A method for intelligent collection of national land space planning data

Abstract

A method for intelligently collecting land space planning data, specifically relating to the field of spatial planning and collection technology. The solution includes a data collection module for collecting basic data related to regional planning and traffic volume analysis included in images and videos within the current target area; an image recognition and analysis module for receiving basic data and extracting spatial features from images and videos; a spatial planning calculation module for sequentially calculating and outputting a spatial planning trigger value K, an optimized spatial planning value TF, and a final result value JSD based on the basic data and spatial features; a warning display module for triggering an early warning for the calculated output spatial planning trigger value K; and a data integration and visualization module for receiving, integrating, and displaying the final result value JSD and analyzing the final result value JSD. The present invention provides a data processing method based on image and video recognition to ensure that spatial planning can meet actual needs.

Description

Technical Field

[0001] The present invention relates to the field of spatial planning and data collection technology, and in particular to a method for intelligently collecting national land space planning data. Background Art

[0002] In traditional national land space planning, data collection and analysis rely on manual surveys, satellite remote sensing, and geographic information system tools. However, these methods are often limited by the accuracy and timeliness of manual operations and the complexity of data processing. With the advancement of computer vision, image processing, and video analysis technologies, image and video recognition technologies have provided new possibilities for spatial planning data collection. These technologies can process large amounts of image data from different sensors in real time and extract valuable spatial information, thereby supporting spatial planning and optimization work more efficiently and accurately.

[0003] Existing spatial planning methods based on image and video recognition technologies often lack precise algorithmic support, resulting in certain errors in the processing and optimization of spatial data. In particular, when faced with complex areas and diverse data, inconsistent planning results are easily generated. Existing methods usually rely on static data input and fail to achieve automated adjustments to spatial planning based on real-time data, which in turn makes spatial planning lack the ability to respond immediately to dynamic changes.

[0004] Therefore, those skilled in the art provide a method for intelligently collecting land space planning data to solve the problems raised in the above background technology. Summary of the Invention

[0005] The technical problem solved by the present invention is to provide a method for intelligent collection of national land space planning data, so as to achieve the purpose of improving the timeliness of warning triggering, enhancing the accuracy of spatial planning optimization, self-adjustment and feedback loop.

[0006] In order to solve the above problems, the present invention provides the following technical solutions:

[0007] A method for intelligently collecting land space planning data includes a data collection module, an image recognition and analysis module, a space planning calculation module, a warning display module, and a data integration and visualization module. The method is characterized in that the space planning calculation module includes a space compliance detection unit, a space planning optimization unit, and a final optimization evaluation unit.

[0008] The details are as follows:

[0009] Data acquisition module: used to collect basic data related to regional planning and traffic volume analysis included in images and videos within the current target area;

[0010] Image recognition and analysis module: used to receive basic data and extract spatial features from images and videos;

[0011] Space planning calculation module: Based on basic data and space characteristics, it calculates and outputs the space planning trigger value K, the optimized space planning value TF, and the final result value JSD in sequence;

[0012] Warning display module: used to trigger an early warning for the calculated output space planning trigger value K, and transmit an instruction to the space planning calculation module on whether to calculate the optimized space planning value TF and the final result value JSD;

[0013] Data integration and visualization module: used to receive, integrate, display the final result value JSD and analyze the final result value JSD.

[0014] Further: the equipment used in the data acquisition module includes a high-resolution camera, a depth camera, an image sensor, a traffic flow sensor, and satellite images;

[0015] The equipment used in the image recognition and analysis module includes computer vision software, image quality assessment software, and image processing software;

[0016] The equipment used in the spatial planning calculation module includes a GIS system and spatial data interface calculation hardware;

[0017] The equipment used in the warning display module includes an alarm and a display device;

[0018] The equipment used in the data integration and visualization module includes space planning and optimization software.

[0019] Further: The calculation formula of the spatial compliance detection unit is as follows:

[0020] K=SQ×(G+J)-A0;

[0021] in:

[0022] K is the spatial planning trigger value;

[0023] SQ is the recognition strength. SQ is a key parameter in image recognition, which indicates the accuracy of identifying spatial elements in the target area extracted from the image through image processing algorithms.

