A system and method for identifying urban green space encroachment and degradation based on computer vision recognition

Abstract

The present application provides a system and method for identifying encroachment and degradation of urban green space based on computer vision recognition, wherein the method includes collecting multi-temporal images of urban green space and sorting them by timestamp to generate a difference map to reflect the dynamic changes of green space; vectorizing the dynamic information, establishing a digital model as a reference benchmark for the green space boundary, and overlaying and comparing it with the latest remote sensing image to obtain the corrected green space boundary; using a target detection network to identify non-vegetation covered areas in multi-temporal images, generating a preliminary green space encroachment location map, and then performing shape regularization and size filtering to optimize the green space encroachment location map; based on the optimized map, analyzing the temporal and spatial distribution characteristics of each factor, combining the changing trend of the non-vegetation covered area to make a prediction, and generating a trend prediction result. Finally, the prediction results are quantitatively evaluated to generate a comprehensive degradation severity report. The present application improves the efficiency and accuracy of identifying encroachment and degradation of urban green space.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer vision recognition technology, and in particular to a system and method for identifying urban green space encroachment and degradation based on computer vision recognition. Background Art

[0002] Against the backdrop of rapid urbanization, urban green spaces, as an important component of improving environmental quality and enhancing residents' quality of life, are facing serious problems of encroachment and degradation.

[0003] In order to effectively monitor these changes, traditional monitoring methods mainly include field surveys, remote sensing image analysis, and analysis of geographic information systems combined with historical data.

[0004] However, field surveys rely on manual visits and record-keeping, which can provide intuitive information but are inefficient and difficult to cover large areas. Remote sensing image analysis uses data collected by satellites or drones to monitor green space changes. While this can expand the monitoring scope, the manual labeling and simple classification algorithms used in traditional methods have a low degree of automation and are unable to accurately handle changes in complex environments. While GIS-based historical data analysis can provide some reference, it has limitations in capturing real-time changes. Overall, traditional methods for identifying encroachment and degradation of urban green spaces are inefficient. Summary of the Invention

[0005] The embodiments of the present application provide a system and method for identifying encroachment and degradation of urban green spaces based on computer vision recognition, so as to solve the problem of low efficiency in identifying encroachment and degradation of urban green spaces in the prior art.

[0006] In a first aspect, the present invention provides an urban green space encroachment and degradation identification system based on computer vision recognition, comprising:

[0007] The acquisition module (i.e., the drone imaging detection platform) is used to periodically collect multi-temporal images of urban green spaces, sort the multi-temporal images by timestamp, generate difference maps between the images of each temporal phase, and obtain dynamic information reflecting the changes of urban green spaces over time based on the difference maps between the images of each temporal phase;

[0008] A processing module (i.e., a high-performance server) is used to vectorize the dynamic information reflecting the changes in green space over time based on historical geographic information system records and legally required land boundary information to establish a digital model as a reference for the green space boundary. The digital model is then overlaid and compared with the latest remote sensing imagery to obtain a corrected green space boundary. The latest remote sensing imagery refers to an image acquired at a recent point in time using modern remote sensing technology to provide the most up-to-date information on land surface conditions.

[0009] an identification module for identifying non-vegetation covered areas in the multi-temporal image based on the corrected green space boundaries using a deep learning target detection network to generate a preliminary green space encroachment location map, and performing shape regularization and size filtering on the preliminary green space encroachment location map using morphological operations and connected domain analysis techniques to generate an optimized green space encroachment location map, wherein the non-vegetation covered areas include artificial structures and hardened ground in the green space image;

[0010] A generation module is used to obtain the temporal and spatial distribution characteristics of various factors based on the optimized green space encroachment location map, using a spatiotemporal data analysis framework and combining environmental parameters, predict the temporal and spatial distribution characteristics of various factors in combination with the changing trend of the non-vegetation covered area, generate trend prediction results, perform quantitative evaluation processing on the trend prediction results, and generate a degradation severity report, wherein the environmental parameters include climate data and human activity intensity, and the various factors refer to various variables or conditions that may affect green space encroachment and degradation.

[0011] In a second aspect, an embodiment of the present application provides a method for identifying encroachment and degradation of urban green spaces based on computer vision recognition, comprising:

[0012] Periodically collecting multi-temporal images of urban green spaces, sorting the multi-temporal images according to timestamps, generating difference maps between the images of each temporal phase, and obtaining dynamic information reflecting temporal changes of urban green spaces based on the difference maps between the images of each temporal phase;

[0013] Based on historical geographic information system records and legally required land boundary information, vectorize the dynamic information reflecting the changes in the green space over time to establish a digital model as a reference for the green space boundary. Superimpose and compare the digital model with the latest remote sensing imagery to obtain a corrected green space boundary. The latest remote sensing imagery refers to an image acquired at a recent point in time using modern remote sensing technology to provide the most up-to-date information on the surface conditions.

[0014] Based on the corrected green space boundaries, a deep learning object detection network is used to identify non-vegetation covered areas in the multi-temporal image to generate a preliminary green space encroachment location map. Morphological operations and connected domain analysis techniques are used to perform shape regularization and size filtering on the preliminary green space encroachment location map to generate an optimized green space encroachment location map, wherein the non-vegetation covered areas include artificial structures and hardened ground in the green space image.

[0015] Based on the optimized green space encroachment location map, the spatiotemporal data analysis framework is used in combination with environmental parameters to obtain the temporal and spatial distribution characteristics of each factor. The temporal and spatial distribution characteristics of each factor are combined with the changing trend of the non-vegetation covered area to perform forecast processing to generate trend forecast results. The trend forecast results are quantitatively evaluated to generate a degradation severity report. The environmental parameters include climate data and human activity intensity. The factors refer to various variables or conditions that may affect green space encroachment and degradation.

[0016] Optionally, based on the corrected green space boundary, a deep learning target detection network is used to identify non-vegetation covered areas in the multi-temporal image to generate a preliminary green space encroachment location map, and morphological operations and connected domain analysis techniques are used to perform shape regularization and size filtering on the preliminary green space encroachment location map to generate an optimized green space encroachment location map, including:

[0017] Based on the corrected green space boundaries, a pre-trained deep learning object detection network is used in combination with a transfer learning algorithm to optimize model parameters. Each green space image in the multi-temporal image dataset is automatically identified for non-vegetation covered areas to obtain a preliminary green space encroachment location map.

[0018] Based on the preliminary green space encroachment location map, morphological operation technology is used in combination with the watershed algorithm to perform shape regularization processing on the detected non-vegetation covered areas to obtain shape-regularized regions. Connected domain analysis technology is used in combination with the distance transformation algorithm to perform size filtering processing on the shape-regularized regions to generate accurate connected domains that meet the actual green space encroachment standards.

[0019] The information of the accurate connected domain that meets the actual green space encroachment standard is comprehensively processed, and the spatial relationship between each connected domain in the accurate connected domain is evaluated using a spatial statistical analysis method to output a final green space encroachment location map.

[0020] Optionally, based on the corrected green space boundary, a pre-trained deep learning object detection network is used in combination with a transfer learning algorithm to optimize model parameters, and each green space image in the multi-temporal image dataset is automatically identified for non-vegetation covered areas to obtain a preliminary green space encroachment location map, including:

[0021] Using a deep learning object detection network suitable for urban green space scenes, preprocessing each green space image in the multi-temporal image dataset to generate prepared image data, wherein the preprocessing includes resizing, color space conversion, and normalization;

[0022] Obtain a small sample data set collected locally, use a transfer learning algorithm to fine-tune the pre-trained model, optimize the last layer or layers of the pre-trained model, adapt the pre-trained model to the data distribution of the new task, optimize the parameters of the pre-trained model, and obtain an object detection model optimized by transfer learning;

[0023] Applying the object detection model optimized by transfer learning to perform pixel-level classification and bounding box prediction on the prepared green space image, using non-maximum suppression technology to remove redundant detection boxes, retaining the most likely candidate areas, and generating an image marked with non-vegetation covered areas;

[0024] Based on the image marked with the non-vegetation covered area, a preliminary green space encroachment location map is formed, and the image marked with the non-vegetation covered area shows the location and scope of the suspected encroachment area.

