Land space planning modeling system based on image processing

Abstract

The invention discloses a territorial space planning modeling system based on image processing, which relates to the technical field of territorial space planning and comprises an image acquisition unit, an image verification unit, a parameter analysis unit, a master control unit and a three-dimensional modeling unit. The target image in the sampling area is acquired through the unmanned aerial vehicle, the definition analysis is performed according to the target image to calculate the image ambiguity coefficient, and the flight state is evaluated according to the flight parameters and the flight environment analysis is performed according to the real-time environment data after the target image is judged not to meet the definition requirement. When the target image is not clear due to the influence of the flight state, the unmanned aerial vehicle can be controlled to return along the flight path of the unmanned aerial vehicle to realize secondary sampling, and when the target image is not clear due to the influence of the flight environment, the unmanned aerial vehicle is controlled to return to the departure point, and time needs to be selected for secondary sampling; the flight efficiency of the unmanned aerial vehicle for executing the flight task is guaranteed, and meanwhile the image definition of a modeling source is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of territorial spatial planning, and particularly to a territorial spatial planning modeling system based on image processing. Background Art

[0002] With the acceleration of the urbanization process and the rapid development of social economy, territorial spatial planning plays a crucial role in the development of the country and regions. It involves multiple aspects such as land use, urban construction, resource allocation, and environmental protection, and has far-reaching significance for achieving sustainable development, improving the quality of life of residents, and promoting coordinated regional development. However, traditional territorial spatial planning methods gradually show many limitations when facing increasingly complex real-world demands and rapidly changing environments; The most important part of territorial spatial planning is data acquisition, and then presenting the data effect through modeling. Compared with traditional two-dimensional maps, three-dimensional spatial modeling provides richer data, which can include more dimensions and information, providing a more comprehensive basis for planning design and decision-making analysis. In the prior art, in the process of traditional three-dimensional spatial modeling, in order to obtain accurate information on the ground surface, drones are usually used for aerial photography. However, due to environmental factors, flight parameters, and coverage rate effects, the photos taken by drones may have problems such as offset and blurring, resulting in insufficient accuracy of ground surface imaging, and thus affecting the accuracy and precision of three-dimensional spatial modeling.

[0003] In view of the above technical deficiencies, a solution is now proposed. Summary of the Invention

[0004] The purpose of the present invention is to: evaluate the flight state according to flight parameters and perform flight environment analysis based on real-time environmental data. When the target image is unclear due to the influence of the flight state, the drone can be controlled to return along the flight path of the drone for secondary sampling. When the target image is unclear due to the influence of the flight environment, the drone is controlled to return to the starting point and another time is required for secondary sampling, which not only ensures the flight efficiency of the drone in performing flight tasks but also ensures the clarity of the images for modeling.

[0005] To achieve the above purpose, the present invention adopts the following technical solution: a territorial spatial planning modeling system based on image processing, including an image acquisition unit, an image verification unit, a parameter analysis unit, a general control unit, and a three-dimensional modeling unit; The image acquisition unit is used to divide the target area of territorial spatial planning into multiple sampling areas, plan the flight path of the drone in the sampling area and send it to the general control unit, obtain the target images in the sampling area through the drone, and send the target images to the image verification unit in real time; The image verification unit is used to obtain and process the target image, perform clarity analysis on the target image to calculate the image blur coefficient, and judge that the target image does not meet the clarity requirements according to the preset blur threshold to generate an error retrieval signal; The parameter analysis unit is used to obtain and process the error retrieval signal, including a flight parameter analysis module and an environmental factor analysis module. The flight parameter analysis module is used to obtain the real-time flight parameters of the drone, evaluate the flight state according to the flight parameters, and generate a flight return signal according to the evaluation result of the flight state and send it to the total control unit; The environmental factor analysis module is used to obtain the real-time environmental data of the environment where the drone is located, perform flight environment analysis according to the real-time environmental data, and generate a flight withdrawal signal according to the analysis result of the flight environment and send it to the total control unit; The total control unit is used to obtain the flight path of the drone to control the drone to fly according to the predetermined path in the adoption area to obtain images. At the same time, it can obtain the flight withdrawal signal to control the drone to return to the starting point, and obtain the flight return signal to return along the flight path of the drone to achieve secondary sampling, and send the sampled target image to the 3D modeling unit; The 3D modeling unit is used to obtain and process the target image, construct a 3D geographical model based on the target image, and construct a building model on the basis of the 3D geographical model. The texture mapping modeling algorithm is used to enhance the realism and three-dimensional sense of the model, and generate the final 3D space model.

