Land space overall planning current situation investigation data acquisition system

Abstract

The invention discloses a land space overall planning current situation investigation data acquisition system, which comprises an equipment information acquisition unit, an image information acquisition unit, an equipment preprocessing unit, an investigation image acquisition unit and an investigation image merging unit, and relates to the technical field of data acquisition. Global intelligent behaviors are realized through coordination and cooperation of the simple platform main body, mutual cooperation between the multiple unmanned aerial vehicles and the control machine table is promoted, acquisition points of space investigation data are effectively determined, the data acquisition range is expanded, and corresponding acquisition positions are generated according to distribution and decision making of the multiple unmanned aerial vehicles, so that the data acquisition efficiency is improved. According to the method, path planning and collaborative acquisition tasks can be quickly and accurately executed, the data acquisition efficiency is effectively improved, and the problem of different proportions of live-action images caused by different flight heights is effectively avoided by determining the flight heights of the multiple unmanned aerial vehicles, so that the acquisition and splicing of the live-action images become simpler and more convenient.

Description

Technical Field

[0001] This invention relates to the field of data acquisition technology, specifically to a data acquisition system for a survey of the current status of national land spatial planning. Background Technology

[0002] Unmanned aerial vehicle (UAV) real-scene image acquisition technology is a product of modern technological development. It has been widely applied in various fields, such as basic surveying and mapping, land resource investigation and monitoring, dynamic land use monitoring, digital city construction, and emergency disaster relief mapping data acquisition. This technology integrates the advantages of UAVs and digital cameras, featuring high mobility, high efficiency, high speed, high precision and accuracy, and low cost. It has a significant advantage, especially in the rapid acquisition of high-resolution images in small areas and areas with difficult flight conditions.

[0003] When acquiring real-scene images, the flight altitude of the drones must be considered. Since drones take off from different starting points and fly at varying altitudes, the resulting real-scene images may have different scales compared to the actual site, leading to problems with image stitching. Therefore, determining the flight altitude of multiple drones is a crucial step in acquiring real-scene images.

[0004] In summary, UAV real-scene image acquisition technology has broad application prospects and enormous development potential. However, how to further improve the efficiency and quality of image acquisition, and how to solve potential problems, remain important directions for future research. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a data collection system for a survey of the current status of national land spatial planning, which solves the problems mentioned in the background section.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a data collection system for a survey of the current status of national land spatial planning, comprising: The equipment information acquisition unit is used to acquire the pair-to-pair distance parameters and the platform-to-platform distance parameters of multiple drones. The pair-to-pair distance parameters are the distance parameters between two drones, and the platform-to-platform distance parameters are the distance parameters between each drone and the control platform. The image information acquisition unit is used to acquire multiple sets of recorded image information captured by the drone; among which, the recorded image information is real-scene video captured by the high-definition camera mounted on the drone and not stored. The equipment preprocessing unit is used to adjust the flight altitude of other drones in the target area based on the flight altitude of one drone, combined with the distance parameters between the two drones and the distance parameters between the two drones; The survey image acquisition unit is used for multiple drones to move horizontally at this flight altitude and collect real-world photos while moving according to the corresponding moving reference distance. At the same time, the collection points at the corresponding moving reference distance are marked by the pre-trained position marking model, and the corresponding position marks are added to the corresponding real-world photos. The survey image merging unit is used to import the acquired real-scene images into a pre-trained image merging model. The image merging model stitches together all the real-scene images based on the location markers in each real-scene image to obtain a survey map of the target area.

[0007] As a further aspect of the present invention, the distance parameter is obtained by any one of satellite positioning, base station positioning, and TOF ranging methods.

