A Dynamic Modeling Viewpoint Optimization System Based on UAV Photography

Abstract

The present invention discloses a dynamic modeling viewpoint optimization system based on UAV photography, which relates to the technical field of photography management and improves the accuracy of photography results. The present invention collects first scene photography data of a target scene area through a UAV, and establishes multiple dynamic UAV flight paths according to a fuzzy scene grid from a scene modeling end. Then, each UAV collects second scene photography data of the target scene area along the dynamic UAV flight paths. At the same time, during the UAV flight, the dynamic UAV flight paths are dynamically updated according to the change of the attraction grid position in the fuzzy scene grid. A fuzzy scene grid is established according to the first scene photography data, and several attraction grids are marked on the fuzzy scene grid according to the modeling viewpoint information. At the same time, a dynamic scene visualization model is established according to the second scene photography data, and the position of the attraction grid on the fuzzy scene grid is updated based on the dynamic scene visualization model.

Description

Technical Field

[0001] The present invention relates to the technical field of photography management, and specifically to a dynamic modeling view point optimization system based on UAV photography. Background Art

[0002] Traditional methods for target scene modeling and data collection often rely on ground measurement equipment or manual on-site surveys. These methods are not only inefficient and costly, but also difficult to obtain comprehensive and accurate data when faced with complex terrains, large areas, or dangerous environments.

[0003] With the development of UAV technology, using UAVs for scene data collection has gradually become a trend. However, existing UAV data collection methods have many deficiencies. On the one hand, the flight paths of UAVs are usually pre-set and difficult to dynamically adjust according to the actual situation of the scene, resulting in possible omissions or repetitions in the collected data and unable to comprehensively and accurately reflect the characteristics of the target scene. On the other hand, the collected photographic data lacks an effective verification and fusion mechanism, and it is difficult to effectively integrate the data collected at different stages, affecting the accuracy and reliability of the final scene modeling. Therefore, a dynamic modeling view point optimization system based on UAV photography is provided. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a dynamic modeling view point optimization system based on UAV photography.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] A dynamic modeling view point optimization system based on UAV photography, including a cloud computing platform, which is communicatively connected to a UAV management terminal and a scene modeling terminal;

[0007] The UAV management terminal is used to collect first scene photographic data of the target scene area through UAVs, and establish multiple dynamic UAV flight paths according to the fuzzy scene grid from the scene modeling terminal;

[0008] Furthermore, each UAV collects second scene photographic data of the target scene area along the dynamic UAV flight path. At the same time, during the UAV flight, the dynamic UAV flight path is dynamically updated according to the change of the attraction grid position in the fuzzy scene grid, and the difference detection is performed on the first scene photographic data and the second scene photographic data;

[0009] The scene modeling end is used to obtain modeling viewpoint information, establish a fuzzy scene grid based on the first scene photography data, and then mark a number of attraction grids on the fuzzy scene grid according to the modeling viewpoint information. At the same time, a dynamic scene visualization model is established based on the second scene photography data, and the positions of the attraction grids on the fuzzy scene grid are updated based on the dynamic scene visualization model.

[0010] Further, the acquisition process of the first scene photography data includes:

[0011] Set n drones, each drone is set with a camera range with a radius of r, and n one-way drone flight routes are set according to the scene acquisition range, and the distance between each one-way drone flight route is less than r, where n is a natural number greater than 10;

[0012] Let each drone fly over the target scene area along the one-way drone flight route at the same speed, and during the flight, each drone collects the first scene photography data within its shooting range;

[0013] After each drone finishes flying, collect the first scene photography data collected by each drone.

[0014] Further, the process for the first scene photography data includes:

[0015] Establish a two-dimensional coordinate system, map the first scene photography data collected by each drone onto the two-dimensional coordinate system according to its flight route, perform grayscale processing on all the first scene photography data, and set a pixel difference threshold;

[0016] Judge the size relationship between the pixel difference between the overlapping grayscale pixels in the two-dimensional coordinate system and the pixel difference threshold;

[0017] If the pixel difference is less than or equal to the pixel difference threshold, do nothing;

[0018] If the pixel difference is greater than the pixel difference threshold, judge whether the adjacent grayscales of the corresponding grayscale pixels have the same size relationship at the same time. If so, splice the overlapping positions of the two grayscale pixels, otherwise directly add the pixel values of the two grayscale pixels and take the average;

[0019] When all the judgments of the overlapping grayscale pixels are completed, shift any layer of the grayscale pixels at the overlapping positions of the spliced grayscale pixels one grayscale pixel size distance in four directions along the plane direction in turn;