[0025] Optionally, applying the object detection model optimized by transfer learning to perform pixel-level classification and bounding box prediction on the prepared green space image, using non-maximum suppression technology to remove redundant detection boxes, retaining the most likely candidate areas, and generating an image marked with non-vegetation covered areas, including:

[0026] Using the object detection model optimized by transfer learning, the prepared green space image is classified at the pixel level to obtain a probability map of each pixel belonging to the background or non-vegetation covered area;

[0027] Based on the probability map of each pixel belonging to the background or non-vegetation covered area, the regression information output by the target detection model is used to obtain the detected non-vegetation covered area, and a bounding box prediction is performed on the detected non-vegetation covered area to generate a series of candidate area bounding boxes including position information and confidence scores, wherein the position information includes center coordinates, width, and height;

[0028] Based on the series of candidate region bounding boxes containing position information and confidence scores, applying non-maximum suppression technology, sorting by confidence score, sequentially comparing the intersection-over-union ratios between adjacent bounding boxes of the candidate region bounding boxes, and retaining the bounding boxes with the highest confidence score for those whose intersection-over-union ratios are higher than a preset threshold, and removing other redundant detection boxes to obtain the retained bounding boxes;

[0029] The retained bounding box is drawn onto the periodic multi-temporal image dataset to form an image with non-vegetation covered areas marked.

[0030] Optionally, based on the optimized green space encroachment location map, a spatiotemporal data analysis framework is used in combination with environmental parameters to obtain temporal and spatial distribution characteristics of various factors, the temporal and spatial distribution characteristics of various factors are combined with the change trend of the non-vegetation covered area to perform forecasting processing to generate trend forecast results, the trend forecast results are quantitatively evaluated to generate a degradation severity report, including:

[0031] Using the optimized green space encroachment location map data, the information of the non-vegetation covered area is integrated and processed to obtain a data set suitable for a spatiotemporal data analysis framework;

[0032] Collecting and preprocessing environmental parameters based on the datasets suitable for the spatiotemporal data analysis framework to generate multidimensional spatiotemporal data related to changes in non-vegetated areas;

[0033] Based on the multidimensional spatiotemporal data related to the changes in non-vegetation covered areas, the temporal and spatial distribution characteristics of each factor in the environmental parameters are analyzed and modeled to obtain a relationship model between different environmental parameters and the changes in non-vegetation covered areas;

[0034] Using the relationship model between the different environmental parameters and the changes in the non-vegetation covered area, the change trend of the non-vegetation covered area is predicted and processed to generate trend prediction results for a period of time in the future;

[0035] Based on the trend prediction results for the future period, a quantitative assessment is conducted on the expansion speed and impact range of the non-vegetation covered area and the degree of ecological impact of the non-vegetation covered area to generate a degradation severity report.

[0036] Optionally, the using of the relationship model between the different environmental parameters and the change of the non-vegetation covered area to predict the change trend of the non-vegetation covered area and generate a trend prediction result for a period of time in the future includes:

[0037] Using the relationship model between the different environmental parameters and the changes in non-vegetation covered areas, selecting an appropriate machine learning or statistical model, training the change data of the non-vegetation covered areas, and constructing a prediction model that captures the temporal and spatial variation patterns;

[0038] According to the requirements of the prediction model that captures temporal and spatial variation patterns, the pre-processed multi-dimensional spatiotemporal data are integrated, and the non-vegetation covered area change data including historical periods and the latest observations are used as input to generate an input dataset suitable for prediction;

[0039] Based on the input data set suitable for prediction, different future scenario assumptions are set to simulate the changing trends of different non-vegetation covered areas that may occur in the future, and generate multiple prediction scenarios covering best-case scenarios, most likely scenarios, and worst-case scenarios. The different future scenario assumptions include different paths of climate change and changes in the intensity of human activities;

[0040] By using the multiple prediction scenarios covering the best case, the most likely case and the worst case, the short-term and long-term change trends of the non-vegetation covered area are predicted and processed to generate trend prediction results at a series of future time points.

[0041] Optionally, the dynamic information reflecting the changes of the green space over time is vectorized based on historical geographic information system records and legally required land boundary information to establish a digital model as a reference for the green space boundary, and the digital model is superimposed and compared with the latest remote sensing imagery to obtain a corrected green space boundary, including:

[0042] Using historical geographic information system records and legally required land use boundary information, vectorize the dynamic information reflecting the changes of green space over time to obtain vector data that accurately represents the changes of green space and the legal boundaries of green space changes;

[0043] Based on the vector data accurately representing the green space changes and the legal boundaries of the green space changes, a digital model is established and used as a reference for the green space boundaries, converted into a digital format, and a high-precision digital model of the green space changes and boundary locations is generated;

[0044] Acquire the latest remote sensing images with high resolution, high precision and high timeliness, use image registration technology to make the coordinate system of the digital model consistent with that of the latest remote sensing images, and perform superposition and comparison processing to obtain the detection results of green space boundary changes;

[0045] Based on the detection results of the green space boundary changes, combined with field investigations or other auxiliary data sources, the dynamic information reflecting the changes of the green space over time is adjusted and corrected to generate a corrected green space boundary.

[0046] In a third aspect, an embodiment of the present application provides a computing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods for identifying encroachment and degradation of urban green space based on computer vision recognition as described in the first aspect.

[0047] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, which, when executed by a processor, implements a method for identifying encroachment and degradation of urban green space based on computer vision recognition as described in any one of the first aspects.

[0048] In an embodiment of the present application, multi-temporal images of urban green spaces are periodically collected, sorted according to timestamps, and difference maps between the images of each temporal phase are generated. Based on the difference maps between the images of each temporal phase, dynamic information reflecting the temporal changes of urban green spaces is obtained. Based on historical geographic information system records and legally required land boundary information, the dynamic information reflecting the temporal changes of green spaces is vectorized to establish a digital model as a reference for the green space boundary. The digital model is superimposed and compared with the latest remote sensing imagery to obtain a corrected green space boundary. The latest remote sensing image refers to an image acquired at a recent point in time using modern remote sensing technology to provide the latest surface condition information.

[0049] Based on the corrected green space boundaries, a deep learning object detection network is used to identify non-vegetation covered areas in the multi-temporal image to generate a preliminary green space encroachment location map. Morphological operations and connected domain analysis techniques are used to perform shape regularization and size filtering on the preliminary green space encroachment location map to generate an optimized green space encroachment location map, wherein the non-vegetation covered areas include artificial structures and hardened ground in the green space image.

[0050] Based on the optimized green space encroachment location map, the spatiotemporal data analysis framework is used in combination with environmental parameters to obtain the temporal and spatial distribution characteristics of each factor. The temporal and spatial distribution characteristics of each factor are combined with the changing trend of the non-vegetation covered area to perform forecast processing to generate trend forecast results. The trend forecast results are quantitatively evaluated to generate a degradation severity report. The environmental parameters include climate data and human activity intensity. The factors refer to various variables or conditions that may affect green space encroachment and degradation.

[0051] The technical solution of this application has the following beneficial effects:

[0052] This application periodically collects multi-temporal images of urban green spaces and generates difference maps sorted by timestamp, accurately capturing the dynamic changes of green spaces over time. This method not only improves the temporal resolution of the data but also provides rich historical information for subsequent analysis. Green space dynamic information is vectorized using historical geographic information system records and legally mandated land boundary information, and a high-precision digital model is established as a reference. By overlaying and comparing this model with the latest remote sensing imagery, the accuracy and timeliness of green space boundaries are ensured, human errors are reduced, and monitoring accuracy is improved.

[0053] Based on the corrected green space boundaries, a deep learning-based object detection network automatically identifies non-vegetated areas, such as artificial structures and hardened surfaces, in multi-temporal imagery, generating preliminary green space encroachment location maps. Morphological operations and connected domain analysis techniques are combined to further optimize these location maps, ensuring the accuracy of shape regularization and size filtering, thereby improving the reliability and practicality of the identification results. Using a spatiotemporal data analysis framework, combined with environmental parameters such as climate data and human activity intensity, the temporal and spatial distribution characteristics of various factors are analyzed to predict the changing trends of non-vegetated areas. This comprehensive analysis approach considers not only the influence of natural factors but also the impact of human activities, providing a more comprehensive assessment of the severity of green space degradation. The predicted results are quantitatively evaluated to generate detailed degradation severity reports. These reports are presented in intuitive electronic maps and charts for easy understanding and application by decision makers. Furthermore, the expert system's rule library and case study database provide scientifically sound conservation recommendations, providing strong support for urban planning and environmental protection.