[0008] As a further aspect of the present invention, the adjustment method of the equipment preprocessing unit is as follows: Step A1: Select two drones, pre-determine a flight start point in the target area, and fix the control unit at the flight start point position; Step A2: Select one of the two drones and fly vertically upwards a certain distance from the reference flight starting point. Make the drone fly in place, and the height from the position of the in-place flight to the control console is defined as the flight altitude of the drone. At the same time, mark the drone as drone A. Step A3: Obtain the distance parameters between the drone A and the platform during in-situ flight, and record them as the distance from the ground for data collection. Step A4: Obtain the recorded image information taken by the drone A, which is flying in place, at its current location; Step A5: Obtain the specified edge center point in the recorded image information, then select another drone from the two drones to fly to the edge center point and land on the ground corresponding to that point, and mark the drone as drone B. Step A6: Obtain the distance parameter between UAV A and UAV B, and record it as the analysis and acquisition distance; Step A7: Treat the distance from the ground as the right side of a right triangle, and the analysis distance as the hypotenuse of the right triangle. Then, use the Pythagorean theorem to calculate the other right side of the right triangle, which is the distance between the drone B and the platform, and mark it as the moving reference distance. Step A8: Fly drone B vertically upwards at the distance from the ground for data collection, and then make the drone fly in place. Step A9: Obtain the recorded image information taken by the UAV B, which is flying in place, at the current position. Then, find the edge center point in the recorded image information that is opposite to the edge center point specified by UAV A, and record this edge center point as the adjustment center point. Step A10: Based on the adjustment center point and the control unit, adjust and confirm the flight altitude of UAV B for the second time. Specifically, the operator controls UAV B to rise or fall vertically so that the adjustment center point in the currently acquired recorded image information of the UAV coincides with the position of the control unit.

[0009] As a further aspect of the present invention: the edge center point is defined as follows: when the drone captures the recorded image information, the image obtained by the high-definition camera is in a rectangular state, and the real-time scene is located at the center of each of the four sides of the rectangle, which is the edge center point. The designated edge center point is preset by the operator in advance, that is, the center position of one side in the rectangular recorded image information; As a further aspect of the present invention: the specific method of the image acquisition unit is as follows: Step C1, draw a straight line with UAV A and UAV B as two points; Step C2: Record the current position of drone A as the origin position. Drone B moves along the straight line from the current position to a reference distance away from drone A and reaches the corresponding position one. Step C3: The current positions of drones A and B are marked using a pre-trained position marking model. At the same time, real-world photos are taken and saved at the corresponding position marking locations using the high-definition cameras mounted on drones A and B. The position markings corresponding to the current positions of drones A and B are then added to the corresponding real-world photos. Step C4: Move drone A from its current position along the straight line away from drone B by 2 reference distances, and mark the position of drone A using a pre-trained position marking model. Simultaneously, drone A is moved along the straight line from its corresponding position by two reference distances away from drone B, and the position of drone A is marked using a pre-trained position marking model. Step C5: Simultaneously, take real-world photos at the corresponding marked locations using the high-definition camera mounted on Drone A and save them. Also, add the current location markers of Drone A and Drone B to the corresponding real-world photos. Step C6: Based on the location of drone A, continue to move 2 more reference distances in the direction of travel of the drone in the previous step. At the same time, based on the location of drone B1, continue to move two more reference distances in the direction of the drone's previous movement. And obtain the corresponding real-scene photos according to Step C5; Step C7: Continue in this manner until all real-world photos of the target area with corresponding location markers at the corresponding ray positions are obtained.

[0010] As a further aspect of the present invention: the location marking model contains preset location marking rules, and the location marking model performs location marking in the following way: the real-scene images acquired by UAVs A and B respectively are marked with their locations according to the order in which UAVs A and B acquired the real-scene images in the location marking rules.

[0011] As a further aspect of the present invention: the image information acquisition unit is also used to acquire the lengths of two adjacent edges in the recorded image information obtained by the drone; Next, the image acquisition unit investigates the movement reference distance between UAV A and UAV B and its corresponding edge length, and then performs a proportional conversion with the length of the adjacent edge to obtain the movement reference distance corresponding to the length of the adjacent edge. Subsequently, both UAV A and UAV B moved to the next shooting point in the target area according to the moving reference distance corresponding to the length of the other adjacent edge to collect real-scene images.

[0012] As a further aspect of the present invention: the recorded image information is rectangular in shape; the edge length is represented as the distance from the center point of the recorded image to the center point of one side, and the adjacent edge lengths are represented as the angle between the two edge lengths being 90 degrees.