[0020] Successively determine the magnitude relationship between the pixel differences among the grayscale pixels in the overlapping positions of the grayscale pixels after each translation and the pixel difference threshold, count the number of grayscale pixels with pixel differences less than or equal to the pixel difference threshold in each direction, and then select the direction with the largest number of grayscale pixels that exceeds half of the total number of grayscale pixels as the correction direction. Displace the overlapping positions of the grayscale pixels in the splicing state, and then perform pixel averaging on the grayscale pixels with pixel differences less than or equal to the pixel difference threshold;

[0021] If there is no direction with the largest number of grayscale pixels that exceeds half of the total number of grayscale pixels, perform pixel averaging on the overlapping grayscale pixels at the original overlapping positions of the grayscale pixels.

[0022] Furthermore, the process of establishing the fuzzy scene grid includes:

[0023] Perform image stitching on the first scene photography data, and establish a fuzzy scene grid according to the image stitching result. The fuzzy scene grid consists of several two-dimensional image grids;

[0024] Mark multiple viewpoint feature models on the fuzzy scene grid according to the modeling viewpoint information uploaded by the user. At the same time, according to the priority level of the modeling viewpoint information set by the user, set corresponding photography priorities for each viewpoint feature model.

[0025] Furthermore, the process of establishing the dynamic UAV flight path includes:

[0026] According to the position distribution of the viewpoint feature models in the fuzzy scene grid, set several attraction grids in the fuzzy scene grid, and set the attraction degree for each attraction grid according to the photography priority carried by each viewpoint feature model;

[0027] Set n flight starting grids with different spatial positions in the fuzzy scene grid, and then start simultaneously from each flight starting grid to obtain the attraction value β between each flight starting grid and each attraction grid;

[0028] According to the direction of the attraction grid with the largest attraction value β, select an adjacent two-dimensional image grid of the flight starting grid as the next flight grid, and determine whether there is an overlap in the flight grids associated with each flight starting grid. If there is an overlap, compare the maximum values of the attraction values β associated with the two flight starting grids. Then, for the flight starting grid with a smaller attraction value β, select the direction of the attraction grid with the second largest attraction value β of it, reselect a flight grid, and repeat whether there is an overlap in the flight grid again until there is no overlap in the flight grids associated with each flight starting grid;

[0029] Then, according to each flight starting grid, the attraction value β between its respective attraction grids is re-obtained, and the above processes of setting the flight grids and determining whether there is an overlap of the flight grids are repeated until each attraction grid is selected as a flight grid. Then, corresponding dynamic UAV flight paths are generated according to the flight grids associated with each flight starting grid.

[0030] Further, according to the decreasing order of the photography priorities, the attraction degrees carried by the corresponding attraction grids decrease in sequence.

[0031] Further, a data upload period is set for each UAV. Then, during the flight of each UAV along the dynamic UAV flight path, the second-scene photography data within its shooting range is collected.

[0032] Further, the establishment process of the dynamic scene visualization model includes:

[0033] The second-scene photography data of each is fused to obtain a scene visualization image for the corresponding data upload period. A dynamic scene visualization model is established or updated according to the scene visualization image, and multiple scene tracking grids are marked in the dynamic scene visualization model through a viewpoint feature model;

[0034] Whenever a data upload period starts, the UAV management terminal updates the distribution of each attraction grid in the fuzzy scene grid according to the scene tracking grids in the dynamic scene visualization model, and then re-plans the dynamic UAV flight paths of each UAV and synchronously sends them to each UAV.

[0035] Compared with the prior art, the beneficial effects of the present invention are:

[0036] 1. The present invention establishes a fuzzy scene grid based on the first-scene photography data and marks the attraction grids, and establishes a dynamic scene visualization model based on the second-scene photography data and updates the positions of the attraction grids. While realizing the organic combination of the data collected in different stages, it dynamically and accurately models the target scene, and more accurately reflects the actual changes of the scene.

[0037] 2. The present invention establishes multiple dynamic UAV flight paths based on the fuzzy scene grid and dynamically updates the paths according to the changes in the positions of the attraction grids, enabling the UAVs to comprehensively and accurately collect the photography data of the target scene area under the condition of adapting to the actual situation of the target scene, thus effectively avoiding the problems of data omission or duplication in the traditional fixed-path collection method. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is the system structure diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features and their effects of the present invention as follows.

