Aerial image-based landscaping area measurement management system

Abstract

The invention relates to the field of greening area measurement, and in particular relates to a landscaping area measurement management system based on an aerial image, which is used for solving the problems that the intelligent degree is low and the aerial image has relatively serious interference on the greening area due to angle difference in the greening area measurement process. Comprising an image acquisition unit, an image comprehensive analysis unit, a measurement management unit, a height selection management unit and a surface area statistical unit. According to the invention, through verification of the shooting angle and the greening height, the greening areas of the earth surface area and the projection area are calculated respectively, so that the projection area of greening on the ground can be obtained, and the problem of difference between the greening area and the actual area caused by inclination of the shooting angle is avoided; when the affiliation of the earth surface and the protrusions of the greening area is judged, synchronous shooting and comparison verification are carried out through binocular vision of the machine and the TOF camera, the accuracy of height data during shooting is ensured, and the judgment accuracy of the greening area is improved.

Description

Technical Field

[0001] The present invention relates to the field of green area measurement, and specifically to a measurement and management system for the greening area of gardens and landscapes based on aerial images. Background Technique

[0002] The quota indicators of urban green spaces refer to the public green space area per capita in the city, the urban greening coverage rate, the urban green space rate, etc. It is an indicator reflecting the quantity and quality of greening in a city, the economic development of the city during a certain period, the level of living welfare guarantee for urban residents, and is also one of the standards for evaluating the urban environmental quality and a symbol of urban spiritual civilization;

[0003] At present, there are certain deficiencies in the existing green area measurement methods. The existing measurement methods have a high demand for human costs and insufficient intelligence. At the same time, due to the angle during aerial photography, for green trees with a certain height, when the shooting angle is inclined, it will cause the shooting of the inclined surface of the trees, resulting in a problem that the green area is larger than the actual value, which is not conducive to the efficient and accurate measurement of the green area;

[0004] In view of the above technical problems, this application proposes a solution. Summary of the Invention

[0005] In the present invention, by verifying the shooting angle and the greening height, the greening areas of the ground area and the raised area are calculated separately, so as to obtain the projected area of the greening on the ground, avoiding the problem that the greening area is different from the actual area due to the inclination of the shooting angle. When judging the attribution of the ground and the raised areas of the greening area, binocular vision of the machine and a TOF camera are used to take synchronous shots and compare and verify, ensuring the accuracy of the height data during shooting and improving the accuracy of greening area judgment. At the same time, multiple images are combined and analyzed according to the shooting angle and the shooting area, and intelligent analysis and secondary shooting are carried out on the missing areas, improving the intelligence level in the process of greening area measurement and solving the problems of low intelligence level in the process of greening area measurement and serious interference of the aerial images on the greening area due to angle differences, and a measurement and management system for the greening area of gardens and landscapes based on aerial images is proposed.

[0006] The object of the present invention can be achieved through the following technical solutions:

[0007] A measurement and management system for the greening area of gardens and landscapes based on aerial images, including an image acquisition unit, where the image acquisition unit is used to collect aerial images through multiple cameras and transmit the collected images back;

[0008] Image comprehensive analysis unit, which acquires the transmitted images, performs comparison processing on the images, realizes image fusion and data verification, and classifies the verified images into available images and backup images;

[0009] Height selection management unit, which analyzes the combined images of available images, intercepts and combines the missing parts of the images, and completes the combined control of different regions;

[0010] Measurement management unit, which analyzes the images after the combined control of the height selection management unit, marks the missing regions, and performs secondary acquisition of the missing parts of the images through the image acquisition unit;

[0011] Surface area statistics unit, which performs combined analysis on the available images and backup images, completes the combination of multiple images, and calculates the green area ratio and actual green area of the combined images.

[0012] As a preferred embodiment of the present invention, when the image acquisition unit takes aerial images, it synchronously acquires through a binocular vision camera module and a TOF camera. The binocular vision camera module realizes the acquisition of three-dimensional images by the difference in the shooting angles of the same object, obtains the distance of the object from the shooting point, and the TOF camera calculates the distance between the photographed object and the shooting point through the emission and return time of infrared pulses, records it as a depth image, and transmits the depth image and the three-dimensional image to the image comprehensive analysis unit together.