[0013] This invention provides a data collection system for a survey of the current status of national land spatial planning. Compared with existing technologies, it has the following advantages: This invention adjusts the acquisition positions of each drone through the device preprocessing unit, enabling each drone to accurately and effectively acquire real-scene images of the target area. This solves the problem in the prior art where, when a single or multiple drones acquire multiple real-scene photos of a designated area, the photos contain a large number of repeated real-scene parts, leading to an increase in the number of photos and the inability to effectively stitch them together. Furthermore, stitching requires further retouching of the photos, resulting in low acquisition efficiency. The present invention greatly reduces the overlap rate of real scenes in the image by pre-adjusting the drone, thereby effectively reducing the number of photos and the corresponding editing time, and greatly improving the collection efficiency of spatial survey data. This invention achieves global intelligent behavior through the coordinated cooperation of a simple platform, promotes mutual collaboration between multiple drones and control units, effectively determines the collection points of spatial survey data, expands the scope of data collection, and generates corresponding collection positions based on the allocation and decision-making of multiple drones. It can quickly and accurately execute path planning and collaborative collection tasks, effectively improving data collection efficiency. This embodiment of the invention effectively improves the efficiency and quality of real-scene image acquisition by using the movement strategy of the drone and combining it with the edge length corresponding to the recorded image information. This invention effectively avoids the problem of inconsistent scale in real-world images caused by varying flight altitudes of multiple drones, thus simplifying and facilitating the acquisition and stitching of real-world images. This not only meets the needs of various application scenarios but also provides new ideas and methods for the development of drone real-world image acquisition technology. Attached Figure Description

[0014] Figure 1 This is a system block diagram of the present invention; Figure 2 This is a schematic diagram of the flight data of the present invention; Figure 3 This is a schematic diagram illustrating the image information captured by the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] As an embodiment of the present invention Please see Figures 1-3 This invention provides a technical solution: a data collection system for a survey of the current status of national land spatial planning, comprising: This system is based on multiple drones equipped with high-definition cameras and a control unit for controlling these drones. In this embodiment, when the UAV is flying in a straight line in parallel within the target area, the angle of deflection caused by the Earth's spherical shape compared to the horizon is negligible. Multiple drones work together in a coordinated manner; in this embodiment, the number of cooperating drones is 2. The equipment information acquisition unit is used to acquire the flight data of multiple drones. The flight data includes the distance parameters between the multiple drones and the distance parameters between the multiple drones and the control station, which are recorded as the distance parameters between the drones and the control station respectively. like Figure 2 As shown, Y1 and Y2 represent UAVs, Y2 represents control units, J1 refers to the distance between control units, and J2 refers to the distance between the two units. The distance parameter is obtained through any one of the following methods: satellite positioning, base station positioning, and TOF ranging. The image information acquisition unit is used to acquire multiple sets of recorded image information captured by drones. Among them, the recorded image information is real-world video captured by a high-definition camera mounted on the drone and not stored; The equipment preprocessing unit is used to adjust the flight altitude of each UAV in the target area based on the dual-UAV spacing parameters and the table UAV spacing parameters. The adjustment method is as follows: Step A1: Pre-determine a flight start point in the target area and fix the control unit at the flight start point location; Step A2: Select one drone from the multiple drones and fly it vertically upwards a certain distance from the reference flight starting point. Make the drone fly in place, and the height from the position of the in-place flight to the control console is defined as the flight altitude of the drone. At the same time, mark the drone as drone A. Step A3: Obtain the distance parameters between the drone A and the ground, and record them as the distance from the ground. Step A4: Obtain the recorded image information taken by the drone A, which is flying in place, at its current location; Step A5: Obtain the specified edge center point in the recorded image information, then select another drone from multiple drones to fly to the edge center point and land on the ground corresponding to that point, and mark the drone as drone B. The edge center point is defined as follows: when the drone captures the recorded image information, the image obtained by the high-definition camera is in a rectangular state, and the real-time scene is located at the center of each of the four sides of the rectangle, which is the edge center point. The designated edge center point is preset by the operator in advance, that is, the center position of one side in the rectangular recorded image information; Step A6: Obtain the distance parameter between UAV A and UAV B, and record it as the analysis and acquisition distance; Step A7: Treat the distance from the ground as the right side of a right triangle, and the analysis distance as the hypotenuse of the right triangle. Then, use the Pythagorean theorem to calculate the other right side of the right triangle, which is the distance between the drone B and the platform, and mark it as the moving reference distance. Step A8: Fly drone B vertically upwards at the distance from the ground for data collection, and then make the drone fly in place. Step A9: Obtain the recorded image information taken by the UAV B, which is flying in place, at the current position. Then, find the edge center point in the recorded image information that is opposite to the edge center point specified by UAV A, and record this edge center point as the adjustment center point. Step A10: Based on the adjustment center point and in conjunction with the control unit, make a second adjustment and confirm the flight altitude of UAV B; The specific method is as follows: the operator controls the drone B to rise or fall vertically, so that the center point in the currently acquired recorded image information of the drone coincides with the position of the control station; In this embodiment, the drone is propelled by natural wind, making the change in the drone's position negligible; In this embodiment, the flight altitudes of multiple drones were first determined. This step is crucial because it ensures that all drones fly on the same horizontal line, thus avoiding the problem of different scales in the real-world images due to varying flight altitudes.