[0006] Further, the 3D modeling unit further includes a model dynamic update module. When a new target image is collected and the new target image is compared with the historical target image, when the difference between the new target image and the historical target image reaches the preset update reference value, the 3D space model is automatically updated to ensure that the 3D space model is consistent with the actual situation.

[0007] Further, the specific process of generating the error retrieval signal is as follows: S101. Obtain the flight parameters of the drone. The flight parameters include flight speed and shooting coverage. Set the drone shooting nodes according to the flight parameters and shooting coverage. When the drone executes the flight task content along the flight path, obtain the target image at each drone shooting node; S102. After denoising the target image, use the weighted gradient algorithm to calculate the image blur coefficient D(f) of the target image: , where e1 and e2 are preset weight coefficients, f(x, y) is the gray value of the corresponding pixel point (x, y) of the target image, x and y are the abscissa and ordinate of the pixel point in the target image respectively, and G(x, y) is the convolution of the Laplacian operator of the pixel point (x, y); S103. The image blurriness coefficient is used to reflect the clarity of the target image. The larger the image blurriness coefficient, the higher the clarity of the target image. Conversely, the smaller the image blurriness coefficient, the lower the clarity of the target image. Obtain a preset blurriness threshold. If the image blurriness coefficient is less than or equal to the blurriness threshold, the clarity of the target image does not meet the requirements, and an error retrieval signal is generated.

[0008] Further, the specific process of generating a flight return signal is as follows: S201. Obtain the real-time flight parameters of the drone. The real-time flight parameters include real-time flight altitude data Hi, real-time flight speed data Vi, and flight attitude coefficient Fi. The flight attitude coefficient Fi is obtained by comprehensively calculating the flight roll angle, flight pitch angle, and flight yaw angle. S202. Obtain the pre-target image of the target image, perform feature extraction based on the pre-target image, and obtain the ground occlusion coverage rate η in the pre-target image. S203. Calculate the flight stability coefficient Ki according to the following formula: , where α, β, and γ are preset weight coefficients, Hmax is the restricted flight altitude within the sampling area, Vmax is the restricted flight speed within the sampling area, and the flight stability coefficient is used to reflect the flight state of the drone when performing the sampling task content. The larger the flight stability coefficient, the more stable the flight state of the drone. Conversely, the smaller the flight stability coefficient, the more fluctuating the flight state of the drone. S204. Obtain a preset flight stability threshold. If the flight stability coefficient Ki is less than or equal to the flight stability threshold, it means that the drone is in an unstable state and does not meet the requirements of the sampling task. At this time, a flight return signal is generated, and at the same time, updated flight parameters to be adjusted are generated according to the real-time flight parameters and sent to the total control unit.

[0009] Further, the specific process of generating a flight withdrawal signal is as follows: S301. Obtain the real-time environmental data of the environment where the drone is located. The real-time environmental data includes light intensity data E, wind speed data Vb, and temperature data Yi. S302. Obtain real-time weather forecast data, judge the rainfall possibility based on the real-time weather forecast data, and convert the rainfall possibility into a specific rainfall coefficient value ω according to the preset possibility judgment standard. S303. Calculate the flight environment evaluation coefficient Wi according to the following formula: , where e3, e4, and e5 are preset weight coefficients. The flight environment evaluation coefficient is used to reflect the degree of influence of the current environment where the UAV is located on the flight state. The larger the flight environment evaluation coefficient, the more favorable the environment where the UAV is located for performing the flight sampling task. The smaller the flight environment evaluation coefficient, the more unfavorable the environment where the UAV is located for performing the flight sampling task; S304. Obtain the preset flight environment evaluation threshold. If the flight stability coefficient Ki is less than or equal to the flight environment evaluation threshold, it indicates that the flight environment interferes with the sampling task at this time, and a flight withdrawal signal is generated at this time.