[0013] As a preferred embodiment of the present invention, the image comprehensive analysis unit acquires the three-dimensional image and the depth image taken by the image acquisition unit, overlaps the three-dimensional image and the depth image according to the coordinates. The image comprehensive analysis unit selects any point in the overlapping images, extracts the height of the overlapping point from the three-dimensional image, and at the same time extracts the height of the same point from the depth image. If the difference between the height on the three-dimensional image and the height on the depth image is within the allowable error range, the heights on the three-dimensional image and the depth image are arithmetically averaged and recorded as the confirmed height. If the difference between the height on the three-dimensional image and the height on the depth image is outside the allowable error range, the height of the overlapping point is re-shot, and the re-shot three-dimensional image and depth image are overlapped again until all the points after the overlap of the three-dimensional image and the depth image are recorded as the confirmed height. When the image comprehensive analysis unit generates the fused image, it uses the confirmed height to replace the height in the three-dimensional image.

[0014] As a preferred embodiment of the present invention, the image comprehensive analysis unit judges the height of the fused image, records the area in the fused image with a height less than or equal to the preset threshold height as the ground area, and records the area in the fused image with a height greater than the preset threshold height as the convex area;

[0015] The image comprehensive analysis unit selects a preset rectangular range in the middle of the fused image and records it as the vertical shooting range. If there is a convex area outside the vertical shooting range in the fused image, the fused image is recorded as a standby image. If there is no convex area outside the vertical shooting range in the fused image, the fused image is recorded as an available image;

[0016] The image comprehensive analysis unit combines all available images according to the coordinates, performs integrity analysis on the combined image, and judges whether there is a missing part. If there is no missing part, it is directly sent to the ground area statistics unit. If there is a missing part, it is sent to the height selection management unit.

[0017] As a preferred embodiment of the present invention, after obtaining the combined image, the ground area statistics unit performs gray-scale transformation on the entire combined image, and uses the bimodal method based on the gray-scale transformation to segment the image after gray-scale change to obtain a black-and-white binary image. The number of pixels in the white area and the total number of pixels are counted, and the greening area ratio is obtained by the number of white areas / the total number of pixels. After the ground area statistics unit obtains the greening area ratio, it multiplies the greening area ratio by the total area of all the photographed areas to obtain the actual greening area.

[0018] As a preferred embodiment of the present invention, after obtaining the combined image with missing parts, the height selection management unit marks the missing parts, obtains all the standby images through the image comprehensive analysis unit, deletes all the convex areas in the standby images and then combines them with the combined image again to obtain a secondary combined image. Subsequently, after deleting the areas outside the vertical shooting range in the standby images, it combines them with the secondary combined image again to obtain a tertiary combined image. The height selection management unit performs integrity analysis on the tertiary combined image. If there is no missing part in the tertiary combined image, it sends the tertiary combined image to the ground area statistics unit. If there is a missing part in the tertiary combined image, it marks the coordinates of the missing area to form a missing coordinate set and sends the missing coordinate set to the image comprehensive analysis unit.

[0019] As a preferred embodiment of the present invention, the image comprehensive analysis unit sends the set of missing coordinates to the measurement management unit. After obtaining the set of coordinate missing, the measurement management unit draws the missing area according to the coordinates in the set of coordinate missing. At the same time, it overlaps the vertical shooting range in the aerial image with the drawn missing area. If the vertical shooting range is larger than the drawn missing area, a direct shooting signal is generated. If the vertical shooting range is smaller than the drawn missing area, the missing area is divided by the dichotomy method until all the divided areas are smaller than the vertical shooting range. At the same time, multiple shooting signals corresponding to the number of divided areas are generated according to the number of divided areas.