[0054] Furthermore, by combining a transfer learning algorithm to optimize model parameters, a pre-trained deep learning object detection network was used to automatically identify non-vegetated areas for each green space image in the multi-temporal image dataset. This approach not only improved the model's adaptability and generalization capabilities in specific urban green space scenarios, but also significantly enhanced the accuracy of identifying non-vegetated areas. The initial green space encroachment location map was then regularized using morphological operations combined with a watershed algorithm, ensuring that the detected non-vegetated areas had more regular shapes and clear boundaries. Furthermore, connected domain analysis techniques and a distance transformation algorithm were used to size-filter the regularized regions, generating accurate connected domains that met the actual green space encroachment criteria. This approach effectively removed small areas of false positives while retaining larger areas that truly exhibited encroachment characteristics, further improving the reliability of the results. The accurate connected domain information that met the actual green space encroachment criteria was then comprehensively processed, and spatial statistical analysis methods were used to evaluate the spatial relationships between each connected domain, ultimately producing a comprehensive and detailed green space encroachment location map. This not only provides intuitive visualization results but also provides a scientific basis for subsequent spatial relationship research and decision support, helping to formulate more appropriate conservation measures. The entire process, from image preprocessing and identification of non-vegetated areas to shape regularization and size filtering, and finally to spatial relationship assessment, is highly automated. This reduces the need for manual intervention, improves work efficiency, and makes large-scale green space monitoring possible.

[0055] Furthermore, a deep learning target detection network suitable for urban green space scenes is used to preprocess each green space image in the multi-temporal image dataset, including resizing, color space conversion and normalization. These preprocessing steps ensure the consistency and high quality of the input image, laying a good foundation for subsequent recognition processing. At the same time, a small sample data set collected locally is obtained, and the pre-trained model is fine-tuned using a transfer learning algorithm so that the model can better adapt to the data distribution of the new task, thereby optimizing the model parameters and improving the adaptability of the model in specific scenarios. At the same time, this embodiment applies the target detection model optimized by transfer learning to perform pixel-level classification and bounding box prediction on the prepared green space images, uses non-maximum suppression technology to remove redundant detection frames, and retains the most likely candidate areas. This process not only improves the accuracy of identifying non-vegetation covered areas, but also ensures the precise positioning of the detection frame, reduces the possibility of false detection and missed detection, and generates images marked with non-vegetation covered areas, showing the location and range of suspected encroachment areas.

[0056] Finally, based on the above-mentioned images marked with non-vegetation covered areas, a preliminary green space encroachment location map is formed. This map not only intuitively shows the situation of green space encroachment, but also provides a reliable basis for subsequent shape regularization and size filtering processing. Analysis of the above technical solutions shows that the entire recognition method can complete the analysis of large-scale green space images in a relatively short period of time, greatly improving the efficiency of green space monitoring. At the same time, by introducing a local small sample data set for model fine-tuning and using regularization terms to prevent overfitting, it is ensured that the model has good robustness and stability when facing complex and changeable urban green space scenes. In particular, when processing different batches of data, different weights are given to different batches, which improves the overall performance of the model and ensures the stability and consistency of the recognition results. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A flowchart of a method for identifying urban green space encroachment and degradation based on computer vision recognition provided in an embodiment of the present application;

[0058] Figure 2 A schematic diagram of the structure of a system for identifying urban green space encroachment and degradation based on computer vision recognition provided in an embodiment of the present application;

[0059] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0061] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0062] Based on this, this application provides a method for identifying urban green space encroachment and degradation based on computer vision recognition, such as Figure 1 ,include:

[0063] Step 101: Periodically collect multi-temporal images of urban green spaces, sort the multi-temporal images according to timestamps, generate difference maps between the images of each temporal phase, and obtain dynamic information reflecting the temporal changes of urban green spaces based on the difference maps between the images of each temporal phase;

[0064] In this step, periodic data collection involves repeated observations of a specific area at fixed intervals, such as monthly, quarterly, or annually, to capture data on changes in that area over time. Multitemporal images are images of the same area acquired at different points in time. These images are sorted by timestamp to generate a difference map, which compares the differences between images at different times to reveal changes in land cover. This dynamic information can reveal trends in urban green space development over time.

[0065] In the embodiment of this application, suppose that a city's greening bureau wants to monitor changes in green spaces in downtown parks. They can use satellite remote sensing technology, such as Landsat series satellites or high-resolution commercial satellites, to collect images of the area every three months. Then, using specialized software tools such as ENVI and ERDAS, these images are preprocessed and analyzed to calculate the change in each pixel value over time, thereby generating a difference map. This will help identify changes in green space area, changes in vegetation health, and so on.

[0066] The present invention provides a quantitative method to observe and record the process of green space changes, laying the foundation for subsequent more in-depth analysis. It can help decision makers to understand the status of green space resources in a timely manner and take necessary protective measures.

[0067] Step 102: Based on historical geographic information system records and legally required land boundary information, vectorize the dynamic information reflecting the changes in the green space over time to establish a digital model as a reference for the green space boundary. The digital model is then overlaid and compared with the latest remote sensing imagery to obtain a corrected green space boundary.

[0068] In this step, the most recent remote sensing imagery refers to images acquired using modern remote sensing technology at the most recent point in time, providing the latest information on surface conditions. Vectorization refers to the process of converting raster map data into vector format to facilitate spatial analysis. The reference baseline for green space boundaries is a digital model created based on historical Geographic Information System (GIS) records and legally mandated land boundary information. The most recent remote sensing imagery refers to high-quality ground imagery obtained recently and is used to update existing green space boundary information.

[0069] In this application, continuing with the above example, the Greenery Bureau can construct a vector database containing all known green space boundaries based on GIS records from past years and official land boundary information provided by the city planning department. This database can then be overlaid with the latest high-resolution remote sensing imagery to check for discrepancies. If any, the boundaries in the vector model are adjusted to match the actual conditions.

[0070] The present invention can obtain more accurate green space boundary definitions, ensuring that the underlying data for subsequent analysis is up-to-date and reliable. This is crucial for detecting green space encroachment, as any inaccurate boundaries can lead to misjudgments.

[0071] Step 103: Based on the corrected green space boundaries, a deep learning object detection network is used to identify non-vegetation covered areas in the multi-temporal image to generate a preliminary green space encroachment location map. Morphological operations and connected domain analysis techniques are then used to perform shape regularization and size filtering on the preliminary green space encroachment location map to generate an optimized green space encroachment location map.

[0072] In this step, non-vegetation areas include artificial structures and hardened surfaces in green space images. A deep learning object detection network is an artificial intelligence algorithm that automatically identifies specific objects or patterns in images. Non-vegetation areas refer to portions of green space images that are not part of natural vegetation, such as buildings, roads, or other artificial structures. Morphological operations and connected domain analysis techniques are used to improve the quality of the initial detection results, eliminating noise points while retaining key features.

[0073] In an embodiment of the present application, the Greening Bureau can use a trained convolutional neural network (CNN network) to identify non-vegetation covered areas in multi-temporal images. First, a pre-trained model suitable for the urban environment is selected and fine-tuned using a local small sample data set. Afterwards, the optimized model is applied to classify the prepared green space images and mark the locations of all non-vegetation covered areas. Finally, morphological operations are used to remove isolated small patches, and the final green space encroachment location map is determined through connected domain analysis.

[0074] The embodiment of the present application improves the accuracy of identifying non-vegetation covered areas and reduces the false alarm rate, making the green space encroachment location map more reliable. At the same time, the automated process greatly improves work efficiency and reduces labor costs.

[0075] Step 104: Based on the optimized green space encroachment location map, using the spatiotemporal data analysis framework and combining it with environmental parameters, the temporal and spatial distribution characteristics of each factor are obtained, the temporal and spatial distribution characteristics of each factor are combined with the changing trend of the non-vegetation covered area to perform forecasting processing, and trend forecasting results are generated. The trend forecasting results are quantitatively evaluated and processed to generate a degradation severity report.

[0076] In this step, environmental parameters include climate data and the intensity of human activity. Factors refer to various variables or conditions that may influence green space encroachment and degradation. The spatiotemporal data analysis framework combines information from both time and space to analyze and predict trends in geographic phenomena. Environmental parameters encompass both natural and socioeconomic factors that influence green space health. Understanding these parameters and their interactions can better predict future problems and develop preventative strategies.

[0077] In an embodiment of the present application, the Greening Bureau can integrate data from multiple sources, such as climate data such as temperature and precipitation provided by weather stations, as well as data reflecting the intensity of human activities such as traffic flow and the number of building permits issued. Then, the spatiotemporal data analysis framework is used to explore the relationship between these factors and green space encroachment. Based on the results obtained, the Greening Bureau can predict future trends in green space encroachment, quantitatively assess the potential impact, and generate a degradation severity report. For example, if it is found that the intensity of human activities in a certain area is increasing year by year, while the area of ​​green space is decreasing during the same period, then it can be warned that the area may face more serious green space degradation problems.

[0078] The embodiments of this application can provide scientific foresight on the future development of green areas, providing strong support for policy making. In addition, quantitative assessment can help decision makers intuitively understand the severity of the problem and prioritize the areas most in need of intervention.