[0024] G is the planning index, which is calculated by using the data including building outlines and functional divisions in the target area through image recognition;

[0025] J is the traffic flow density parameter, which reflects the traffic conditions of the target area extracted from the image;

[0026] A0 is the planning benchmark value;

[0027] The product of SQ×(G+J) reflects the planning value of comprehensive identification, planning, and transportation in the current target area, and is compared and analyzed with the planning benchmark value A0:

[0028] If SQ×(G+J)>A0, then K>0, and a space warning is triggered;

[0029] If SQ×(G+J)≤A0, then K<0 / K=0, and the space warning is not triggered;

[0030] And when K>0, there are trigger factors with the following values:

[0031] A large SQ value indicates that the spatial elements of image recognition are obvious and the region has high resource demand;

[0032] A large G value indicates that the planning density of the current target area is high and that additional resources are needed for support;

[0033] A large J value indicates a high traffic flow density and an increased load on the current target area.

[0034] Furthermore, the recognition strength SQ, the planning index G, and the traffic flow density parameter J all rely on image recognition technology, and the recognition strength SQ evaluates the strength of spatial elements based on the color, texture, and edge features of objects in the target area. The specific calculation formula of the recognition strength SQ is as follows:

[0035] ;

[0036] n is the total amount of sub-region images, which reflects the total amount of sub-region images divided in the target area;

[0037] a i is the weight of the i-th sub-region;

[0038] S i is the accuracy value of the recognition result of the i-th sub-region, where the recognition result is based on the focus of the required collection, and is identified in any one of the three aspects of color, texture, and edge;

[0039] The equipment used for the identification strength SQ includes a high-resolution camera, a depth camera, an image sensor, and computer vision software;

[0040] The calculation formula of the planning index G is as follows:

[0041] ;

[0042] b i Planning factor for the i-th sub-region;

[0043] G i Plan benchmark indicators for the i-th sub-region;

[0044] The equipment used for the planning indicator G includes a GIS system and a spatial data interface for obtaining and calculating the planning factor b of the ith sub-region related to spatial planning. i and the planning benchmark index G of the i-th sub-region i ;

[0045] The calculation formula of the traffic flow density parameter J is as follows:

[0046] ;

[0047] m is the number of measurement points;

[0048] J i is the traffic flow density parameter of the i-th measurement point;

[0049] The equipment used for the traffic flow density parameter J includes traffic flow sensors and satellite images.

[0050] Further: The calculation formula of the space planning optimization unit is as follows:

[0051] ;

[0052] in:

[0053] TF is the optimized space planning value;

[0054] KC is the planning cost;

[0055] Y is the optimization parameter, which reflects the optimization degree evaluation obtained in the process of image recognition target area, including image quality and recognition accuracy;

[0056] M is the area of ​​the target region;

[0057] Y max is the maximum optimization parameter;

[0058] Z is a quality parameter, which reflects the quality assessment of the target area image analysis including image clarity;

[0059] W is the error parameter;

[0060] 、 、 All three calculation parts involve multiplication with the planning cost KC, so that the cost has an appropriate weight in the planning scheme and is reflected in the cost-effectiveness in the actual planning.

[0061] Further: The calculation formula of the optimization parameter Y is as follows:

[0062] ;

[0063] Y i Optimize the quality score for the i-th sub-region;

[0064] The equipment used to optimize the parameter Y includes a high-resolution camera and image quality assessment software;

[0065] The calculation formula of the quality parameter Z is as follows:

[0066] ;

[0067] Z i is the quality assessment value of the i-th sub-region;

[0068] The equipment used for the quality parameter Z includes image quality analysis software;

[0069] The calculation formula of the error parameter W is as follows:

[0070] ;

[0071] E is the total number of error samples, which reflects the total number of samples that generate error calculations in the image within the target area;

[0072] W i is the error value of the i-th sample;

[0073] The equipment used for the error parameter W includes image processing software.

[0074] Further: The calculation formula of the final optimization evaluation unit is as follows:

[0075] ;

[0076] in:

[0077] JSD is the final result value;

[0078] X is the correction factor;

[0079] By calculating the square root of X, the excessive influence of the correction coefficient X on the optimization results can be reduced.