[0017] Next, the drone takes off at a predetermined altitude and begins collecting real-world images. During this process, the drone's position and altitude remain fixed, therefore the proportional relationships between the collected real-world images are also fixed.

[0018] Finally, once all the real-world images have been captured, they can be stitched together according to their proportional relationships to form a complete real-world image.

[0019] In summary, this embodiment effectively avoids the problem of different scales in real-world images caused by varying flight altitudes by determining the flight altitudes of multiple drones, thus making the acquisition and stitching of real-world images simpler and more convenient. This not only meets the needs of various application scenarios but also provides new ideas and methods for the development of drone real-world image acquisition technology.

[0020] The survey image acquisition unit is used to acquire real-world images of the target area using multiple drones, and the acquisition method is as follows; Step B1: Using UAV A as the origin of the ray and UAV B as the path point of the ray, a ray is formed. Then, UAV B is moved along the direction of the ray and to the designated position according to the reference distance. Step B2: The current positions of drone A and drone B are marked using a pre-trained position marking model. Real-world photos are taken and saved at the corresponding marked positions using the high-definition cameras mounted on drone A and drone B. At the same time, the position marks corresponding to the current positions of drone A and drone B are added to the corresponding real-world photos. The location marking method is as follows: Step B3: Then, combine the moving reference distance with the preset jump distance to calculate the real-time moving distance, specifically: Real-time moving distance = Moving reference distance - Jump distance; Step B4: Use drone A as the mobile device and drone B as the positioning device. Then, drone A moves to the corresponding position one along the ray direction formed by drone A and drone B according to the real-time movement distance. Step B5: Drone A moves vertically upward by one jump distance from the corresponding position one obtained in Step B4 to the corresponding position two; Step B6: Drone A moves two jump distances along the ray direction formed by Drone A and Drone B to reach the corresponding position 3 after obtaining the corresponding position 2 in Step B5. Step B7: Drone A moves vertically downwards by one jump distance from the corresponding position three obtained in Step B6 to the corresponding position four. This corresponding position is a path point on the ray formed by Drone A and Drone B. The purpose is to make Drone A return to the ray formed by Drone A and Drone B. Step B8: Drone A moves a real-time distance along the ray direction formed by Drone A and Drone B to the corresponding position 5, and marks the position using a pre-trained position marking model. At the same time, a real-world photo is taken and saved at the corresponding position mark using a high-definition camera mounted on Drone A. The position marks corresponding to the current positions of Drone A and Drone B are added to the corresponding real-world photo. Step B9: Next, swap drone A with the positioning device and drone B with the mobile device. Then, follow Step B4-Step B8 to obtain real-world photos of each location marker and the corresponding location marker. Repeat this process, swapping the positioning and movement attributes of drone A and drone B until all real-world photos of the target area with the corresponding location marker at the corresponding ray position are obtained. The location marking model contains preset location marking rules. In this embodiment, the rules are as follows: Combine drone A and drone B, and mark the locations of the real-world images acquired by the two drones in chronological order as 00001a, 00002a, 00003a, etc. The location marking model performs location marking in the following way: The time corresponding to the real-scene image obtained by UAV A at the position corresponding to the ray origin is the start time, and the position of the real-scene image is marked as 00001a. Then, the time corresponding to the first acquisition position of UAV B is sorted as the second time, and the position of the real-scene image corresponding to it is marked as 00002a. Then, the position of the real-scene image taken after UAV A passes UAV B is marked as 00003a, and so on... This embodiment adjusts the acquisition positions of each drone through the device preprocessing unit, enabling each drone to accurately and effectively acquire real-world images of the target area. This solves the problem in the prior art where, when a single or multiple drones acquire multiple real-world photos of a designated area, the photos contain a large number of repeated real-world scenes, leading to an increase in the number of photos and the inability to effectively stitch them together. Furthermore, stitching requires further retouching of the photos, resulting in low acquisition efficiency. This embodiment, by pre-adjusting the drones, greatly reduces the overlap rate of real-world scenes in the images, thereby effectively reducing the number of photos and the corresponding retouching time, and significantly improving the acquisition efficiency of spatial survey data.