[0079] Through these four steps, the solution establishes a comprehensive urban green space monitoring and early warning system. It can track green space changes in real time, accurately identify encroachment, predict future development trends, and provide effective management strategies. This approach significantly improves the efficiency and scientific nature of urban green space protection, helping to maintain the city's ecological balance and residents' quality of life.

[0080] Optionally, in step 103, based on the corrected green space boundary, a deep learning target detection network is used to identify non-vegetation covered areas in the multi-temporal image to generate a preliminary green space encroachment location map, and morphological operations and connected domain analysis techniques are used to perform shape regularization and size filtering on the preliminary green space encroachment location map to generate an optimized green space encroachment location map, including: based on the corrected green space boundary, using a pre-trained deep learning target detection network, combined with a transfer learning algorithm to optimize model parameters, automatically identifying non-vegetation covered areas for each green space image in the multi-temporal image dataset The method adopts the method of the present invention to carry out shape regularization processing on the detected non-vegetation covered areas according to the preliminary green space encroachment location map, adopts the morphological operation technology and the watershed algorithm to carry out shape regularization processing on the detected non-vegetation covered areas according to the preliminary green space encroachment location map, and obtains the shape regularized areas, applies the connected domain analysis technology and the distance transformation algorithm to carry out size filtering processing on the shape regularized areas, and generates the accurate connected domain that meets the actual green space encroachment standard; comprehensively processes the information of the accurate connected domain that meets the actual green space encroachment standard, and uses the spatial statistical analysis method to evaluate the spatial relationship between each connected domain in the accurate connected domain, and outputs the final green space encroachment location map.

[0081] In this step, transfer learning is a machine learning method that applies knowledge gained in one domain or task to another related domain or task to accelerate model training and improve performance. In this scenario, transfer learning is used to optimize the model parameters of a deep learning object detection network to better adapt it to a multi-temporal image dataset of green spaces in a specific city. Morphological operations refer to a series of image processing operations, such as dilation and erosion, used to improve the quality of binary images. The watershed algorithm is a segmentation method that effectively separates adjacent but distinct regions and facilitates shape regularization. The distance transform algorithm calculates the distance from each pixel to the nearest background pixel. Combined with connected domain analysis techniques, it can help screen out accurate connected domains that meet the actual green space encroachment criteria, namely, those non-vegetated areas that meet preset conditions in size and shape. Spatial statistical analysis methods are used to evaluate the spatial distribution patterns between different connected domains, ensuring that the final output green space encroachment location map is both accurate and geographically meaningful.

[0082] In an embodiment of the present application, the optional solution first uses a deep learning target detection network that has been pre-trained and optimized through transfer learning to automatically identify each green space image within the corrected green space boundary, mark all non-vegetation covered areas, and thus generate a preliminary green space encroachment location map. Then, a combination of morphological operations and watershed algorithms is used to perform shape regularization on the preliminary identification results, so that the detected non-vegetation covered areas are more in line with the actual situation. Next, the connected domain analysis technology and the distance transformation algorithm are used to further size filter the shape-regularized areas, and only retain those connected domains that meet the actual green space encroachment standards. Finally, the information of these accurate connected domains is comprehensively processed, and spatial statistical analysis is used to evaluate the relationship between each connected domain to ensure that the final green space encroachment location map output not only accurately reflects the current situation, but also provides a reliable basis for subsequent spatial analysis.

[0083] In a large-scale urban greening management project, the environmental protection department decided to use this optimization solution to monitor changes in multiple parks and public green spaces within the city. They first collected high-resolution remote sensing imagery from the past few years and calibrated the green space boundaries based on the latest GIS data.

[0084] Next, the team selected a deep learning model that had performed well in similar environments and applied transfer learning technology to fine-tune it to more accurately identify local non-vegetation cover features. Subsequently, they used morphological operations and watershed algorithms to regularize the shape of the initially generated green space encroachment location map to ensure that each suspected encroachment point has a reasonable geometric shape. In order to eliminate small-area anomalies that are false positives, they also implemented connected domain analysis and distance transformation to retain only those areas that meet the actual green space encroachment standards. Finally, through spatial statistical analysis, the team was able to fully understand the spatial relationship between each connected domain and provide decision makers with a detailed report on the green space encroachment phenomenon, including the specific location, scale, and possible scope of impact. This method significantly improves work efficiency and also provides scientific support for the formulation of targeted protection measures.

[0085] In the task of identifying urban green space encroachment, a deep learning object detection network combined with a transfer learning algorithm to optimize model parameters automatically identifies non-vegetation-covered areas in each green space image in a multi-temporal image dataset. This process requires a mathematical formula to describe how to generate a preliminary green space encroachment map based on the corrected green space boundaries using a pre-trained and optimized object detection model. The design of this formula must consider the updating of model parameters, the calculation of the loss function, the consistency of feature distribution, and the final classification and prediction.

[0086] Optionally, based on the corrected green space boundary, a pre-trained deep learning target detection network is used, combined with a transfer learning algorithm to optimize model parameters, and each green space image in the multi-temporal image dataset is automatically identified for non-vegetation covered areas to obtain a preliminary green space encroachment location map, including: using a deep learning target detection network suitable for urban green space scenes to pre-process each green space image in the multi-temporal image dataset to generate prepared image data, wherein the pre-processing includes size adjustment, color space conversion and normalization; obtaining a small sample data set collected locally, using a transfer learning algorithm to fine-tune the pre-trained model, optimizing the last layer or layers of the pre-trained model, adapting the pre-trained model to the data distribution of the new task, optimizing the parameters of the pre-trained model, and obtaining a target detection model optimized by transfer learning;

[0087] The target detection model optimized by transfer learning is applied to perform pixel-level classification and bounding box prediction on the prepared green space image, and non-maximum suppression technology is used to remove redundant detection frames, retain the most likely candidate areas, and generate an image marked with non-vegetation covered areas; based on the image marked with non-vegetation covered areas, a preliminary green space encroachment location map is formed, and the image marked with non-vegetation covered areas shows the location and scope of the suspected encroachment area.

[0088] More specifically, the embodiment of the present application further provides a formula for the model parameters after transfer learning optimization, which is used to calculate the model parameters after transfer learning optimization. The specific calculation formula is as follows:

[0089]

[0090] Among them, P base Represents the basic parameters of the pre-training model; P opt represents the model parameters after transfer learning optimization; η represents the learning rate, which controls the speed of parameter update; N represents the number of different batches in the small sample data set S collected locally; α i Represents the importance weight of each batch; L(S,P) represents the loss function calculated on the small sample dataset S; represents the gradient of the loss function L(S,P) with respect to the parameter P; γ represents the update factor of the weight matrix W, which controls the adjustment speed of the feature map weight; S i represents the small sample data of the i-th batch; W represents the feature map weight matrix, which indicates the degree of attention paid by the model to different features; W(S i ) represents the small sample data S in batch i i The feature map weight matrix generated above; W base Represents the weight matrix of the basic feature map of the pre-training model; D KL(W(S i )||W base ) is the Kullback-Leibler divergence, which is used to measure the difference between the weight distribution of the feature map in the new task and the weight distribution of the feature map of the pre-trained model; β represents the regularization term coefficient, which is used to prevent overfitting; R(P base ) represents the regularization term to ensure the generalization ability of the model.

[0091] The overall formula aims to improve the adaptability and accuracy of pre-trained models in specific urban green space scenarios by introducing transfer learning and optimization techniques. The formula not only covers the update rules for model parameters but also considers the importance weights of different batches of data, learning rate decay, regularization terms, and adjustments to the feature map weight matrix. This ensures that the model can efficiently learn from local small sample datasets and maintain good generalization capabilities. Furthermore, the Kullback-Leibler divergence is introduced to measure the consistency of feature distributions between new and old tasks, helping the model smoothly transition to new tasks.

[0092] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0093]

[0094] After the model parameters P are optimized by transfer learning opt In the formula, P opt The optimized model parameters are designed to enable the model to show higher accuracy and adaptability in specific urban green space scenarios through transfer learning and local data fine-tuning.

[0095] P base It refers to introducing the basic parameters of the pre-trained model and using its sufficient training results on large-scale general datasets as the starting point for new tasks, reducing the time and resources required for training from scratch.

[0096] η refers to the introduction of a dynamically decaying learning rate to accelerate the convergence speed in the early training stage, and gradually reduce the learning rate in the later stage to prevent overfitting, ensuring that the model can fine-tune parameters and find the optimal solution.

[0097] N refers to the number of different batches, considering that the small sample dataset collected locally may contain multiple batches of data, so as to better manage the impact of each batch on the model update.

[0098] S i Refers to the small sample data S for each batch i , calculate the gradients separately to ensure that the model can make full use of limited local data for effective learning and improve the generalization ability of the model.