[0080] Further: The calculation formula of the correction coefficient X is as follows:

[0081] ;

[0082] L is the correction amount, which reflects the completed spatial planning and the total amount of correction difference values ​​before and after the spatial planning;

[0083] X i is the i-th corrected difference value;

[0084] The identification strength SQ, the planning index G and the traffic flow density parameter J, the planning benchmark value A0, the optimization parameter Y, the target area M, the maximum optimization parameter Y max , the quality parameter Z, the error parameter W, and the correction coefficient X are all obtained using the spatial data interface.

[0085] Further: any of the target areas are located in different spatial planning areas in the spatial planning, wherein the final result value JSD of the completed planning project that is in the same spatial planning area as the current target area will be collected and intelligently set as the threshold range:

[0086] If the JSD value of the final result of the completed planning project is in the interval of {5-10}, then the threshold value of the JSD value of the final result of the current target area is 7.5, which is the middle value of the threshold interval;

[0087] When the final result value JSD is greater than the middle value of the threshold interval, it reflects that the spatial planning optimization effect is good, which should promote the implementation of the project and provide a basis for the subsequent threshold interval;

[0088] When the final result value JSD is close to zero, it reflects that the spatial planning effect is average and there is room for improvement. The project planning scheme should be continuously optimized.

[0089] When the final result value JSD is negative, the spatial planning effect is not ideal and there are major problems. The planning scheme should be redesigned and the quality of image recognition data should be improved.

[0090] The effects of the above solution are as follows:

[0091] 1. The present invention can quickly determine whether planning standards are met based on spatial information obtained in real time from images and videos through the calculation of the spatial compliance detection unit, and promptly trigger an alert for results where K>0. This real-time feedback based on image recognition technology effectively avoids the delays caused by manual analysis and judgment in traditional methods.

[0092] 2. The present invention can achieve precise optimization through complex calculations of the spatial planning optimization unit, combined with image analysis results and spatial planning data. This method breaks through the traditional spatial planning method's reliance on static data, can dynamically adjust the spatial planning scheme, and improves accuracy and reliability.

[0093] 3. The final optimization evaluation unit of the present invention provides a self-optimization mechanism based on the spatial compliance detection unit and the spatial planning optimization unit. By continuously adjusting the planning results and combining them with the correction coefficient X, it can dynamically adapt to the planning needs of different spaces and ensure the optimization of the planning scheme under different conditions. This innovation greatly improves the flexibility and adaptability of spatial planning and solves the problem that traditional methods cannot adapt to changes in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] Figure 1 This is a flowchart of the method for intelligent collection of land and space planning data;

[0095] Figure 2 This is a structural diagram of the intelligent data collection method for national land space planning;

[0096] Figure 3 This is a schematic diagram of the structure of the space planning calculation module in the present invention;

[0097] Figure 4 This is a schematic diagram of the planning analysis of the final result value JSD result in the present invention. DETAILED DESCRIPTION

[0098] The technical solutions in the embodiments of the present invention will be clearly and completely introduced below with reference to the accompanying drawings in the embodiments of the present invention.

[0099] For example 1, please refer to Figure 1-4 A method for intelligently collecting land space planning data includes a data collection module, an image recognition and analysis module, a space planning calculation module, a warning display module, and a data integration and visualization module. The method is characterized in that the space planning calculation module includes a space compliance detection unit, a space planning optimization unit, and a final optimization evaluation unit.

[0100] The details are as follows:

[0101] Data acquisition module: used to collect basic data related to regional planning and traffic volume analysis included in images and videos within the current target area;

[0102] Image recognition and analysis module: used to receive basic data and extract spatial features from images and videos;

[0103] Space planning calculation module: Based on basic data and space characteristics, it calculates and outputs the space planning trigger value K, the optimized space planning value TF, and the final result value JSD in sequence;

[0104] Warning display module: used to trigger an early warning for the calculated output space planning trigger value K, and transmit an instruction to the space planning calculation module on whether to calculate the optimized space planning value TF and the final result value JSD;

[0105] Data integration and visualization module: used to receive, integrate, display the final result value JSD and analyze the final result value JSD;

[0106] The equipment used in the data acquisition module includes high-resolution cameras, depth cameras, image sensors, traffic flow sensors, and satellite images;

[0107] The equipment used in the image recognition and analysis module includes computer vision software, image quality assessment software, and image processing software;

[0108] The equipment used in the spatial planning calculation module includes GIS system and spatial data interface calculation hardware;

[0109] The equipment used in the alarm display module includes alarms and display devices;

[0110] The equipment used in the data integration and visualization module includes space planning and optimization software.