[0021] The survey image merging unit is used to import the acquired real-scene images into the pre-trained image merging model. The image merging model stitches together all the real-scene images according to the location markers in each real-scene image to obtain the overall survey map of the target area. The specific method is as follows: The image merging model obtains the location markers in each real-world image, and then stitches together the real-world images corresponding to two adjacent location markers; Image stitching is an existing technology, so it will not be described in detail. By coordinating and cooperating with a simple platform entity, global intelligent behavior is achieved, promoting mutual collaboration between multiple drones and control units. This effectively determines the collection points for spatial survey data, expands the scope of data collection, and generates corresponding collection locations based on the allocation and decision-making of multiple drones. It can quickly and accurately execute path planning and collaborative collection tasks, effectively improving data collection efficiency.

[0022] Example 2 As a second embodiment of the present invention, in specific implementation, the technical solution of this embodiment differs from that of embodiment one only in that: the method by which the survey image acquisition unit acquires real-scene images of the target area through multiple drones in this embodiment is as follows: Step C1: Draw a straight line with drone A and drone B as two points; Step C2: Record the current position of drone A as the origin position. Drone B moves along the straight line from the current position to a reference distance away from drone A and reaches the corresponding position one. Step C3: The current positions of drones A and B are marked using a pre-trained position marking model. At the same time, real-world photos are taken and saved at the corresponding position marking locations using the high-definition cameras mounted on drones A and B. The position markings corresponding to the current positions of drones A and B are then added to the corresponding real-world photos. Step C4: Move drone A from its current position along the straight line away from drone B by 2 reference distances, and mark the position of drone A using a pre-trained position marking model. Simultaneously, drone A is moved along the straight line from its corresponding position by two reference distances away from drone B, and the position of drone A is marked using a pre-trained position marking model. Step C5: Simultaneously, take real-world photos at the corresponding marked locations using the high-definition camera mounted on Drone A and save them. Also, add the current location markers of Drone A and Drone B to the corresponding real-world photos. Step C6: Based on the location of drone A, continue moving it two more reference distances in the direction it traveled in the previous step. Simultaneously, based on the location of drone B1, continue moving two more reference distances in the direction it traveled in the previous step. And obtain the corresponding real-scene photos according to Step C5; Step C7: Continue in this manner until all real-world photos of the target area containing the corresponding location markers at the corresponding ray positions are obtained; The location marking model contains preset location marking rules. In this embodiment, the rules are as follows: The direction of movement of UAV A is recorded as the positive direction, and the location of the first real-scene image acquired by UAV A is marked as A00001, the location of the second real-scene image acquired by UAV A is marked as A00002, ... the location of the 15th real-scene image acquired by UAV A is marked as A00015, and so on... The direction of movement of UAV B is recorded as the opposite direction, and the location of the first real-scene image acquired by UAV B is marked as B00001, the location of the second real-scene image acquired by UAV B is marked as B00002, ... the location of the 15th real-scene image acquired by UAV B is marked as B00015, and so on... The location marking model performs location marking in the following way: The origin position is used as the location marker for the first real-world image acquired by drone A, and the location marker A00001 in the location marker rule