[0020] As a preferred embodiment of the present invention, the measurement management unit sends the multiple shooting signal or the direct shooting signal to the image acquisition unit. The image acquisition unit takes corresponding aerial images according to the number of shootings, and after analyzing the taken images by the image comprehensive analysis unit again, combines the images with the three - combined images again.

[0021] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0022] 1. In the present invention, when measuring the greening area, by verifying the shooting angle and the greening height, the greening of the surface area is calculated by direct shooting. When calculating the greening area of the convex area, it is calculated based on the vertically - taken image, so as to obtain the projected area of the greening on the ground, thus avoiding the problem that the greening area is different from the actual area due to the inclination of the shooting angle.

[0023] 2. In the present invention, when judging the attribution of the surface and convex parts of the greening area, binocular machine vision and a TOF camera are used for synchronous shooting, and the captured data are compared and verified to ensure the accuracy of the height data during shooting and improve the accuracy of greening area judgment.

[0024] 3. In the present invention, when processing the greening images, multiple images are combined and analyzed according to the shooting angle and shooting area, and the missing areas are intelligently analyzed and shot twice, which improves the degree of intelligence in the process of measuring the greening area, reduces the frequency of manual intervention, and saves manpower. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0026] Figure 1 is the system block diagram of the present invention;

[0027] Figure 2 is the system flow chart of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0028] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] Embodiment 1:

[0030] Please refer to Figure 1 - Figure 2 As shown, the landscaping area measurement and management system based on aerial images includes an image acquisition unit, an image comprehensive analysis unit, a measurement and management unit, a height selection management unit, and a surface area statistics unit. The image acquisition unit can acquire aerial images. When taking aerial images, the unmanned aerial vehicle (UAV) is equipped with a binocular vision camera module. By using the difference in the shooting angles of different cameras in the camera module for the same object, three-dimensional images are acquired, and the distance between the object and the shooting point is obtained. At the same time, the TOF camera carried on the UAV is used to synchronously shoot with the binocular vision camera module. The distance between the photographed object and the shooting point is calculated by the emission and return time of the infrared pulse, recorded as a depth image, and the depth image and the three-dimensional image are jointly transmitted to the image comprehensive analysis unit.

[0031] The image comprehensive analysis unit acquires the three-dimensional image and the depth image photographed by the image acquisition unit, overlaps the three-dimensional image and the depth image according to the coordinates. The image comprehensive analysis unit selects any point in the overlapping images, extracts the height of the overlapping point from the three-dimensional image, and at the same time extracts the height of the same point from the depth image. If the difference between the height on the three-dimensional image and the height on the depth image is within the allowable error range, the heights on the three-dimensional image and the depth image are arithmetically averaged and recorded as the confirmed height. If the difference between the height on the three-dimensional image and the height on the depth image is outside the allowable error range, the height of the overlapping point is re-shot, and the re-shot three-dimensional image and depth image are overlapped again until all points are recorded as the confirmed height after the three-dimensional image and the depth image are overlapped. The image comprehensive analysis unit replaces the height in the three-dimensional image with the confirmed height to form a new fused image.

[0032] The image comprehensive analysis unit judges the height of the fused image, records the area in the fused image with a height less than or equal to the preset threshold height as the ground surface area, and records the area in the fused image with a height greater than the preset threshold height as the convex area. The image comprehensive analysis unit selects a preset rectangular range in the middle of the fused image and records it as the vertical shooting range. If there is a convex area outside the vertical shooting range in the fused image, the fused image is recorded as a backup image. If there is no convex area outside the vertical shooting range in the fused image, the fused image is recorded as an available image;

[0033] The image comprehensive analysis unit combines all available images according to the coordinates, analyzes the integrity of the combined image, and judges whether there is a missing part. If there is no missing part, it is directly sent to the ground surface area statistics unit. If there is a missing part, it is sent to the height selection management unit;

[0034] After obtaining the combined image, the ground surface area statistics unit performs gray-scale transformation on the whole combined image, and after gray-scale transformation, uses the gray-scale-based threshold segmentation method on the image. The threshold segmentation method can adopt the double-peak method segmentation based on gray-scale transformation. After being segmented by the double-peak method, the combined image becomes a black-and-white binary image. The number of pixels in the white area and the total number of pixels are counted, and the greening area ratio is obtained by the number of white areas / the total number of pixels. After the ground surface area statistics unit obtains the greening area ratio, it multiplies the greening area ratio by the total area of all the photographed areas to obtain the actual greening area.