[0111] This embodiment focuses on image and video recognition technology, and effectively realizes the intelligent collection and optimization of national land space planning through multiple links such as data collection, image analysis, spatial planning optimization, and result integration. The close cooperation between modules and the optimization of calculation methods ensure the accuracy and rationality of the final results. At the same time, it also provides a data processing method based on image and video recognition to ensure that spatial planning can meet actual needs.

[0112] See also Figure 1-4 , the calculation formula of the spatial compliance detection unit is as follows:

[0113] K=SQ×(G+J)-A0;

[0114] in:

[0115] K is the spatial planning trigger value;

[0116] SQ is the recognition strength. SQ is a key parameter in image recognition, which indicates the accuracy of identifying spatial elements in the target area extracted from the image through image processing algorithms.

[0117] G is the planning index, which is calculated by using the data including building outlines and functional divisions in the target area through image recognition;

[0118] J is the traffic flow density parameter, which reflects the traffic conditions of the target area extracted from the image;

[0119] A0 is the planning benchmark value;

[0120] The product of SQ×(G+J) reflects the planning value of comprehensive identification, planning, and transportation in the current target area, and is compared and analyzed with the planning benchmark value A0:

[0121] If SQ×(G+J)>A0, then K>0, and a space warning is triggered;

[0122] If SQ×(G+J)≤A0, then K<0 / K=0, and the space warning is not triggered;

[0123] And when K>0, there are trigger factors with the following values:

[0124] A large SQ value indicates that the spatial elements of image recognition are obvious and the region has high resource demand;

[0125] A large G value indicates that the planning density of the current target area is high and that additional resources are needed for support;

[0126] A large J value indicates a high traffic density and an increased load on the current target area;

[0127] The recognition strength SQ, planning index G, and traffic flow density parameter J all rely on image recognition technology. The recognition strength SQ evaluates the strength of spatial elements based on the color, texture, and edge features of objects in the target area. The specific calculation formula for the recognition strength SQ is as follows:

[0128] ;

[0129] n is the total amount of sub-region images, which reflects the total amount of sub-region images divided in the target area;

[0130] a i is the weight of the i-th sub-region;

[0131] S i is the accuracy value of the recognition result of the i-th sub-region, where the recognition result is based on the focus of the required collection, and is identified in any one of the three aspects of color, texture, and edge;

[0132] The equipment used to identify the intensity SQ includes high-resolution cameras, depth cameras, image sensors, and computer vision software;

[0133] The calculation formula of planning index G is as follows:

[0134] ;

[0135] b i Planning factor for the i-th sub-region;

[0136] G i Plan benchmark indicators for the i-th sub-region;

[0137] The equipment used for planning indicator G includes GIS system and spatial data interface, which is used to obtain and calculate the planning factor b of the ith sub-region related to spatial planning. i and the planning benchmark index G of the i-th sub-region i ;

[0138] The calculation formula of traffic flow density parameter J is as follows:

[0139] ;

[0140] m is the number of measurement points;

[0141] J i is the traffic flow density parameter of the i-th measurement point;

[0142] The equipment used for traffic flow density parameter J includes traffic flow sensors and satellite images.

[0143] The spatial compliance detection unit of this embodiment determines whether the planning standards are met by evaluating the recognition strength of spatial elements and traffic flow density in images and videos, and triggers warnings and alarms when K>0. Through this mechanism, it is possible to monitor in real time whether the spatial planning exceeds the safety threshold, and issue warnings in time to help planners respond quickly. In addition, the spatial compliance detection unit is used to perform real-time calculations on various spatial data in images and videos, which can help automatically adjust planning standards, including changes in traffic density and building distribution, so that the planning is always within a reasonable safety range.