is marked on the first real-world image acquired by drone A. Then, drone A moves along the straight line from the origin position, first moving two reference distances away from drone B. The position reached is used as the location marker for the second real-world image acquired by drone A, and the location marker A00002 in the location marker rule is marked on the first real-world image acquired by drone A, and so on... The corresponding position 1 is used as the position marker of the first real-scene image acquired by UAV B, and B00001 in the position marking rule is marked on the first real-scene image acquired by UAV B. Then, UAV B moves along the straight line from the origin position, first moving 2 reference distances away from UAV A. The position reached is used as the position marker of the second real-scene image acquired by UAV B, and B00002 in the position marking rule is marked on the first real-scene image acquired by UAV B, and so on... Example 3 As a third embodiment of the present invention, in specific implementation, compared with embodiments one and two, the technical solution of this embodiment is to combine the solutions of embodiments one and two. The only difference between the technical solution of this embodiment and embodiments one and two is that: Based on Embodiment 1, the image information acquisition unit in this embodiment is also used to acquire the lengths of two adjacent edges in the recorded image information obtained by the drone; In this embodiment, the recorded image information is rectangular; the edge length is represented as the distance from the center point of the recorded image to the center point of one side, and adjacent edge lengths are represented as two sets of edge lengths with an included angle of 90 degrees. like Figure 2 As shown, Y4 represents the rectangular frame for recording image information, and L1 and L2 refer to the lengths of two adjacent edges; Next, the image acquisition unit investigates the movement reference distance between UAV A and UAV B and its corresponding edge length, and then performs a proportional conversion with the length of the adjacent edge to obtain the movement reference distance corresponding to the length of the adjacent edge. Subsequently, both UAV A and UAV B moved to the next shooting point in the target area according to the moving reference distance corresponding to the length of the other adjacent edge to collect real-scene images. This embodiment effectively improves the efficiency and quality of real-scene image acquisition by utilizing the drone's movement strategy and combining it with the edge length corresponding to the captured image information. This not only meets the needs of various application scenarios but also provides new ideas and methods for the development of drone real-scene image acquisition technology.

[0023] Example 4 As a fourth embodiment of the present invention, in specific implementation, compared with embodiments one, two, and three, the difference between this embodiment and embodiments one, two, and three is only that: Both Example 1 and Example 2 are used to acquire real-world images along a straight line in the target area using two cameras, and then perform merging processing; This embodiment utilizes four drones to acquire real-world images along multiple straight lines in the target area, and then performs merging processing. The specific method is as follows: Based on the first embodiment, the third drone C and drone A are analyzed in the same way as drone A and drone B. The corresponding analysis and acquisition distance between drone C and drone A is obtained and recorded as the straight-line offset distance. In this embodiment, the edge of drone A's screen has 4 edges, drone B is located on the left edge of drone A's screen edge, and drone C is located on the upper or lower edge of drone A's screen edge. Then, the fourth drone D and drone C were coordinated in the same manner as drone A and drone B. After drone D and drone C have completed measuring a straight line position in the target area, they then move according to the corresponding straight line offset distance to form a new straight line, which is the new data collection route between drone D and drone C. Similarly, drone A and drone B are moved according to their corresponding straight-line offset distances to form a new straight line.