[0035] Example 2:

[0036] Please refer to Figure 1 - Figure 2 As shown in the figure, after obtaining the combined image with missing parts, the height selection management unit marks the missing parts, obtains all the backup images through the image comprehensive analysis unit, deletes all the convex areas in the backup images and then combines them with the combined image again to obtain a secondary combined image. Subsequently, after deleting the areas outside the vertical shooting range in the backup images, it combines them with the secondary combined image again to obtain a tertiary combined image. The height selection management unit analyzes the integrity of the tertiary combined image. If there is no missing part in the tertiary combined image, it sends the tertiary combined image to the ground surface area statistics unit. If there is a missing part in the tertiary combined image, it marks the coordinates of the missing area to form a missing coordinate set and sends the missing coordinate set to the image comprehensive analysis unit;

[0037] The image comprehensive analysis unit sends the set of missing coordinates to the measurement management unit. After obtaining the coordinate missing set, the measurement management unit draws the missing area according to the coordinates in the coordinate missing set. At the same time, it overlaps the vertical shooting range in the aerial image with the drawn missing area. If the vertical shooting range is larger than the drawn missing area, a direct shooting signal is generated. If the vertical shooting range is smaller than the drawn missing area, the missing area is segmented into two areas. If each area is smaller than the vertical shooting range, the cross brace generates multiple shooting signals for separately shooting the two segmented areas. If there is still an area larger than the vertical shooting range after being segmented into two areas, the area larger than the vertical shooting range continues to be segmented into two areas until all the segmented areas are smaller than the vertical shooting range. At the same time, multiple shooting signals corresponding to the number of segmented areas are generated according to the number of segmented areas;

[0038] The measurement management unit sends the multiple shooting signals or the direct shooting signal to the image acquisition unit. The image acquisition unit takes corresponding aerial images according to the number of shootings. After the taken images are analyzed by the image comprehensive analysis unit again, they are combined with the three - time combined image again to fill the missing area in the three - time combined image. After there is no missing area in the three - time combined image, the three - time combined image is sent to the surface area statistics unit to obtain the greening area ratio and the greening area.

[0039] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to the specific implementation manners. Obviously, many modifications and changes can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A landscape greening area measurement and management system based on aerial images, characterized in that It includes an image acquisition unit which is used to acquire aerial images through multiple cameras and transmit the acquired images back; An image comprehensive analysis unit which acquires the transmitted-back images, performs comparison processing on the images, realizes the fusion of the images and the verification of the data, and classifies the verified images into available images and backup images; A height selection and management unit which analyzes the combined images of the available images, intercepts and combines the missing parts of the images, and completes the combined control of different regions; A measurement management unit which analyzes the images after the combined control by the height selection and management unit, marks the missing regions, and performs secondary acquisition of the missing parts of the images through the image acquisition unit; A surface area statistics unit which performs combined analysis on the available images and the backup images, completes the combination of multiple images, and calculates the green area ratio and the actual green area of the combined images.

2. The landscaping area measurement and management system based on aerial images according to claim 1, wherein When taking aerial images, the image acquisition unit performs synchronous acquisition through a binocular vision camera module and a TOF camera. The binocular vision camera module realizes the acquisition of three-dimensional images through the shooting angle difference of the same object, obtains the distance between the object and the shooting point, and the TOF camera calculates the distance between the photographed object and the shooting point through the emission and return time of infrared pulses, records it as a depth image, and transmits the depth image and the three-dimensional image to the image comprehensive analysis unit together.