[0144] See also Figure 1-4 , the calculation formula of the space planning optimization unit is as follows:

[0145] ;

[0146] in:

[0147] TF is the optimized space planning value;

[0148] KC is the planning cost;

[0149] Y is the optimization parameter, which reflects the optimization degree evaluation obtained in the process of image recognition target area, including image quality and recognition accuracy;

[0150] M is the area of ​​the target region;

[0151] Y max is the maximum optimization parameter;

[0152] Z is a quality parameter, which reflects the quality assessment of the target area image analysis including image clarity;

[0153] W is the error parameter;

[0154] 、 、 All three calculation parts involve multiplication with the planning cost KC, so that the cost has an appropriate weight in the planning scheme and is reflected in the cost-effectiveness of the actual planning;

[0155] The calculation formula of the optimization parameter Y is as follows:

[0156] ;

[0157] Y i Optimize the quality score for the i-th sub-region;

[0158] The equipment used to optimize the parameter Y includes a high-resolution camera and image quality assessment software;

[0159] The calculation formula of the quality parameter Z is as follows:

[0160] ;

[0161] Z i is the quality assessment value of the i-th sub-region;

[0162] The equipment used for quality parameter Z includes image quality analysis software;

[0163] The calculation formula of the error parameter W is as follows:

[0164] ;

[0165] E is the total number of error samples, which reflects the total number of samples that generate error calculations in the image within the target area;

[0166] W i is the error value of the i-th sample;

[0167] The equipment used for the error parameter W includes image processing software.

[0168] In this embodiment, first The calculation part calculates the cost factors in spatial planning and adjusts the optimization parameters YC and the target area M to ensure that the optimized plan can meet the needs and control the efficiency of resource use. The calculation part ensures that the optimization range does not exceed the maximum limit, where Partial calculation of the optimization parameter Y and the maximum optimization parameter Y max The ratio of the optimization results to ensure that they do not exceed a certain limit. Through this calculation, the impact of optimization can be balanced to prevent resource waste and system overload caused by over-optimization. The calculation further adjusts the cost factors and takes into account the quality-related influences of spatial planning, among which: The square root operation of Z is performed to obtain a normalized value of the regional quality. The square root operation is often used to reduce the over-amplification effect when the quality is poor, so that the low-quality area will not have too much impact on the overall calculation;

[0169] Specifically, this algorithm Sequentially with and The subtraction of can get the comprehensive adjustment result of cost, which shows how the optimization, quality and error impact of the region are reflected in the spatial planning, and through the adjustment of the relevant factors in the optimization planning process;

[0170] The spatial planning optimization unit of this algorithm is based on the spatial planning trigger value K obtained by the spatial compliance detection unit. It can optimize the spatial planning data. By combining the optimization parameter Y in the image recognition process with the relevant indicators of spatial planning, the spatial planning optimization unit can dynamically adjust the spatial planning scheme to make it more in line with current needs and conditions.

[0171] The optimization parameter Y, quality parameter Z, and error parameter W in the formula can reflect the quality and recognition accuracy of the image data in real time, thereby affecting the planning results. This calculation method can avoid incorrect planning decisions caused by low-quality images.

[0172] In actual applications, if it is found in regional planning that facilities in certain places are too dense, resulting in waste of resources, the spatial planning optimization unit can optimize the resource allocation of relevant areas, including adjusting the development zone area or resource allocation ratio, to improve the rationality of spatial planning.

[0173] See also Figure 1-4 , the calculation formula of the final optimization evaluation unit is as follows:

[0174] ;

[0175] in:

[0176] JSD is the final result value;

[0177] X is the correction factor;

[0178] By calculating the square root of X, the excessive influence of the correction coefficient X on the optimization results is reduced;

[0179] The calculation formula of the correction coefficient X is as follows:

[0180] ;

[0181] L is the correction amount, which reflects the completed spatial planning and the total amount of correction difference values ​​before and after the spatial planning;

[0182] X i is the i-th corrected difference value;

[0183] Identification strength SQ, planning index G and traffic flow density parameter J, planning benchmark value A0, optimization parameter Y, target area M, maximum optimization parameter Y max , quality parameter Z, error parameter W, and correction coefficient X are all obtained using the spatial data interface.

[0184] In this embodiment, first The calculation part calculates the ratio between the optimized space planning value TF and the space planning trigger value K. Dividing the optimized space planning value TF by the space planning trigger value K can obtain the ratio of the optimized planning result to the original warning trigger value. If the value is large, it means that the optimization effect is obvious. If it is small, further optimization of the planning is needed.