[0040] As Figure 1 shown, a dynamic modeling viewpoint optimization system based on UAV photography includes a cloud computing platform, which is communicatively connected to a UAV management terminal and a scene modeling terminal;

[0041] The UAV management terminal is provided with a UAV flight management module and a photography data verification module;

[0042] The UAV flight management module is used to collect first-scene photography data of a target scene area through a UAV, and establish multiple dynamic UAV flight paths according to a fuzzy scene grid from the scene modeling terminal. Furthermore, according to the dynamic UAV flight paths, it collects second-scene photography data of the target scene area. At the same time, during the UAV flight process, it dynamically updates the dynamic UAV flight paths according to the change of the attraction grid position in the fuzzy scene grid;

[0043] The photography data verification module is used to perform difference detection on the first-scene photography data and the second-scene photography data;

[0044] The scene modeling terminal is provided with a photography data fusion module and a scene modeling module;

[0045] The photography data fusion module is used to obtain modeling viewpoint information, establish a fuzzy scene grid according to the first-scene photography data, and then mark a number of attraction grids on the fuzzy scene grid according to the modeling viewpoint information;

[0046] The scene modeling module is used to establish a dynamic scene visualization model according to the second-scene photography data, and update the positions of the attraction grids on the fuzzy scene grid based on the dynamic scene visualization model.

[0047] Furthermore, the working principle of the present invention is illustrated through the following embodiments:

[0048] The user uploads the modeling viewpoint information and the target scene information to the photography data fusion module through the scene modeling terminal. The modeling viewpoint information includes clouds, people, vehicles, plants, etc., and the target scene information includes the scene coordinate position and the scene acquisition range;

[0049] It should be noted that after the user uploads the modeling viewpoint information, the priority level of the modeling viewpoint information can be set in the photography data fusion module. That is, when collecting the image data of the target scene, according to the priority level of the modeling viewpoint information, the level of photography focus is set. For the targets with a high priority level of photography focus, they are preferentially collected and allocated updated data analysis resources;

[0050] After the user completes the upload of the modeling view point information and the target scene information, the target scene information is sent to the UAV management terminal;

[0051] In the UAV management terminal, the UAV flight management module locates the target scene area according to the scene coordinate position and the scene acquisition range of the target scene information;

[0052] Set n UAVs, each UAV is set with a camera range of radius r, and n one-way UAV flight routes are set according to the scene acquisition range, and the distance between each one-way UAV flight route is less than r, where n is a natural number greater than 10;

[0053] Let each UAV fly over the target scene area along the one-way UAV flight route at the same speed, and during the flight, each UAV collects the first scene photography data within its shooting range;

[0054] When each UAV finishes flying, the UAV flight management module collects the first scene photography data collected by each UAV and sends it to the photography data verification module;

[0055] Since the distance between each one-way UAV flight route is less than r, there are identical parts in the first scene photography data collected by adjacent UAVs at adjacent spatial positions;

[0056] Furthermore, the photography data verification module establishes a two-dimensional coordinate system, maps the first scene photography data collected by each UAV onto the two-dimensional coordinate system according to the flight route of each UAV, performs grayscale processing on all the first scene photography data, and sets the pixel difference threshold;

[0057] Judge the size relationship between the pixel difference between the grayscale pixels in the overlapping state in the two-dimensional coordinate system and the pixel difference threshold;

[0058] If the pixel difference is less than or equal to the pixel difference threshold, do nothing;

[0059] If the pixel difference is greater than the pixel difference threshold, judge whether the adjacent grayscales of the corresponding grayscale pixels have the same size relationship at the same time. If so, splice the overlapping positions of the two grayscale pixels, otherwise directly accumulate the pixel values of the two grayscale pixels and take the average;

[0060] When all the grayscale pixels in the overlapping state are judged, shift any layer of grayscale pixels in the overlapping position of the spliced grayscale pixels one grayscale pixel size distance in four directions along the plane direction in turn;

[0061] Successively determine the magnitude relationship between the pixel differences between the grayscale pixels in the overlapping positions of the grayscale pixels after each translation and the pixel difference threshold, count the number of grayscale pixels with pixel differences less than or equal to the pixel difference threshold in each direction, and then select the direction with the largest number of grayscale pixels that exceeds half of the total number of grayscale pixels as the correction direction, displace the overlapping positions of the grayscale pixels in the splicing state, and then perform pixel averaging on the grayscale pixels with pixel differences less than or equal to the pixel difference threshold;

[0062] If there is no direction with the largest number of grayscale pixels that exceeds half of the total number of grayscale pixels, perform pixel averaging on the grayscale pixels in the overlapping state at the original overlapping positions of the grayscale pixels.