[0099] α iRefers to the introduction of importance weight α i , weighted according to the quality score of each batch of data, ensuring that high-quality data has a greater impact on the model, thereby improving the robustness and accuracy of the model.

[0100] Refers to calculating the loss function with respect to the parameter P base The gradient guides the update direction of the model parameters and ensures that each iteration moves in the direction of reducing the loss.

[0101] γ refers to the introduction of the feature map weight update factor γ, which controls the update speed of the feature map weight matrix, helps the model smoothly transition to new tasks, maintains the consistency of feature distribution, and prevents the model from deviating too much from the original knowledge.

[0102] D KL (W(S i )||W base ) refers to using the Kullback-Leibler divergence to measure the difference between the weight distribution of feature maps in the new task and the weight distribution of feature maps of the pre-trained model, ensuring that the model can flexibly adapt to the needs of new tasks while retaining useful features.

[0103] β refers to the introduction of the regularization term coefficient β, which is used to prevent the model from overfitting and ensure that the model has good generalization ability and can perform well on unseen data.

[0104] R(P base ) refers to adding regularization terms to constrain the complexity of model parameters, avoid overfitting caused by excessive model complexity, and improve the stability and reliability of the model.

[0105] The following is a brief introduction to how to obtain the parameters of this formula:

[0106] P base Download model weights trained on large datasets from public pre-trained model repositories. For example, use the official pre-trained models provided by PyTorch or TensorFlow.

[0107] η (Learning Rate): The initial learning rate can be set to 0.001 based on experience and is calculated exponentially based on the number of iterations. The learning rate can also be adjusted dynamically using a learning rate scheduler. For a specific task, the optimal learning rate range can be found through grid search or random search.

[0108] N (number of batches): This is determined by the size of the locally collected small sample dataset. Typically, small sample datasets are batched based on timestamps, geographic locations, or other characteristics, with each batch containing a certain number of images. Automatic batching can be achieved using dataset partitioning tools.

[0109] S i (Data for batch i): Regularly acquire high-resolution images of urban green spaces using field equipment, or download multi-temporal remote sensing images of the required area from a public geospatial data platform. Each batch of data should include annotation information for supervised learning.

[0110] α i (Importance weight): Based on the image quality score q i , calculated using metrics such as image clarity and annotation accuracy. Image quality can be assessed using an image quality assessment algorithm and combined with the accuracy of manual annotation to create a comprehensive score. These scores are then normalized into importance weights using the softmax function.

[0111] γ (feature map weight update factor): Initially set to a small value (such as 0.01) and based on the Kullback-Leibler divergence D KL (W(S i )||W base ) changes dynamically. Appropriate initial values ​​and adjustment strategies can be determined through experiments to ensure that the model can smoothly transition to new tasks.

[0112] D KL (W(S i )||W base ) (Kullback-Leibler divergence): obtained by calculating the difference between the weight distribution of the feature map in the new task and the weight distribution of the feature map of the pre-trained model. It can be directly calculated using built-in functions in deep learning frameworks.

[0113] β (regularization coefficient): The initial value is set to a small constant (such as 0.0005) and dynamically adjusted through methods such as cross-validation or Bayesian optimization. You can monitor changes in the mean and standard deviation of the training loss and fine-tune the regularization coefficient based on the model's performance to prevent overfitting.

[0114] R(P hase Regularization: Choose an appropriate regularization method based on the model architecture, such as L2 regularization or dropout. Consult the literature or best practice guides to select a regularization technique appropriate for the task at hand. For deep learning models, you can also use ensemble regularization methods such as weight decay and batch normalization.

[0115] In order to more accurately reflect the impact of different batches of data on model training, the system needs to quantify the quality of each batch of data. By introducing the importance weight α i , which ensures that high-quality data is given greater weight during training, thereby improving the robustness and accuracy of the model. Specifically, the batch importance weight αi The calculation formula is as follows:

[0116]

[0117] Among them, q i is the quality score of the small sample data of the i-th batch, which can be calculated based on indicators such as image clarity and annotation accuracy; λ is a tuning parameter that controls the degree of weight difference between different batches; N represents the number of different batches in the locally collected small sample dataset S;

[0118] In the batch importance weight α i The purpose of this formula is to introduce the softmax function to score the quality of each batch of data q i Normalization is performed to give higher weight to high-quality data and reduce the impact of low-quality data. Furthermore, the parameter λ is used to adjust the sensitivity of the weight calculation to suit the needs of different tasks. This approach not only ensures that the model learns more general and useful features from high-quality data, but also effectively prevents overfitting, improving the model's performance in specific application scenarios.

[0119] To ensure rapid convergence of the model in the early stages of training and to avoid oscillation and overfitting when approaching the optimal solution, the system needs to dynamically adjust the learning rate. By introducing a decay mechanism, the learning rate can be kept high in the early stages of training to accelerate convergence, and gradually reduced in the later stages of training to fine-tune the parameters. Specifically, the learning rate η is calculated as follows:

[0120]

[0121] Where η0 is the initial learning rate; t is the current iteration number; T is the total number of iterations; γ is the decay factor that controls how quickly the learning rate changes over time;

[0122] The formula for calculating the learning rate η is designed to accelerate convergence by providing a large learning rate at the beginning of training, then gradually reducing it as the number of iterations increases. This ensures that the model can fine-tune parameters in the later stages and steadily converge to the optimal solution. The decay factor controls the rate at which the learning rate decreases, allowing the model to maintain efficient training while avoiding instability or overfitting caused by excessively large learning rates, thereby improving the model's generalization and ultimate performance.

[0123] In order to ensure that the model can effectively prevent overfitting during training and dynamically adjust the strength of regularization according to data distribution, the system needs to adaptively adjust the regularization term coefficient. Specifically, the calculation formula of the regularization term coefficient β is as follows:

[0124] β=β0·(1+exp(-κ·(μ-σ))) -1

[0125] Where β0 is the initial regularization coefficient; μ is the mean of the training loss; σ is the standard deviation of the training loss; κ is the sensitivity parameter that controls how quickly the regularization coefficient changes with the loss distribution.

[0126] The formula for calculating the regularization term coefficient β is designed to dynamically adjust the regularization strength based on the statistical properties of the training loss (such as the mean and standard deviation), ensuring strong regularization in the early stages of training to prevent overfitting. As training progresses and model performance improves, the regularization coefficient is gradually reduced, allowing the model to better adapt to complex patterns in the data. This approach ensures that the model maintains good generalization capabilities throughout training and can flexibly respond to training requirements at different stages, thereby optimizing final performance and stability.

[0127] In order to ensure that the model can smoothly transition to new tasks during transfer learning and retain useful pre-trained features, the system needs to dynamically adjust the feature map weights based on the difference in feature distribution between the new and old tasks. Specifically, the calculation formula for the feature map weight update factor γ is as follows:

[0128]

[0129] Among them, γ0 is the initial feature map weight update factor; D KL (W(S i )||W base ) is the Kullback-Leibler divergence, which measures the difference between the weight distribution of the feature map in the new task and the weight distribution of the feature map of the pre-trained model; is the maximum possible Kullback-Leibler divergence value, used for normalization.

[0130] In the calculation formula of the feature map weight update factor γ, this formula is designed to optimize the model's performance in transfer learning and ensure that it can flexibly adapt to the needs of new tasks while retaining useful pre-trained features. The system introduces the feature map weight update factor γ, which dynamically adjusts the update speed of the feature map weight by measuring the Kullback-Leibler divergence difference between the feature distribution of the new task and the feature distribution of the pre-trained model, ensuring that the model can not only maintain the advantages of the original features, but also flexibly respond to the specific needs of new tasks, thereby improving overall performance and stability.

[0131] Assuming the current number of iterations t = 5000, calculate the learning rate η:

[0132]

[0133] Assume that the quality score q of a batch of data is i =0.8, calculate the importance weight α i :

[0134]

[0135] Here we assume that all batches of data have the same quality score.

[0136] Assume that the Kullback-Leibler divergence D of a batch KL (W(S i )||W base )=0.3, calculate the feature map weight update factor γ:

[0137]

[0138] Through the above formula and parameter settings, we have successfully optimized the YOLOv5 model, making it more suitable for urban green space scenarios. As the number of iterations increases, the learning rate gradually decreases, which helps the model adjust parameters more finely and avoid oscillation near the optimal solution. Importance weight α i Ensuring high-quality data has a greater impact on model training, improving its robustness and stability. The feature map weight update factor γ controls the update speed of the feature map weight matrix, enabling the model to flexibly adapt to new task requirements while retaining useful features. Ultimately, the optimized model can accurately identify non-vegetated areas within green spaces and generate a preliminary map of green space encroachment locations, providing a scientific basis for subsequent spatial analysis and decision support.

