the position information, and combining the sub-paths to obtain the identification path of the changed area include:

[0085] Respectively obtaining coordinate information of an outer boundary point of the preset area, position information of the changed area, and position information of the preset path;

[0086] Mapping the preset area, the changed area, and the preset path to a preset coordinate system according to the coordinate information of the outer boundary point of the preset area, the position information of the changed area, and the position information of the preset path;

[0087] determining the sub-path to which the changed area belongs based on positional relationship information of the changed area relative to the arcuate path;

[0088] The sub-paths are connected and combined in an arcuate manner in an initial order to obtain an identification path for the change region.

[0089] Furthermore, in the above-mentioned area change recognition system based on drone-collected images, the step of determining the sub-path to which the changed area belongs based on the positional relationship information of the changed area relative to the arched path includes:

[0090] Obtaining a minimum bounding rectangle of each of the change regions, and determining whether the change region intersects with the subpath based on the minimum bounding rectangle;

[0091] If so, the intersecting sub-path and the two transverse sub-paths on both sides of the sub-path are used as the sub-paths;

[0092] If not, the lateral sub-paths on both sides of the change area are used as the branch paths.

[0093] Furthermore, in the above-mentioned area change recognition system based on drone-collected images, the step of obtaining the minimum bounding rectangle of each of the changed areas includes:

[0094] Rotating the change region at set intervals within a preset angle range, and obtaining a circumscribed rectangle of each rotated change region;

[0095] Comparing the bounding rectangles obtained at all rotation angles, and determining a target bounding rectangle with the smallest area;

[0096] The target bounding rectangle is rotated in the opposite direction by the same angle to obtain the minimum bounding rectangle of the changed area.

[0097] Furthermore, the above-mentioned area change recognition system based on drone-collected images further includes:

[0098] The interception module is configured to obtain the distance spanned by the minimum circumscribed rectangle in the horizontal direction, intercept the sub-path according to the spanned distance to obtain a target sub-path, and use the target sub-path as the final sub-path.

[0099] Furthermore, in the above-mentioned area change recognition system based on drone-collected images, after the step of using the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path as the sub-paths, the step further includes:

[0100] Obtain target areas formed by the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path, obtain the area of ​​the covering portion of the change area and the target area, and determine whether to remove the sub-path on one side according to the area.

[0101] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments and will not be repeated here.

[0102] Example 4

[0103] Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the above-mentioned embodiments 1 to 2.

[0104] Example 5

[0105] On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and runnable on the processor, and when the processor executes the program, the steps of the method described in any one of the above embodiments one to two are implemented.

[0106] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0107] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0108] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0109] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0110] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0111] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for identifying regional changes based on images collected by drones, characterized in that: The method comprises: Controlling the drone to collect images within a preset area along a preset path at different times to obtain a first image and a second image of a real scene of the preset area that are different in time; Performing feature comparison on the first image and the second image to determine at least one changed area where the real scene within the preset area has changed; Determining position information of the changed area, determining a sub-path to which each of the changed areas belongs in the preset path according to the position information, and combining the sub-paths to obtain an identification path of the changed area; Controlling the UAV according to the identification path to respectively collect change images of the change area and identifying the change images to identify the change area; The preset path is an arcuate path, and the arcuate path includes multiple sub-paths distributed horizontally and vertically. The steps of determining, based on the position information, the sub-path to which each of the change areas belongs in the preset path, and combining the sub-paths to obtain the identification path of the change area include: Respectively obtaining coordinate information of an outer boundary point of the preset area, position information of the changed area, and position information of the preset path; Mapping the preset area, the changed area, and the preset path to a preset coordinate system according to the coordinate information of the outer boundary point of the preset area, the position information of the changed area, and the position information of the preset path; determining the sub-path to which the changed area belongs based on positional relationship information of the changed area relative to the arcuate path; Connecting and combining the sub-paths in an arched manner in an initial order to obtain an identification path for the change region; The step of determining the sub-path to which the changed area belongs based on the positional relationship information of the changed area relative to the arcuate path includes: Obtaining a minimum bounding rectangle of each of the change regions, and determining whether the change region intersects with the subpath based on the minimum bounding rectangle; If so, the intersecting sub-path and the two transverse sub-paths on both sides of the sub-path are used as the sub-paths; If not, the lateral sub-paths on both sides of the change area are used as the branch paths.

2. The method for identifying regional changes based on images collected by drones according to claim 1, characterized in that: The step of performing feature comparison on the first image and the second image to determine at least one changed area where the real scene within the preset area has changed includes: Extracting key points from the first image and the second image respectively, and finding matching key point pairs in the first image and the second image using a feature matching algorithm; Inconsistent feature points in the first image and the second image are screened out by comparing the key point pairs, and adjacent feature points are spatially clustered to form continuous regions to obtain the changed region.

3. The method for identifying regional changes based on images collected by drones according to claim 1, characterized in that: The step of obtaining the minimum bounding rectangle of each of the change areas comprises: Rotating the change region at set intervals within a preset angle range, and obtaining a circumscribed rectangle of each rotated change region; Comparing the bounding rectangles obtained at all rotation angles, and determining a target bounding rectangle with the smallest area; The target bounding rectangle is rotated in the opposite direction by the same angle to obtain the minimum bounding rectangle of the changed area.

4. The method for identifying regional changes based on images collected by drones according to claim 1, characterized in that: The method further comprises: The distance spanned by the minimum circumscribed rectangle in the transverse direction is obtained, and a target sub-path is obtained by intercepting the sub-path according to the spanned distance, and the target sub-path is used as the final sub-path.

5. The method for identifying regional changes based on images collected by drones according to claim 4, characterized in that: After the step of using the intersecting sub-path and the two transverse sub-paths on both sides of the sub-path as the sub-paths, the following step further comprises: Obtain target areas formed by the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path, obtain the area of ​​the covering portion of the change area and the target area, and determine whether to remove the sub-path on one side according to the area.

6. A regional change recognition system based on images collected by drones, characterized in that: A system for implementing the method for identifying regional changes based on images collected by a drone according to any one of claims 1 to 5, comprising: An acquisition module is used to control the drone to acquire images within a preset area along a preset path at different times, thereby obtaining a first image and a second image of a real scene of the preset area that are different in time; a comparison module, configured to perform feature comparison on the first image and the second image, thereby determining at least one changed region where the real scene within the preset region has changed; a combining module, configured to determine position information of the changed area, determine a sub-path to which each changed area belongs in the preset path according to the position information, and combine the sub-paths to obtain an identification path of the changed area; The recognition module is used to control the UAV according to the recognition path to respectively collect the change images of the change area and recognize the change images to identify the change area.

7. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 5 when executing the program.

Images