[0185] The calculation part further adjusts the optimization results by introducing a correction coefficient X and takes into account the influence of external factors. X represents a correction coefficient related to spatial planning and is related to the accuracy of geographic information and regional variation factors. By calculating the square root of X, the excessive influence of the correction coefficient X on the optimization results can be reduced, ensuring that the influence of the correction factor is within a controllable range.

[0186] The algorithm's final optimization evaluation unit calculates the final result value JSD by combining the optimized spatial planning value TF from the spatial planning optimization unit and the spatial planning trigger value K from the spatial compliance detection unit. This result not only takes into account the optimization effect of spatial planning but also fine-tunes the result using the correction coefficient X to ensure that the final result better meets actual needs.

[0187] The final optimization evaluation unit not only outputs the results, but its calculations also reversely affect the initial input values ​​in the spatial compliance detection unit, prompting continuous optimization of spatial planning. This "feedback loop" enables spatial planning to be continuously adjusted as new data changes, thereby forming an adaptive optimization effect.

[0188] For example 2, please refer to Figure 1-4 , any target area is located in different spatial planning areas in the spatial planning. Among them, the final result value JSD of the completed planning project that is in the same spatial planning area as the current target area will be collected and intelligently set as the threshold range:

[0189] If the JSD value of the final result of the completed planning project is in the interval of {5-10}, then the threshold value of the JSD value of the final result of the current target area is 7.5, which is the middle value of the threshold interval;

[0190] When the final result value JSD is greater than the middle value of the threshold interval, it reflects that the spatial planning optimization effect is good, which should promote the implementation of the project and provide a basis for the subsequent threshold interval;

[0191] When the final result value JSD is close to zero, it reflects that the spatial planning effect is average and there is room for improvement. The project planning scheme should be continuously optimized.

[0192] If the final result value JSD is negative, the spatial planning effect is not ideal and there are major problems. The planning scheme should be redesigned and the quality of image recognition data should be improved.

[0193] In this embodiment, the final result value JSD calculated by the final optimization evaluation unit continuously adjusts the planning scheme and also reversely affects the various input parameters in the spatial compliance detection unit. Specifically, when the final result value JSD indicates that some spatial planning is unreasonable, it will prompt the relevant parameters in the spatial compliance detection unit to be recalculated to ensure that the adjustment of the spatial planning is more accurate and reasonable.

[0194] This embodiment uses the feedback function of the final optimization and evaluation unit to enable spatial planning to be automatically and dynamically adjusted according to actual conditions. This allows for continuous optimization of planning solutions during implementation, reduces human intervention, and improves the scientific nature and real-time nature of decision-making. As new spatial data and monitoring information are continuously input, the self-correction mechanism provided by the final optimization and evaluation unit can automatically update planning results, reducing planning errors and improving space utilization efficiency.

[0195] Overall, the combination of the spatial compliance detection unit, the spatial planning optimization unit, and the final optimization evaluation unit forms a dynamic optimization and feedback adjustment cycle mechanism, providing an efficient, accurate, and adaptive solution for the collection of national land space planning data under image and video recognition. Through these formulas, the system can collect data in real time, evaluate planning effects, optimize spatial planning, and automatically adjust during the planning process, ultimately improving the accuracy, flexibility, and feasibility of planning. This beneficial effect not only enhances the scientific nature and accuracy of spatial planning, but also greatly improves decision-making efficiency and reduces the need for human intervention.

[0196] As for the final result value JSD, it is worth noting that when the final result value JSD is greater than the set threshold, it indicates that the spatial planning optimization effect is good and meets the expected goals. The final result value JSD greater than the threshold also indicates that the optimization indicators of resource allocation, land use, and traffic flow in the plan have achieved the expected results. This shows that the spatial planning data obtained by image and video recognition has effectively helped optimize the allocation of regional resources and facility construction. A higher final result value JSD means that the current planning is successful and can meet the needs of the region and promote the construction and development process. The high value of the final result value JSD can also be used as the basis for subsequent decision-making to further improve spatial planning. Through the feedback of image recognition and video analysis data, the allocation of regional resources can continue to be optimized to adapt to future changes in demand. In addition, through the identification and analysis of high final result values ​​JSD, the spatial planning system can maintain efficient resource allocation and optimization strategies. This shows that the image recognition system performs well in processing spatial data and improves the overall efficiency of the planning system.