[0139] Optionally, applying the object detection model optimized by transfer learning to perform pixel-level classification and bounding box prediction on the prepared green space image, using non-maximum suppression technology to remove redundant detection boxes, retaining the most likely candidate areas, and generating an image marked with non-vegetation covered areas, including:

[0140] Using a target detection model optimized by transfer learning, the prepared green space image is classified at the pixel level to obtain a probability map of whether each pixel belongs to the background or non-vegetation covered area; based on the probability map of whether each pixel belongs to the background or non-vegetation covered area, the regression information output by the target detection model is used to obtain the detected non-vegetation covered area, and bounding box prediction is performed on the detected non-vegetation covered area to generate a series of candidate area bounding boxes containing position information and confidence scores, wherein the position information includes center coordinates, width, and height;

[0141] Based on the series of candidate region bounding boxes containing location information and confidence scores, a non-maximum suppression technique is applied, and the candidate region bounding boxes are sorted according to the confidence scores. The intersection-over-union ratios between adjacent bounding boxes of the candidate region bounding boxes are compared in sequence. For the bounding boxes whose intersection-over-union ratios are higher than a preset threshold, the one with the highest confidence is retained, and other redundant detection boxes are removed to obtain the retained bounding boxes; the retained bounding boxes are drawn onto the periodic multi-temporal image dataset to form an image marked with non-vegetation covered areas.

[0142] In this step, the concepts involved in this solution include deep learning object detection networks, transfer learning algorithms, preprocessing, non-maximum suppression techniques, pixel-level classification, and bounding box prediction. The deep learning object detection network is a neural network that can automatically identify specific objects in an image. It is used to identify non-vegetation covered areas in the multi-temporal green space image dataset in this case. Transfer learning algorithms allow the use of a model trained on one domain or task and adapt it to a new but related domain or task through fine-tuning. This refers to using a pre-trained model and optimizing it for a small sample dataset collected locally to better adapt to urban green space scenarios.

[0143] Preprocessing refers to a series of transformations performed on raw image data, such as resizing, color space conversion, and normalization, to ensure that the data input to the model meets the requirements and improve model performance. Non-maximum suppression technology is used to select the most likely box from a series of candidate detection boxes, removing redundant overlapping boxes by comparing the intersection-over-union ratio. Pixel-level classification is the process of determining the category of each pixel in the image, while bounding box prediction generates location information and confidence scores for detected objects.

[0144] In an embodiment of the present application, the solution first pre-processes each green space image in the multi-temporal image dataset, including resizing, color space conversion and normalization, to generate prepared image data suitable for model input. Then, based on a small sample dataset collected locally, a transfer learning algorithm is used to fine-tune the pre-trained target detection model, especially optimizing the last layer or layers to make the model parameters more in line with the data distribution of the new task. Next, the optimized target detection model is applied to perform pixel-level classification and bounding box prediction on the prepared image to obtain a probability map of each pixel belonging to the background or non-vegetation covered area, and based on this, a candidate area bounding box containing location information and a confidence score is generated. Finally, the non-maximum suppression technology is used to remove redundant detection frames and retain the most likely candidate areas to form images marked with non-vegetation covered areas. These images show the location and range of the suspected encroachment area, thereby constructing a preliminary green space encroachment location map.

[0145] In a smart city project, to monitor changes in urban park green spaces, the relevant departments decided to adopt the above-mentioned approach to analyze green space encroachment. The team first collected high-resolution satellite imagery taken in different seasons over the past few years as a multi-temporal image dataset and performed the necessary preprocessing. They selected a deep learning object detection model that performed well in similar environments and optimized it through transfer learning using a local small-sample dataset, specifically adjusting the model's final layer to accommodate local characteristics. The optimized model was applied to the processed images, performing pixel-level classification and bounding box prediction, generating a series of candidate boxes representing possible areas without vegetation cover.

[0146] Then, using non-maximum suppression techniques, the optimal bounding boxes were selected, resulting in images clearly marking areas without vegetation cover. These images not only revealed the specific location and extent of suspected green space encroachment but also helped the team accurately assess trends in green space changes, providing strong support for the development of subsequent conservation measures. Ultimately, this approach improved the efficiency and precision of green space management, helping to maintain the city's green ecological balance.

[0147] Optionally, in step 104, based on the optimized green space encroachment location map, a spatiotemporal data analysis framework is used in combination with environmental parameters to obtain the temporal and spatial distribution characteristics of each factor, the temporal and spatial distribution characteristics of each factor are combined with the change trend of the non-vegetation covered area to perform prediction processing to generate a trend prediction result, the trend prediction result is quantitatively evaluated and processed to generate a degradation severity report, including: using the optimized green space encroachment location map data, integrating the information of the non-vegetation covered area to obtain a data set suitable for the spatiotemporal data analysis framework; collecting and preprocessing the environmental parameters according to the data set suitable for the spatiotemporal data analysis framework to generate a data set suitable for the non-vegetation covered area. Multidimensional spatiotemporal data related to changes in covered areas; based on the multidimensional spatiotemporal data related to changes in non-vegetation covered areas, the temporal and spatial distribution characteristics of each factor in the environmental parameters are analyzed and modeled to obtain a relationship model between different environmental parameters and changes in non-vegetation covered areas; using the relationship model between different environmental parameters and changes in non-vegetation covered areas, the trend of changes in the non-vegetation covered areas is predicted and processed to generate trend prediction results for a period of time in the future; based on the trend prediction results for a period of time in the future, the expansion speed, impact range and degree of ecological impact of the non-vegetation covered areas are quantitatively evaluated to generate a degradation severity report. Optionally, using the relationship model between different environmental parameters and changes in non-vegetation covered areas to predict the trend of changes in the non-vegetation covered areas and generate trend prediction results for a period of time in the future includes:

[0148] Utilizing the relationship model between the different environmental parameters and the changes in non-vegetation covered areas, a suitable machine learning or statistical model is selected to train the change data of the non-vegetation covered areas and construct a prediction model that captures temporal and spatial variation patterns; based on the requirements of the prediction model that captures temporal and spatial variation patterns, the pre-processed multidimensional spatiotemporal data is integrated, and the non-vegetation covered area change data including historical periods and the latest observations is used as input to generate an input data set suitable for prediction;

[0149] Based on the input data set suitable for prediction, different future scenario assumptions are set to simulate the changing trends of different non-vegetation covered areas that may occur in the future, and generate multiple prediction scenarios covering best-case scenarios, most likely scenarios, and worst-case scenarios. The different future scenario assumptions include different paths of climate change and changes in the intensity of human activities;

[0150] By using the multiple prediction scenarios covering the best case, the most likely case and the worst case, the short-term and long-term change trends of the non-vegetation covered area are predicted and processed to generate trend prediction results at a series of future time points.

[0151] In this step, the concepts covered in this solution include a spatiotemporal data analysis framework, environmental parameters, multidimensional spatiotemporal data, relational models, predictive models, and scenario hypotheses. The spatiotemporal data analysis framework is an analytical method that integrates time series and spatial distribution information to study the patterns of change in geographical phenomena over time and location. Environmental parameters refer to various external factors that influence changes in green space, such as climate conditions and the intensity of human activity. Multidimensional spatiotemporal data combines changes in non-vegetated areas with environmental parameters to form a multi-dimensional dataset that comprehensively reflects the changing process. Relational models are correlation models established through statistical or machine learning methods between different environmental parameters and changes in non-vegetated areas, revealing the causal relationship between the two. Predictive models are mathematical models trained using historical data that capture patterns of temporal and spatial change and are used to predict future trends. Scenarios simulate different possible future development scenarios, such as different paths of climate change and changes in the intensity of human activity, to simulate multiple possible outcomes and provide a basis for decision-making.

[0152] In an embodiment of the present application, the solution first integrates and processes the non-vegetation covered area information in the optimized green space encroachment location map to generate a dataset suitable for the spatiotemporal data analysis framework. Then, relevant environmental parameters are collected and preprocessed to construct multidimensional spatiotemporal data related to changes in non-vegetation covered areas. Next, based on this multidimensional spatiotemporal data, the temporal and spatial distribution characteristics of each environmental parameter are analyzed and modeled to obtain a relationship model between different environmental parameters and changes in non-vegetation covered areas. Using these relationship models, appropriate machine learning or statistical models are selected to train the change data of non-vegetation covered areas and construct a prediction model that captures the temporal and spatial patterns of change. Based on the requirements of the prediction model, the preprocessed multidimensional spatiotemporal data is integrated to generate an input dataset suitable for prediction. Different future scenario assumptions are then set to simulate different possible change trends. Finally, by predicting short-term and long-term change trends under multiple prediction scenarios covering best-case, most likely, and worst-case scenarios, a series of trend prediction results at future time points are generated. The rate of expansion of non-vegetation covered areas, the scope of impact, and the degree of ecological impact are quantitatively assessed, ultimately generating a degradation severity report.