[0024] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0025] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A data collection system for a survey of the current status of national land spatial planning, characterized in that, include: The equipment information acquisition unit is used to acquire the pair-to-pair distance parameters and the platform-to-platform distance parameters of multiple drones. The pair-to-pair distance parameters are the distance parameters between two drones, and the platform-to-platform distance parameters are the distance parameters between each drone and the control platform. The image information acquisition unit is used to acquire multiple sets of recorded image information captured by the drone; among which, the recorded image information is real-scene video captured by the high-definition camera mounted on the drone and not stored. The equipment preprocessing unit is used to adjust the flight altitude of other drones in the target area based on the flight altitude of one drone, combined with the distance parameters between the two drones and the distance parameters between the two drones; The survey image acquisition unit is used for multiple drones to move horizontally at this flight altitude and collect real-world photos while moving according to the corresponding moving reference distance. At the same time, the collection points at the corresponding moving reference distance are marked by the pre-trained position marking model, and the corresponding position marks are added to the corresponding real-world photos. The survey image merging unit is used to import the acquired real-scene images into a pre-trained image merging model. The image merging model stitches together all the real-scene images based on the location markers in each real-scene image to obtain a survey map of the target area.

2. The land spatial master planning status survey data collection system according to claim 1, characterized in that: The distance parameters are obtained through any one of the following methods: satellite positioning, base station positioning, and TOF ranging.

3. The land spatial planning status quo survey data collection system according to claim 1, characterized in that: The adjustment method for the equipment preprocessing unit is as follows: Step A1: Select two drones, pre-determine a flight start point in the target area, and fix the control unit at the flight start point position; Step A2: Select one of the two drones and fly vertically upwards a certain distance from the reference flight starting point. Make the drone fly in place, and the height from the position of the in-place flight to the control console is defined as the flight altitude of the drone. At the same time, mark the drone as drone A. Step A3: Obtain the distance parameters between the drone A and the platform during in-situ flight, and record them as the distance from the ground for data collection. Step A4: Obtain the recorded image information taken by the drone A, which is flying in place, at its current location; Step A5: Obtain the specified edge center point in the recorded image information, then select another drone from the two drones to fly to the edge center point and land on the ground corresponding to that point, and mark the drone as drone B. Step A6: Obtain the distance parameter between UAV A and UAV B, and record it as the analysis and acquisition distance; Step A7: Treat the distance from the ground as the right side of a right triangle, and the analysis distance as the hypotenuse of the right triangle. Then, use the Pythagorean theorem to calculate the other right side of the right triangle, which is the distance between the drone B and the platform, and mark it as the moving reference distance. Step A8: Fly drone B vertically upwards at the distance from the ground for data collection, and then make the drone fly in place. Step A9: Obtain the recorded image information taken by the UAV B, which is flying in place, at the current position. Then, find the edge center point in the recorded image information that is opposite to the edge center point specified by UAV A, and record this edge center point as the adjustment center point. Step A10: Based on the adjustment center point and the control unit, adjust and confirm the flight altitude of UAV B for the second time. Specifically, the operator controls UAV B to rise or fall vertically so that the adjustment center point in the currently acquired recorded image information of the UAV coincides with the position of the control unit.

4. The land spatial planning status quo survey data collection system according to claim 3, characterized in that: in, The edge center point is defined as follows: when the drone captures the recorded image information, the image obtained by the high-definition camera is in a rectangular state, and the real-time scene is located at the center of each of the four sides of the rectangle, which is the edge center point; The designated edge center point is preset by the operator in advance, which refers to the center position of one side in the rectangular recorded image information.