[0010] Furthermore, after the total control unit controls the UAV to return to the starting point, it obtains the flight task content of the UAV and marks the flight task content as unfinished; After the total control unit obtains the flight withdrawal signal, it controls the UAV to turn around at the signal point, obtains the real-time flight trajectory of the UAV, and according to the preset resampling data S, controls the UAV to complete a flight distance of S meters along the real-time flight trajectory. When the UAV reaches the resampling point, it adjusts the UAV parameters to obtain the target image again. After the UAV completes the flight task and returns to the starting point, it marks the flight task content as completed.

[0011] Furthermore, the specific process of generating the final three-dimensional space model is as follows. Based on the geographic information system, obtain the planar distribution data of the target area of the territorial space planning. Construct the basic two-dimensional coordinates according to the planar distribution data, obtain the target image, and use the stereo vision method to use two or more target images taken from different angles. Calculate the three-dimensional structure using the parallax, and then by comparing the pixel points in different images, deduce the depth information of the object, so as to construct a three-dimensional geographic model on the basis of the basic two-dimensional coordinates. Extract the contour features of the object from the target images of multiple different perspectives, and use the texture mapping modeling algorithm to construct the building model.

[0012] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are: The territorial space planning modeling system based on image processing obtains the target images in the sampling area through the UAV, analyzes the clarity of the target images to calculate the image blurriness coefficient. After judging that the target images do not meet the clarity requirements, it analyzes the flight state based on the flight parameters and the real-time environment data for flight environment analysis. When the target images are not clear due to the influence of the flight state, the UAV can be controlled to return along the UAV flight path for secondary sampling. When the target images are not clear due to the influence of the flight environment, the UAV is controlled to return to the starting point and another time is needed for secondary sampling, which not only ensures the flight efficiency of the UAV performing the flight task but also ensures the clarity of the images for modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 Shows the overall structural schematic diagram of the present invention. Specific embodiments

[0014] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0015] Embodiment: As Figure 1 shown, a national land spatial planning modeling system based on image processing includes an image acquisition unit, an image verification unit, a parameter analysis unit, a general control unit, and a three-dimensional modeling unit; The image acquisition unit is used to divide the target area of the national land spatial planning into multiple sampling areas, plan the UAV flight path in the sampling area and send it to the general control unit, obtain the target image in the sampling area through the UAV, and send the target image to the image verification unit in real time; The image verification unit is used to acquire and process the target image, perform clarity analysis on the target image to calculate the image blur coefficient, and judge that the target image does not meet the clarity requirement according to the preset blur threshold to generate an error retrieval signal; The specific process of generating the error retrieval signal is as follows: S101. Obtain the flight parameters of the UAV. The flight parameters include flight speed and shooting coverage. Set the UAV shooting nodes according to the flight parameters and shooting coverage. During the process of the UAV executing the flight task content along the flight path, obtain the target image at each UAV shooting node; S102. After denoising the target image, use the weighted gradient algorithm to calculate the image blur coefficient D(f) of the target image: , where e1 and e2 are preset weight coefficients, f(x, y) is the gray value of the corresponding pixel point (x, y) of the target image, x and y are the abscissa and ordinate of the pixel point in the target image respectively, and G(x, y) is the convolution of the Laplacian operator of the pixel point (x, y); S103. The image blur coefficient is used to reflect the clarity of the target image. The larger the image blur coefficient, the higher the clarity of the target image. On the contrary, the smaller the image blur coefficient, the lower the clarity of the target image. Obtain the preset blur threshold. If the image blur coefficient is less than or equal to the blur threshold, the clarity of the target image does not meet the requirement, and an error retrieval signal is generated.