[0153] In an urban planning project, the environmental protection department decided to use this approach to assess future trends and potential impacts of urban green space. They first integrated maps of green space encroachment locations optimized over the past few years and extracted information on areas without vegetation cover, creating a comprehensive spatiotemporal dataset. The team then collected and preprocessed local climate and human activity data to generate multidimensional spatiotemporal data related to changes in areas without vegetation cover.

[0154] Based on this data, the team then established models linking various environmental parameters with changes in non-vegetated areas, revealing the impacts of climate change and human activities on green space changes. Using these models, the team selected random forest regression as a predictive model and trained it on the non-vegetated area change data.

[0155] To generate accurate forecasts, the team integrated preprocessed historical and recently observed data on changes in non-vegetated areas and formulated three future scenarios: best-case, most likely, and worst-case. Based on these scenarios, the team simulated different possible trends over the next 10 years and generated a series of detailed forecasts. Finally, the team quantified the rate of expansion, scope, and ecological impact of non-vegetated areas, compiling a detailed report on the severity of degradation to provide scientific decision-making support to the municipal government. This approach not only improves forecast accuracy but also provides a strong basis for developing sound urban planning and environmental protection strategies.

[0156] Optionally, in step 102, the dynamic information reflecting the changes of the green space over time is vectorized based on historical geographic information system records and legally required land boundary information to establish a digital model as a reference for the green space boundary, and the digital model is superimposed and compared with the latest remote sensing image to obtain a corrected green space boundary, including:

[0157] Using historical geographic information system records and legally required land boundary information, vectorize the dynamic information reflecting the changes in green space over time to obtain vector data that accurately represents the changes in green space and the legal boundaries of green space changes; based on the vector data that accurately represents the changes in green space and the legal boundaries of green space changes, establish a digital model and use it as a reference for the green space boundary, convert it into a digital format, and generate a high-precision digital model of the green space changes and boundary locations;

[0158] Modern remote sensing technology is used to obtain the latest remote sensing images with high resolution, high precision and high timeliness. The coordinate system of the digital model is made consistent with that of the latest remote sensing image through image registration technology, and superposition and comparison processing is performed to obtain the detection results of green space boundary changes. Based on the detection results of green space boundary changes, combined with field surveys or other auxiliary data sources, the dynamic information reflecting the changes of green spaces over time is adjusted and corrected to generate a corrected green space boundary.

[0159] This step involves concepts such as vectorization, digital models, legal boundaries for green space changes, remote sensing imagery, and image registration technology. Vectorization involves converting dynamic information reflecting green space changes over time, such as historical geographic information system records and legally mandated land use boundaries, into a vector data format composed of geometric elements such as points, lines, and surfaces, enabling accurate computer analysis and management. Digital models are digitally constructed as a reference for green space changes and boundaries. They accurately represent the location, shape, and size of green spaces and can be integrated and analyzed with other geographic information data. Legal boundaries for green space changes refer to the boundaries of green space use established by laws and regulations, ensuring their protected status in urban planning. Remote sensing imagery refers to surface information acquired by sensors on platforms such as satellites or aircraft. It offers high resolution, high accuracy, and high timeliness, providing the latest surface coverage for green space monitoring. Image registration technology aligns the coordinate systems of images from different sources to facilitate direct comparison and analysis.

[0160] In the embodiment of the present application, the solution first uses the land boundary information recorded in the historical geographic information system and stipulated by law to vectorize the dynamic information reflecting the changes of green space over time, and generate vector data that accurately represents the changes of green space and its legal boundaries. Then, based on these vector data, a digital model is established as a reference benchmark for the green space boundary, which is converted into a digital format to generate a high-precision digital model of the green space change and boundary position. Next, the latest remote sensing image is obtained through modern remote sensing technology, and the image registration technology is used to keep the coordinate system of the digital model consistent with that of the remote sensing image, and an overlay comparison is performed to detect the changes in the green space boundary. Finally, based on the detection results of the green space boundary changes, combined with field surveys or other auxiliary data sources, such as on-site photos or local regulations updates, the dynamic information reflecting the changes of green space over time is adjusted and corrected, thereby generating a more accurate corrected green space boundary, providing a scientific basis for green space management and protection.

[0161] In a city's green space conservation project, the relevant departments adopted the aforementioned approach to more accurately understand green space changes and develop effective conservation strategies. They first collected historical GIS records from the past few decades, as well as legally mandated land boundary information. This information included the original distribution of green spaces, historical changes, and relevant legal documents. This data was then vectorized to create a vector dataset that accurately represented the green space's evolution and its legal boundaries. The team then developed a digital model, converting this information into a digital format to construct a highly accurate digital model of the green space's evolution and boundary locations. The team then used modern remote sensing technology to obtain the latest high-resolution remote sensing imagery. Using image registration techniques, they ensured the coordinate systems of the digital model and remote sensing imagery matched, overlaying and comparing them to identify changes in the green space's boundaries. Based on these detected changes, the team conducted field visits to verify the remote sensing imagery analysis results. They also incorporated additional data sources, such as feedback from local residents and reports on recent urban construction activities, to adjust and correct the green space evolution information as necessary. Ultimately, the team generated a corrected green space boundary report, which not only improved the accuracy of green space boundaries but also provided an important reference for future green space protection work, contributing to the effective management and sustainable development of urban green spaces.

[0162] Example 2

[0163] Figure 2 The present invention provides a schematic diagram of a system for identifying urban green space encroachment and degradation based on computer vision recognition. Figure 2 As shown, the system includes:

[0164] The acquisition module 21 (i.e., the drone imaging detection platform) is used to periodically collect multi-temporal images of urban green spaces, sort the multi-temporal images by timestamp, generate difference maps between the images of each temporal phase, and obtain dynamic information reflecting the changes of urban green spaces over time based on the difference maps between the images of each temporal phase;

[0165] The processing module 22 (i.e., a high-performance server) is configured to vectorize the dynamic information reflecting the changes in the green space over time based on historical geographic information system records and legally required land boundary information, thereby establishing a digital model as a reference for the green space boundary. The digital model is then overlaid and compared with the latest remote sensing imagery to obtain a corrected green space boundary. The latest remote sensing imagery refers to an image acquired at a recent point in time using modern remote sensing technology to provide the latest surface condition information.

[0166] an identification module 23 for identifying non-vegetation covered areas in the multi-temporal image based on the corrected green space boundaries using a deep learning object detection network to generate a preliminary green space encroachment location map, and performing shape regularization and size filtering on the preliminary green space encroachment location map using morphological operations and connected domain analysis techniques to generate an optimized green space encroachment location map, wherein the non-vegetation covered areas include artificial structures and hardened ground in the green space image;

[0167] A generation module 24 is used to obtain the temporal and spatial distribution characteristics of each factor based on the optimized green space encroachment location map, using a spatiotemporal data analysis framework and combining environmental parameters, and to predict the temporal and spatial distribution characteristics of each factor in combination with the changing trend of the non-vegetation covered area to generate a trend prediction result, and to quantitatively evaluate the trend prediction result to generate a degradation severity report. The environmental parameters include climate data and human activity intensity, and the factors refer to various variables or conditions that may affect green space encroachment and degradation.

[0168] The acquisition module is a drone imaging detection platform: the drone imaging detection platform is used to periodically acquire multi-temporal images of urban green spaces. These platforms can be equipped with high-resolution cameras, multispectral or thermal imaging sensors and other equipment. The processing module preferably uses a high-performance server; it is used to store large amounts of historical geographic information system (GIS) data and land boundary information, as well as to perform complex vectorization processing and model building tasks. The server needs to have sufficient CPU / GPU computing power to support large-scale data processing and machine learning algorithm training. The above-mentioned high-performance server will also implement the functions of the above-mentioned recognition module 23 and generation module 24;

[0169] Figure 2 The urban green space encroachment and degradation identification system based on computer vision recognition can be implemented Figure 1The implementation principles and technical effects of the computer vision-based urban green space encroachment and degradation identification method described in the illustrated embodiment are not further elaborated. The specific manner in which each module and unit performs operations in the computer vision-based urban green space encroachment and degradation identification system described in the aforementioned embodiment has been described in detail in the related method embodiments and will not be further elaborated here.