[0197] When the final result value JSD is close to zero, it means that the optimization effect of spatial planning is not ideal and there are some problems. At this time, although there are negative effects, it also means that some parameters in spatial planning have not been effectively optimized. At this time, although the planning has made certain adjustments, further optimization is still needed. It is necessary to re-examine the regional division and traffic flow prediction factors. Some regional recognition in image and video data may also have deviations and inaccuracies, which prompts the need to improve the accuracy of data collection and analysis. Since the accuracy and quality of image recognition is one of the reasons why the final result value JSD is close to zero, the feedback results of the number of times indicate that more high-quality image data needs to be collected;

[0198] A negative JSD indicates a severely underperforming plan. While this is not ideal, it can provide valuable information that can help address underlying issues. Specifically, a negative JSD indicates significant flaws in the spatial plan, including severely uneven resource allocation, overbuilding in some areas while under-resourced in others, and errors in the image recognition data, leading to incorrect zoning. These issues must be addressed promptly to avoid further losses. A negative JSD also indicates that the current spatial plan is insufficient and requires a thorough overhaul, including changes in resource allocation, improved data analysis methods, and corrected image recognition results. This ensures that the plan ultimately meets actual needs. A negative JSD can also serve as an important driver for improving image recognition algorithms and data quality. Negative values ​​indicate significant errors and mismatches in image recognition and video analysis, necessitating a comprehensive assessment and improvement of data collection, analysis, and processing. Negative values ​​provide clear feedback on areas that need improvement to ensure more accurate and effective future planning.

[0199] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be based on the scope defined by the claims.

Claims

1. A method for intelligently collecting land and space planning data, comprising a data collection module, an image recognition and analysis module, a spatial planning calculation module, a warning display module, and a data integration and visualization module, characterized in that: The spatial planning calculation module includes a spatial compliance detection unit, a spatial planning optimization unit, and a final optimization evaluation unit; Specifically as follows: Data acquisition module: Used to collect basic data related to regional planning and traffic volume analysis included in images and videos within the current target area; Image recognition and analysis module: Used to receive the basic data and extract spatial features from the images and videos; Spatial planning calculation module: Based on the basic data and spatial features, and sequentially calculate and output the spatial planning trigger value K, the optimized spatial planning value TF, and the final result value JSD; Alarm display module: Used to trigger an early warning for the calculated spatial planning trigger value K, and transmit an instruction on whether to calculate the optimized spatial planning value TF and the final result value JSD to the spatial planning calculation module; Data integration and visualization module: Used to receive, integrate, display the final result value JSD, and the analysis of the final result value JSD; The calculation formula of the spatial compliance detection unit is as follows: K = SQ×(G + J) - A0; Where: K is the spatial planning trigger value; SQ is the recognition intensity; G is the planning index; J is the traffic flow density parameter; A0 is the planning reference value; The recognition intensity SQ, the planning index G, and the traffic flow density parameter J all rely on image recognition technology, and the recognition intensity SQ evaluates the intensity of spatial elements based on the characteristics of the color, texture, and edges of objects in the target area. The specific calculation formula of the recognition intensity SQ is as follows: ； n is the total amount of sub-region images, which reflects the total amount of sub-region images divided in the target area; a i is the weight of the i-th sub-region; S i is the accuracy value of the recognition result of the i-th sub-region, where the recognition result is based on the focus of the required collection, and is identified in any one of the three aspects of color, texture, and edge; The devices used for the recognition intensity SQ include high-resolution cameras, depth cameras, image sensors, and computer vision software; The calculation formula of the planning index G is as follows: ； b i is the planning factor for the i-th sub-region; G i Plan benchmark indicators for the i-th sub-region; The equipment used for the planning indicator G includes a GIS system and a spatial data interface for obtaining and calculating the planning factor b of the ith sub-region related to spatial planning. i and the planning benchmark index G of the i-th sub-region i ; The calculation formula of the traffic flow density parameter J is as follows: ； m is the number of measurement points; J i is the traffic flow density parameter of the i-th measurement point; The devices used for the traffic flow density parameter J include traffic flow sensors and satellite images; The calculation formula of the spatial planning optimization unit is as follows: ； Where: TF is the optimized spatial planning value; KC is the planning cost; Y is the optimization parameter, which reflects the optimization degree evaluation obtained in the process of image recognition target area, including image quality and recognition accuracy; M is the area of ​​the target area; Y max is the maximum optimization parameter; Z is the quality parameter, which reflects the quality assessment of the target area image analysis including image clarity; W is the error parameter.