3. The garden greening area measurement and management system based on aerial images according to claim 1, characterized in that The image comprehensive analysis unit acquires the three-dimensional image and the depth image taken by the image acquisition unit, overlaps the three-dimensional image and the depth image according to the coordinates. The image comprehensive analysis unit selects any point in the overlapped images, extracts the height of the overlapping point from the three-dimensional image, and at the same time extracts the height of the same point from the depth image. If the difference between the height on the three-dimensional image and the height on the depth image is within the allowable error range, the heights on the three-dimensional image and the depth image are arithmetically averaged and recorded as the confirmed height. If the difference between the height on the three-dimensional image and the height on the depth image is outside the allowable error range, the height of the overlapping point is re-shot, and the re-shot three-dimensional image and depth image are overlapped again until all the points after the overlap of the three-dimensional image and the depth image are recorded as the confirmed height. When generating the fused image, the image comprehensive analysis unit uses the confirmed height to replace the height in the three-dimensional image.

4. The landscaping area measurement and management system based on aerial images according to claim 1, characterized in that, The image comprehensive analysis unit judges the height of the fused image, records the region where the height in the fused image is less than or equal to the preset threshold height as the surface region, and records the region where the height in the fused image is greater than the preset threshold height as the convex region; The image comprehensive analysis unit selects a preset rectangular range in the middle of the fused image and records it as the vertical shooting range. If there is a convex region outside the vertical shooting range in the fused image, the fused image is recorded as a backup image. If there is no convex region outside the vertical shooting range in the fused image, the fused image is recorded as an available image; The image comprehensive analysis unit combines all available images according to the coordinates, analyzes the integrity of the combined images, and determines whether there are missing parts. If there are no missing parts, it is directly sent to the surface area statistics unit. If there are missing parts, it is sent to the height selection management unit.

5. The landscaping area measurement and management system based on aerial images according to claim 1, characterized in that, After obtaining the combined image, the surface area statistics unit performs gray-scale transformation on the entire combined image, and uses the bimodal method based on the gray-scale transformation to segment the image after gray-scale change to obtain a black-and-white binary image. It counts the number of pixels in the white area and the total number of pixels, and obtains the greening area ratio by white area quantity / total pixel quantity. After the surface area statistics unit obtains the greening area ratio, it multiplies the greening area ratio by the total area of all the photographed areas to obtain the actual greening area.

6. The landscaping area measurement and management system based on aerial images according to claim 1, characterized in that After obtaining the combined image with missing parts, the height selection management unit marks the missing parts, obtains all the backup images through the image comprehensive analysis unit, deletes all the raised areas in the backup images and then combines them with the combined image again to obtain a secondary combined image. Subsequently, after deleting the areas outside the vertical shooting range in the backup images, it combines them with the secondary combined image again to obtain a tertiary combined image. The height selection management unit analyzes the integrity of the tertiary combined image. If there are no missing parts in the tertiary combined image, it sends the tertiary combined image to the surface area statistics unit. If there are missing parts in the tertiary combined image, it marks the coordinates of the missing areas to form a missing coordinate set and sends the missing coordinate set to the image comprehensive analysis unit.

7. The landscaping area measurement and management system based on aerial images according to claim 1, characterized in that, The image comprehensive analysis unit sends the missing coordinate set to the measurement management unit. After obtaining the coordinate missing set, the measurement management unit draws the missing area according to the coordinates in the coordinate missing set, and at the same time overlaps the vertical shooting range in the aerial image with the drawn missing area. If the vertical shooting range is greater than the drawn missing area, it generates a direct shooting signal. If the vertical shooting range is less than the drawn missing area, it divides the missing area by the dichotomy method until all the divided areas are smaller than the vertical shooting range, and at the same time generates a corresponding number of multiple shooting signals according to the number of divided areas.

8. The landscaping area measurement and management system based on aerial images according to claim 1, characterized in that, The measurement management unit sends the multiple shooting signal or the direct shooting signal to the image acquisition unit. The image acquisition unit takes the corresponding aerial images according to the number of shootings, and after the photographed images are analyzed by the image comprehensive analysis unit again, they are combined with the tertiary combined image again.

Images