[0016] The parameter analysis unit is used to obtain and process the error retrieval signal, including a flight parameter analysis module and an environmental factor analysis module. The flight parameter analysis module is used to obtain the real-time flight parameters of the drone, evaluate the flight state according to the flight parameters, and generate a flight return signal according to the evaluation result of the flight state and send it to the general control unit; The specific process of generating the flight return signal is as follows: S201. Obtain the real-time flight parameters of the drone. The real-time flight parameters include the real-time flight altitude data Hi, the real-time flight speed data Vi, and the flight attitude coefficient Fi. The flight attitude coefficient Fi is obtained by comprehensively calculating the flight roll angle, the flight pitch angle, and the flight yaw angle; S202. Obtain the pre-target image of the target image, perform feature extraction according to the pre-target image, and obtain the ground occlusion coverage rate η in the pre-target image; S203. Calculate the flight stability coefficient Ki according to the following formula: , where α, β, and γ are preset weight coefficients, Hmax is the restricted flight altitude within the sampling area, Vmax is the restricted flight speed within the sampling area, and the flight stability coefficient is used to reflect the flight state of the drone when performing the sampling task content. The larger the flight stability coefficient, the more stable the flight state of the drone. On the contrary, the smaller the flight stability coefficient, the more fluctuating the flight state of the drone; S204. Obtain the preset flight stability threshold. If the flight stability coefficient Ki is less than or equal to the flight stability threshold, it means that the drone is in an unstable state at this time and does not meet the requirements of the sampling task. At this time, a flight return signal is generated, and at the same time, updated flight parameters to be adjusted are generated according to the real-time flight parameters and sent to the general control unit.

[0017] The environmental factor analysis module is used to obtain the real-time environmental data of the environment where the drone is located, perform flight environment analysis according to the real-time environmental data, and generate a flight withdrawal signal according to the analysis result of the flight environment and send it to the general control unit; The specific process of generating the flight withdrawal signal is as follows: S301. Obtain the real-time environmental data of the environment where the drone is located. The real-time environmental data includes light intensity data E, wind speed data Vb, and temperature data Yi; S302. Obtain the real-time weather forecast data, judge the rainfall possibility based on the real-time weather forecast data, and convert the rainfall possibility into a specific rainfall coefficient value ω according to the preset possibility judgment standard; S303. Calculate the flight environment evaluation coefficient Wi according to the following formula: , where e3, e4, and e5 are preset weight coefficients. The flight environment evaluation coefficient is used to reflect the degree of influence of the current environment where the UAV is located on the flight state. The larger the flight environment evaluation coefficient, the more favorable the environment where the UAV is located for performing the flight sampling task; the smaller the flight environment evaluation coefficient, the more unfavorable the environment where the UAV is located for performing the flight sampling task. S304. Obtain the preset flight environment evaluation threshold. If the flight stability coefficient Ki is less than or equal to the flight environment evaluation threshold, it indicates that the flight environment interferes with the sampling task at this time, and a flight withdrawal signal is generated at this time.

[0018] The total control unit is used to obtain the UAV flight path to control the UAV to fly in the sampling area along a predetermined path for image acquisition. At the same time, it can obtain the flight withdrawal signal to control the UAV to return to the starting point, and obtain the flight return signal to return along the UAV flight path to achieve secondary sampling, and send the sampled target image to the 3D modeling unit. After the total control unit controls the UAV to return to the starting point, it obtains the flight task content of the UAV and marks the flight task content as unfinished. After the total control unit obtains the flight withdrawal signal, it controls the UAV to turn around at the signal point, obtains the real-time flight trajectory of the UAV, and according to the preset resampling data S, controls the UAV to complete a flight distance of S meters along the real-time flight trajectory. When the UAV reaches the resampling point, it adjusts the UAV parameters to obtain the target image again. After the UAV completes the flight task and returns to the starting point, it marks the flight task content as completed.

[0019] The 3D modeling unit is used to obtain and process the target image, build a 3D geographical model based on the target image, and build a building model on the basis of the 3D geographical model. Through the texture mapping modeling algorithm, the realism and three-dimensional sense of the model are enhanced to generate the final 3D space model.