5. The land spatial planning status quo survey data acquisition system according to claim 3, characterized in that: The specific methods for surveying the image acquisition unit are as follows: Step B1: Using UAV A as the origin of the ray and UAV B as the path point of the ray, a ray is formed. Then, UAV B is moved along the direction of the ray and to the designated position according to the reference distance. Step B2: The current positions of drone A and drone B are marked using a pre-trained position marking model. Real-world photos are taken and saved at the corresponding marked positions using the high-definition cameras mounted on drone A and drone B. At the same time, the position marks corresponding to the current positions of drone A and drone B are added to the corresponding real-world photos. Step B3: Then, combine the moving reference distance with the preset jump distance to calculate the real-time moving distance, specifically: Real-time moving distance = Moving reference distance - Jump distance; Step B4: Use drone A as the mobile device and drone B as the positioning device. Then, drone A moves to the corresponding position one along the ray direction formed by drone A and drone B according to the real-time movement distance. Step B5: Drone A moves vertically upward by one jump distance from the corresponding position one obtained in Step B4 to the corresponding position two; Step B6: Drone A moves two jump distances along the ray direction formed by Drone A and Drone B to reach the corresponding position 3 after obtaining the corresponding position 2 in Step B5. Step B7: Drone A moves vertically downwards by one jump distance from the corresponding position three obtained in Step B6 to the corresponding position four. This corresponding position is a path point on the ray formed by Drone A and Drone B. The purpose is to make Drone A return to the ray formed by Drone A and Drone B. Step B8: Drone A moves a real-time distance along the ray direction formed by Drone A and Drone B to the corresponding position 5, and marks the position using a pre-trained position marking model. At the same time, a real-world photo is taken and saved at the corresponding position mark using a high-definition camera mounted on Drone A. The position marks corresponding to the current positions of Drone A and Drone B are added to the corresponding real-world photo. Step B9: Next, swap drone A with the positioning device and drone B with the mobile device. Then, following Step B4-Step B8, obtain real-world photos of each location marker and the corresponding location marker. Repeat this process, swapping the positioning and movement attributes of drones A and B until all real-world photos of the target area containing the corresponding location marker at the corresponding ray position are obtained.

6. The land spatial master planning status survey data acquisition system according to claim 5, characterized in that: The location marking model contains preset location marking rules. The location marking model performs location marking in the following way: combine drone A and drone B, and mark the real-world images acquired by the two drones in chronological order according to the location marking rules.

7. The land spatial master planning status survey data collection system according to claim 3, characterized in that: The specific method for surveying the image acquisition unit is as follows: Step C1, draw a straight line with UAV A and UAV B as two points; Step C2: Record the current position of drone A as the origin position. Drone B moves along the straight line from the current position to a reference distance away from drone A and reaches the corresponding position one. Step C3: The current positions of drones A and B are marked using a pre-trained position marking model. At the same time, real-world photos are taken and saved at the corresponding position marking locations using the high-definition cameras mounted on drones A and B. The position markings corresponding to the current positions of drones A and B are then added to the corresponding real-world photos. Step C4: Move drone A from its current position along the straight line away from drone B by 2 reference distances, and mark the position of drone A using a pre-trained position marking model. Simultaneously, drone A is moved along the straight line from its corresponding position by two reference distances away from drone B, and the position of drone A is marked using a pre-trained position marking model. Step C5: Simultaneously, take real-world photos at the corresponding marked locations using the high-definition camera mounted on Drone A and save them. Also, add the current location markers of Drone A and Drone B to the corresponding real-world photos. Step C6: Based on the location of drone A, continue to move 2 more reference distances in the direction of travel of the drone in the previous step. At the same time, based on the location of drone B1, continue to move two more reference distances in the direction of the drone's previous movement. And obtain the corresponding real-scene photos according to Step C5; Step C7: Continue in this manner until all real-world photos of the target area with corresponding location markers at the corresponding ray positions are obtained.

8. The land spatial planning status quo survey data acquisition system according to claim 5, characterized in that: The location marking model contains preset location marking rules. The location marking model performs location marking in the following way: the real-world images acquired by UAVs A and B are marked according to the order in which UAVs A and B acquired the real-world images in the location marking rules.

9. A data collection system for a survey of the current status of national land spatial planning according to claim 3, characterized in that: The image information acquisition unit is also used to acquire the lengths of two adjacent edges in the recorded image information obtained by the drone; Next, the image acquisition unit investigates the movement reference distance between UAV A and UAV B and its corresponding edge length, and then performs a proportional conversion with the length of the adjacent edge to obtain the movement reference distance corresponding to the length of the adjacent edge. Subsequently, both UAV A and UAV B moved to the next shooting point in the target area according to the moving reference distance corresponding to the length of the other adjacent edge to collect real-scene images.

10. A data collection system for a survey of the current status of national land spatial planning according to claim 9, characterized in that: The recorded image information is rectangular in shape; the edge length is represented by the distance from the center point of the recorded image to the center point of one side, and the adjacent edge length is represented by the angle between the two edge lengths being 90 degrees.

Images