2. The method for intelligently collecting land space planning data according to claim 1, characterized in that: The devices used by the data acquisition module include high-resolution cameras, depth cameras, image sensors, traffic flow sensors, and satellite images; The devices used by the image recognition and analysis module include computer vision software, image quality evaluation software, and image processing software; The devices used by the spatial planning calculation module include a GIS system and spatial data interface calculation hardware; The devices used by the alarm display module include sirens and display devices; 3. The method for intelligently collecting land space planning data according to claim 2, characterized in that: The devices used by the data integration and visualization module include spatial planning and optimization software. The product of SQ×(G + J) reflects the planning value of comprehensive recognition, planning, and traffic within the current target area, and is compared and analyzed with the planning reference value A0: If SQ×(G + J) > A0, then K > 0, and a spatial early warning is triggered; If SQ×(G + J) < A0, then K < 0 / K = 0, and no spatial early warning is triggered; And in the case of K > 0, there are the following triggering factors for the values: A large SQ value indicates that the spatial elements recognized in the image are obvious, and there is a high resource demand in the area; A large G value indicates that the planning density of the current target area is high, and resources need to be increased for support; A large J value indicates a high traffic flow density and an increased load on the current target area.

4. The method for intelligently collecting land space planning data according to claim 3, characterized in that: The calculation formula of the optimization parameter Y is as follows: ； Y i Optimize the quality score for the i-th sub-region; The equipment used to optimize the parameter Y includes a high-resolution camera and image quality assessment software; The calculation formula of the quality parameter Z is as follows: ； Z i is the quality assessment value of the i-th sub-region; The equipment used for the quality parameter Z includes image quality analysis software; The calculation formula of the error parameter W is as follows: ； E is the total number of error samples, which reflects the total number of samples that generate error calculations in the image within the target area; W i is the error value of the i-th sample; The equipment used for the error parameter W includes image processing software.

5. The method for intelligently collecting land space planning data according to claim 4, characterized in that: The calculation formula of the final optimization evaluation unit is as follows: ； in: JSD is the final result value of space planning; X is the correction factor; By calculating the square root of X, the excessive influence of the correction coefficient X on the optimization results can be reduced.

6. The method for intelligently collecting land space planning data according to claim 5, characterized in that: The calculation formula of the correction coefficient X is as follows: ； L is the correction amount, which reflects the completed spatial planning and the total amount of correction difference values ​​before and after the spatial planning; X i is the i-th corrected difference value; The identification strength SQ, the planning index G and the traffic flow density parameter J, the planning benchmark value A0, the optimization parameter Y, the target area M, the maximum optimization parameter Y max , the quality parameter Z, the error parameter W, and the correction coefficient X are all obtained using the spatial data interface.

7. The method for intelligently collecting land space planning data according to claim 6, characterized in that: Any of the target areas is located in different spatial planning areas in the spatial planning, among which the final result value JSD of the completed planning project in the same spatial planning area as the current target area will be collected and intelligently set as the threshold range: If the interval of the collected final result value JSD is {5-10}, then the threshold value of the final result value JSD of the current target area is 5, which is the middle value of the threshold interval; When the final result value JSD is greater than the middle value of the threshold interval, it reflects that the spatial planning optimization effect is good, which should promote the implementation of the project and provide a basis for the subsequent threshold interval; When the final result value JSD is close to zero, it reflects that the spatial planning effect is average and there is room for improvement. The project's land planning scheme should be continuously optimized. When the final result value JSD is negative, the spatial planning effect is not ideal and there are major problems. The planning scheme should be redesigned and the quality of image recognition data should be improved.

Images