[0020] The specific process of generating the final 3D space model is as follows. Based on the geographic information system, obtain the plane distribution data of the target area of the territorial space planning, construct the basic two-dimensional coordinates according to the plane distribution data, obtain the target image, use the stereo vision method with two or more target images taken from different angles, calculate the three-dimensional structure using the parallax, and then deduce the depth information of the object by comparing the pixel points in different images, so as to build a 3D geographical model on the basis of the basic two-dimensional coordinates, extract the contour features of the object from the target images of multiple different perspectives, and build a building model using the texture mapping modeling algorithm.

[0021] The three-dimensional modeling unit further includes a model dynamic update module. When a new target image is acquired and compared with the historical target images, when the difference between the new target image and the historical target images reaches a preset update reference value, the three-dimensional space model is automatically updated to ensure that the three-dimensional space model is consistent with the actual situation.

[0022] In the present invention, target images within a sampling area are obtained by an unmanned aerial vehicle (UAV). Clarity analysis is performed on the target images to calculate an image blurriness coefficient. After determining that the target images do not meet the clarity requirements, flight state evaluation and flight environment analysis are carried out based on flight parameters and real-time environmental data. When the unclear target images are caused by the flight state, the UAV can be controlled to return along the UAV flight path for secondary sampling. When the unclear target images are caused by the flight environment, the UAV is controlled to return to the starting point and another time needs to be selected for secondary sampling, which not only ensures the flight efficiency of the UAV in performing flight tasks but also ensures the clarity of the images for modeling.

[0023] The setting of the threshold value is for the convenience of comparison. Regarding the size of the threshold value, it depends on the amount of sample data and the base quantity set by those skilled in the art for each set of sample data; as long as the proportional relationship between the parameter and the quantified value is not affected.

[0024] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by software simulation of a large amount of collected data to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation. The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes, should be covered within the protection scope of the present invention.

Claims

1. The national land space planning modeling system based on image processing is characterized by: It includes an image acquisition unit, an image verification unit, a parameter analysis unit, a general control unit and a three-dimensional modeling unit; The image acquisition unit is used to divide the target area of ​​the national land space planning into multiple sampling areas, and plan the flight path of the drone in the sampling area and send it to the general control unit, obtain the target image in the sampling area through the drone, and send the target image to the image verification unit in real time; The image verification unit is used to obtain and process the target image, perform clarity analysis on the target image to calculate the image blur coefficient, and determine whether the target image does not meet the clarity requirement according to a preset blur threshold to generate an error retrieval signal; The parameter analysis unit is used to obtain and process the error retrieval signal, and includes a flight parameter analysis module and an environmental factor analysis module. The flight parameter analysis module is used to obtain the real-time flight parameters of the UAV, evaluate the flight status according to the flight parameters, and generate a flight return signal according to the flight status evaluation result and send it to the general control unit; The environmental factor analysis module is used to obtain real-time environmental data of the environment in which the drone is located, perform flight environment analysis based on the real-time environmental data, and generate a flight withdrawal signal based on the flight environment analysis result and send it to the general control unit; The general control unit is used to obtain the flight path of the UAV to control the UAV to fly along the predetermined path in the adopted area to obtain images, and can also obtain the flight withdrawal signal to control the UAV to return to the starting point, and obtain the flight return signal to return along the flight path of the UAV to achieve secondary sampling, and send the sampled target image to the 3D modeling unit; The 3D modeling unit is used to acquire and process the target image, construct a 3D geographic model based on the target image, and construct a building model based on the 3D geographic model. The texture mapping modeling algorithm is used to enhance the realism and stereoscopic sense of the model to generate the final 3D space model.

2. The land space planning modeling system based on image processing according to claim 1 is characterized in that: The three-dimensional modeling unit also includes a model dynamic update module. When a new target image is collected and compared with the historical target image, when the difference between the new target image and the historical target image reaches a preset update reference value, the three-dimensional space model is automatically updated to ensure that the three-dimensional space model is consistent with the actual situation.