[0063] Furthermore, after all the first-scene photography data has completed the difference detection, the UAV management terminal sends all the first-scene photography data to the photography data fusion module;

[0064] The photography data fusion module first performs image stitching on the first-scene photography data and establishes a fuzzy scene grid according to the image stitching result. The fuzzy scene grid consists of several two-dimensional image grids;

[0065] Mark multiple viewpoint feature models on the fuzzy scene grid according to the modeling viewpoint information uploaded by the user. At the same time, according to the priority level of the modeling viewpoint information set by the user, set corresponding photography priorities for each viewpoint feature model, and send the fuzzy scene grid to the UAV management terminal.

[0066] Furthermore, the UAV flight management module in the UAV management terminal sets several attraction grids in the fuzzy scene grid according to the position distribution of the viewpoint feature models in the fuzzy scene grid, and sets the attraction degrees for each attraction grid according to the photography priorities carried by each viewpoint feature model;

[0067] It should be noted that according to the photography priorities from high to low, the attraction degrees carried by the corresponding attraction grids decrease successively. For example, the attraction degree of the attraction grid with the highest photography priority is 100, and the attraction degree of the attraction grid with the lowest photography priority is 10;

[0068] Set n flight starting grids with different spatial positions in the fuzzy scene grid, and then start simultaneously from each flight starting grid to obtain the attraction value β between each flight starting grid and each attraction grid. The calculation formula for the attraction value β is:

[0069] ;

[0070] where represents the attraction value between the i-th flight starting grid and the j-th attraction grid, is a correction parameter, , , and represents the coordinate values of the i-th flight starting grid and the j-th attracting grid, represents the attractiveness of the j-th attracting grid;

[0071] According to the direction of the attracting grid with the largest attracting value β, select a two-dimensional image grid adjacent to the flight starting grid as the next flight grid, and determine whether there is an overlap in the flight grids associated with each flight starting grid. If there is an overlap, then compare the maximum values of the attracting values β associated with the two flight starting grids. Furthermore, for the flight starting grid with a smaller attracting value β, select the direction of the attracting grid with the second largest attracting value β, re-select a flight grid, and repeat again whether there is an overlap in the flight grid until there is no overlap in the flight grids associated with each flight starting grid;

[0072] Then, re-obtain the attracting values β between the respective attracting grids according to each flight starting grid, and repeat the above process of setting the flight grid and determining whether there is an overlap in the flight grid until each attracting grid is selected as a flight grid;

[0073] Generate corresponding dynamic UAV flight paths according to the flight grids associated with each flight starting grid. Furthermore, the UAV flight management module sends the dynamic UAV flight paths and the viewpoint feature models corresponding to the attracting grids thereon to each UAV.

[0074] Furthermore, the UAV flight management module sets a data upload period for each UAV. Then, during the flight of each UAV along the dynamic UAV flight path, collect the second scene photography data within its shooting range, and at the end of each data upload period, send the collected second scene photography data to the photography data verification module;

[0075] The photography data verification module performs difference detection on each second scene photography data according to the difference detection process of the first scene photography data, and sends all the second scene photography data to the scene modeling end after the difference detection ends;

[0076] The photography data fusion module in the scene modeling end fuses each second scene photography data to obtain a scene visualization image for the corresponding data upload period, and sends the scene visualization image and the viewpoint feature model to the scene modeling module.

[0077] The scene modeling module establishes or updates a dynamic scene visualization model based on the scene visualization image, and marks multiple scene tracking grids in the dynamic scene visualization model through the viewpoint feature model, and then sends the dynamic scene visualization model to the UAV management end and the user;

[0078] Whenever a data upload cycle starts, the UAV flight management module in the UAV management end updates the distribution of each attraction grid in the fuzzy scene grid according to the scene tracking grid in the dynamic scene visualization model, and then re-plans the dynamic UAV flight paths of each UAV and synchronously sends them to each UAV;

[0079] Repeat the above process of establishing or updating the dynamic scene visualization model until the user sends a data collection completion prompt to the scene modeling end.