3. The national land space planning modeling system based on image processing according to claim 1 is characterized in that: The specific process of generating the error retrieval signal is as follows: S101, obtaining flight parameters of the drone, wherein the flight parameters include a flight speed and a shooting coverage range, setting drone shooting nodes according to the flight parameters and the shooting coverage range, and obtaining a target image at each drone shooting node during the drone performing the flight mission along the flight path; S102, after denoising the target image, a weighted gradient algorithm is used to calculate the image blur coefficient D (f) of the target image: , where e1 and e2 are preset weight coefficients, f(x, y) is the grayscale value of the pixel point (x, y) corresponding to the target image, x and y are the horizontal and vertical coordinates of the pixel point in the target image, respectively, and G(x, y) is the convolution of the Laplacian operator of the pixel point (x, y); S103, the image blur coefficient is used to reflect the clarity of the target image, and a preset blur threshold is obtained. If the image blur coefficient is less than or equal to the blur threshold, the clarity of the target image does not meet the requirement, and an error retrieval signal is generated.

4. The national land space planning modeling system based on image processing according to claim 1 is characterized in that: The specific process of generating a flight return signal is as follows: S201, obtaining real-time flight parameters of the UAV, wherein the real-time flight parameters include real-time flight altitude data Hi, real-time flight speed data Vi and flight attitude coefficient Fi, wherein the flight attitude coefficient Fi is obtained by comprehensive calculation of the flight roll angle, the flight pitch angle and the flight yaw angle; S202, obtaining a front target image of the target image, performing feature extraction based on the front target image, and obtaining a ground obstruction coverage rate η in the front target image; S203. Calculate the flight stability coefficient Ki according to the following formula: , where α, β and γ are preset weight coefficients, Hmax is the restricted flight altitude within the sampling area, Vmax is the restricted flight speed within the sampling area, and the flight stability coefficient is used to reflect the flight status of the UAV when performing the sampling mission content; S204. Obtain a preset flight stability threshold. If the flight stability coefficient Ki is less than or equal to the flight stability threshold, it means that the UAV is in an unstable state and does not meet the sampling task requirements. At this time, a flight return signal is generated, and at the same time, updated flight parameters to be adjusted are generated according to the real-time flight parameters and sent to the main control unit.

5. The national land space planning modeling system based on image processing according to claim 1 is characterized in that: The specific process of generating a flight withdrawal signal is as follows: S301, obtaining real-time environmental data of the environment in which the drone is located, wherein the real-time environmental data includes light intensity data E, wind speed data Vb and temperature data Yi; S302, acquiring real-time weather forecast data, judging the possibility of rainfall based on the real-time weather forecast data, and converting the possibility of rainfall into a specific rainfall coefficient value ω according to a preset possibility judgment standard; S303. Calculate the flight environment assessment coefficient Wi according to the following formula: , where e3, e4 and e5 are preset weight coefficients, and the flight environment assessment coefficient is used to reflect the impact of the current environment of the UAV on the flight status; S304. Obtain a preset flight environment assessment threshold. If the flight stability coefficient Ki is less than or equal to the flight environment assessment threshold, it means that the flight environment interferes with the sampling task at this time, and a flight withdrawal signal is generated at this time.

6. The national land space planning modeling system based on image processing according to claim 1 is characterized in that: The general control unit controls the drone to return to the starting point and obtains the flight mission content of the drone, and marks the flight mission content as incomplete; After the general control unit obtains the flight withdrawal signal, it controls the UAV to turn around at the signal point and obtains the real-time flight trajectory of the UAV. According to the preset resampling data S, the UAV is controlled to complete a flight distance of S meters along the real-time flight trajectory. When the UAV reaches the resampling point, the UAV parameters are adjusted to obtain the target image again. After the UAV completes the flight mission and returns to the starting point, the flight mission content is marked as completed.

7. The national land space planning modeling system based on image processing according to claim 1 is characterized in that: The specific process of generating the final three-dimensional spatial model is as follows: based on the geographic information system, the plane distribution data of the target area of ​​the national land space planning is obtained, the basic two-dimensional coordinates are constructed according to the plane distribution data, the target image is obtained, and the three-dimensional structure is calculated using two or more target images taken from different angles through the stereoscopic vision method. Then, by comparing the pixel points in different images, the depth information of the object is inferred, thereby constructing a three-dimensional geographic model based on the basic two-dimensional coordinates, extracting the contour features of the object from target images of multiple different perspectives, and using the texture mapping modeling algorithm to construct the building model.

Images