[0080] The above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments by using the disclosed technical content within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any indirect modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A dynamic modeling viewpoint optimization system based on UAV photography, including a cloud computing platform, characterized in that, The cloud computing platform is communicatively connected to a drone management terminal and a scene modeling terminal; The drone management terminal is used to collect first scene photography data of a target scene area through drones, and establish multiple dynamic drone flight paths according to the fuzzy scene grids from the scene modeling terminal; Furthermore, each drone collects second scene photography data of the target scene area along the dynamic drone flight paths. At the same time, during the flight of the drones, according to the change in the position of the attraction grids in the fuzzy scene grids, the dynamic drone flight paths are dynamically updated, and the difference between the first scene photography data and the second scene photography data is detected; The scene modeling terminal is used to obtain modeling viewpoint information, establish a fuzzy scene grid according to the first scene photography data, then mark a number of attraction grids on the fuzzy scene grid according to the modeling viewpoint information, establish a dynamic scene visualization model according to the second scene photography data, and update the positions of the attraction grids on the fuzzy scene grid based on the dynamic scene visualization model; The process of establishing the dynamic drone flight paths includes: According to the position distribution of the viewpoint feature models in the fuzzy scene grid, a number of attraction grids are set in the fuzzy scene grid, and according to the photography priorities carried by each viewpoint feature model, the attraction degrees are set for each attraction grid; Set n flight starting grids with different spatial positions in the fuzzy scene grid, and then start from each flight starting grid simultaneously to obtain the attraction value β between each flight starting grid and each attraction grid; According to the direction of the attraction grid with the largest attraction value β, select a two-dimensional image grid adjacent to the flight starting grid as the next flight grid, and judge whether there is an overlap in the flight grids associated with each flight starting grid. According to the judgment result, reselect a flight grid, and repeat whether there is an overlap in the flight grid again until there is no overlap in the flight grids associated with each flight starting grid; Then, re-obtain the attraction value β between each of its attraction grids according to each flight starting grid, repeat the above process of setting flight grids and determining whether there is an overlap in the flight grids until each attraction grid is selected as a flight grid, and generate corresponding dynamic drone flight paths according to the flight grids associated with each flight starting grid.

2. The dynamic modeling view point optimization system based on UAV photography according to claim 1, wherein, The process of collecting the first scene photography data includes: Set n drones, each drone is set with a camera range with a radius of r, and set n one-way drone flight routes according to the scene collection range, and the distance between each one-way drone flight route is less than r, where n is a natural number greater than 10; Let each drone fly over the target scene area along the one-way drone flight route at the same speed, and during the flight, each drone collects the first scene photography data within its shooting range.

3. The dynamic modeling viewpoint optimization system based on UAV photography according to claim 2, characterized in that The process of processing the first scene photography data includes: Establish a two-dimensional coordinate system, map the first scene photography data collected by each drone onto the two-dimensional coordinate system according to its flight route, perform grayscale processing on all the first scene photography data, and set a pixel difference threshold; Judge the magnitude relationship between the pixel difference between grayscale pixels in the overlapping state in the two-dimensional coordinate system and the pixel difference threshold, and based on the judgment result, judge again whether the adjacent grayscale of the corresponding grayscale pixel has the same magnitude relationship at the same time. Based on the judgment result, perform pixel averaging on the grayscale pixel; For any layer of grayscale pixels at the overlapping position of the grayscale pixels in the splicing state, shift them one grayscale pixel size distance in four directions in sequence along the plane direction; Judge in sequence the magnitude relationship between the pixel difference between the grayscale pixels in the overlapping state within the overlapping position of the grayscale pixels after each translation and the pixel difference threshold, and based on the judgment result, perform pixel averaging on the grayscale pixels in the overlapping state.

4. The dynamic modeling view point optimization system based on UAV photography according to claim 3, characterized in that, The establishment process of the fuzzy scene grid includes: Perform image stitching on the first scene photography data, and establish a fuzzy scene grid according to the image stitching result. The fuzzy scene grid is composed of a number of two-dimensional image grids; Mark multiple viewpoint feature models on the fuzzy scene grid according to the modeling viewpoint information, and set the photography priority for each viewpoint feature model according to the priority level of the modeling viewpoint information set by the user.

5. The dynamic modeling view point optimization system based on UAV photography according to claim 4, characterized in that, According to the photography priority from high to low, the attraction degrees carried by the corresponding attraction grids decrease in sequence.

6. The dynamic modeling viewpoint optimization system based on UAV photography according to claim 5, wherein, The acquisition process of the second scene shooting data includes: Set the data upload period for each drone, and then during the flight of each drone along the dynamic drone flight path, collect the second scene photography data within its shooting range.

7. An optimized dynamic modeling viewpoint system based on UAV photography according to claim 6, characterized in that The establishment process of the dynamic scene visualization model includes: Fuse the shooting data of each second scene to obtain the scene visualization image of the corresponding data upload period, establish or update the dynamic scene visualization model according to the scene visualization image, and mark a number of scene tracking grids in the dynamic scene visualization model through the viewpoint feature model; Whenever a data upload period starts, the drone management terminal updates the distribution of each attraction grid in the fuzzy scene grid according to the scene tracking grid in the dynamic scene visualization model, and then re-plans the dynamic drone flight path of each drone.

Images