[0170] In one possible design, Figure 2 The urban green space encroachment and degradation identification system based on computer vision recognition in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0171] In one possible design, the present invention provides a computer storage medium storing a computer program. When the computer program is executed by a computer, a method for identifying encroachment and degradation of urban green space based on computer vision recognition is implemented.

[0172] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A system for identifying urban green space encroachment and degradation based on computer vision recognition, characterized in that: include: An acquisition module is configured to periodically acquire multi-temporal images of urban green spaces, sort the multi-temporal images according to timestamps, generate difference maps between the images of each temporal phase, and obtain dynamic information reflecting temporal changes of urban green spaces based on the difference maps between the images of each temporal phase; a processing module for vectorizing the dynamic information reflecting the changes in the green space over time based on historical geographic information system records and legally required land boundary information to establish a digital model as a reference for the green space boundary, and for overlaying and comparing the digital model with the latest remote sensing imagery to obtain a corrected green space boundary. The latest remote sensing imagery refers to an image acquired at a recent point in time using modern remote sensing technology to provide the latest surface condition information. an identification module for identifying non-vegetation covered areas in the multi-temporal image based on the corrected green space boundaries using a deep learning target detection network to generate a preliminary green space encroachment location map, and performing shape regularization and size filtering on the preliminary green space encroachment location map using morphological operations and connected domain analysis techniques to generate an optimized green space encroachment location map, wherein the non-vegetation covered areas include artificial structures and hardened ground in the green space image; A generation module is used to obtain the temporal and spatial distribution characteristics of various factors based on the optimized green space encroachment location map, using a spatiotemporal data analysis framework and combining environmental parameters, predict the temporal and spatial distribution characteristics of various factors in combination with the changing trend of the non-vegetation covered area, generate trend prediction results, perform quantitative evaluation processing on the trend prediction results, and generate a degradation severity report, wherein the environmental parameters include climate data and human activity intensity, and the various factors refer to various variables or conditions that may affect green space encroachment and degradation.

2. A method for identifying urban green space encroachment and degradation based on computer vision recognition, characterized in that: include: Periodically collecting multi-temporal images of urban green spaces, sorting the multi-temporal images according to timestamps, generating difference maps between the images of each temporal phase, and obtaining dynamic information reflecting temporal changes of urban green spaces based on the difference maps between the images of each temporal phase; Based on historical geographic information system records and legally required land boundary information, vectorize the dynamic information reflecting the changes in the green space over time to establish a digital model as a reference for the green space boundary. Superimpose and compare the digital model with the latest remote sensing imagery to obtain a corrected green space boundary. The latest remote sensing imagery refers to an image acquired at a recent point in time using modern remote sensing technology to provide the most up-to-date information on the surface conditions. Based on the corrected green space boundaries, a deep learning object detection network is used to identify non-vegetation covered areas in the multi-temporal image to generate a preliminary green space encroachment location map. Morphological operations and connected domain analysis techniques are used to perform shape regularization and size filtering on the preliminary green space encroachment location map to generate an optimized green space encroachment location map, wherein the non-vegetation covered areas include artificial structures and hardened ground in the green space image. Based on the optimized green space encroachment location map, the spatiotemporal data analysis framework is used in combination with environmental parameters to obtain the temporal and spatial distribution characteristics of each factor. The temporal and spatial distribution characteristics of each factor are combined with the changing trend of the non-vegetation covered area to perform forecast processing to generate trend forecast results. The trend forecast results are quantitatively evaluated to generate a degradation severity report. The environmental parameters include climate data and human activity intensity. The factors refer to various variables or conditions that may affect green space encroachment and degradation.

3. The method according to claim 2, characterized in that Based on the corrected green space boundary, a deep learning target detection network is used to identify non-vegetation covered areas in the multi-temporal image to generate a preliminary green space encroachment location map, and morphological operations and connected domain analysis techniques are used to perform shape regularization and size filtering on the preliminary green space encroachment location map to generate an optimized green space encroachment location map, including: Based on the corrected green space boundaries, a pre-trained deep learning object detection network is used in combination with a transfer learning algorithm to optimize model parameters. Each green space image in the multi-temporal image dataset is automatically identified for non-vegetation covered areas to obtain a preliminary green space encroachment location map. Based on the preliminary green space encroachment location map, morphological operation technology is used in combination with the watershed algorithm to perform shape regularization processing on the detected non-vegetation covered areas to obtain shape-regularized regions. Connected domain analysis technology is used in combination with the distance transformation algorithm to perform size filtering processing on the shape-regularized regions to generate accurate connected domains that meet the actual green space encroachment standards. The information of the accurate connected domain that meets the actual green space encroachment standard is comprehensively processed, and the spatial relationship between each connected domain in the accurate connected domain is evaluated using a spatial statistical analysis method to output a final green space encroachment location map.

4. The method according to claim 3, characterized in that Based on the corrected green space boundaries, a pre-trained deep learning target detection network is used in combination with a transfer learning algorithm to optimize model parameters. Each green space image in the multi-temporal image dataset is automatically identified for non-vegetation covered areas to obtain a preliminary green space encroachment location map, including: Using a deep learning object detection network suitable for urban green space scenes, preprocessing each green space image in the multi-temporal image dataset to generate prepared image data, wherein the preprocessing includes resizing, color space conversion, and normalization; Obtain a small sample data set collected locally, use a transfer learning algorithm to fine-tune the pre-trained model, optimize the last layer or layers of the pre-trained model, adapt the pre-trained model to the data distribution of the new task, optimize the parameters of the pre-trained model, and obtain an object detection model optimized by transfer learning; Applying the object detection model optimized by transfer learning to perform pixel-level classification and bounding box prediction on the prepared green space image, using non-maximum suppression technology to remove redundant detection boxes, retaining the most likely candidate areas, and generating an image marked with non-vegetation covered areas; Based on the image marked with the non-vegetation covered area, a preliminary green space encroachment location map is formed, and the image marked with the non-vegetation covered area shows the location and scope of the suspected encroachment area.

5. The method according to claim 4, characterized in that The object detection model optimized by the transfer learning is applied to perform pixel-level classification and bounding box prediction on the prepared green space image, and non-maximum suppression technology is used to remove redundant detection boxes, retain the most likely candidate areas, and generate an image marked with non-vegetation covered areas, including: Using the object detection model optimized by transfer learning, the prepared green space image is classified at the pixel level to obtain a probability map of each pixel belonging to the background or non-vegetation covered area; Based on the probability map of each pixel belonging to the background or non-vegetation covered area, the regression information output by the target detection model is used to obtain the detected non-vegetation covered area, and a bounding box prediction is performed on the detected non-vegetation covered area to generate a series of candidate area bounding boxes including position information and confidence scores, wherein the position information includes center coordinates, width, and height; Based on the series of candidate region bounding boxes containing position information and confidence scores, applying non-maximum suppression technology, sorting by confidence score, sequentially comparing the intersection-over-union ratios between adjacent bounding boxes of the candidate region bounding boxes, and retaining the bounding boxes with the highest confidence score for those whose intersection-over-union ratios are higher than a preset threshold, and removing other redundant detection boxes to obtain the retained bounding boxes; The retained bounding box is drawn onto the periodic multi-temporal image dataset to form an image with non-vegetation covered areas marked.

6. The method according to claim 5, characterized in that Based on the optimized green space encroachment location map, the temporal and spatial distribution characteristics of each factor are obtained by utilizing a spatiotemporal data analysis framework in combination with environmental parameters. The temporal and spatial distribution characteristics of each factor are combined with the change trend of the non-vegetation covered area to perform forecast processing to generate trend forecast results. The trend forecast results are quantitatively evaluated to generate a degradation severity report, including: Using the optimized green space encroachment location map data, the information of the non-vegetation covered area is integrated and processed to obtain a data set suitable for a spatiotemporal data analysis framework; Collecting and preprocessing environmental parameters based on the datasets suitable for the spatiotemporal data analysis framework to generate multidimensional spatiotemporal data related to changes in non-vegetated areas; Based on the multidimensional spatiotemporal data related to the changes in non-vegetation covered areas, the temporal and spatial distribution characteristics of each factor in the environmental parameters are analyzed and modeled to obtain a relationship model between different environmental parameters and the changes in non-vegetation covered areas; Using the relationship model between the different environmental parameters and the changes in the non-vegetation covered area, the change trend of the non-vegetation covered area is predicted and processed to generate trend prediction results for a period of time in the future; Based on the trend prediction results for the future period, a quantitative assessment is conducted on the expansion speed and impact range of the non-vegetation covered area and the degree of ecological impact of the non-vegetation covered area to generate a degradation severity report.

7. The method according to claim 6, characterized in that The method of using the relationship model between the different environmental parameters and the non-vegetation covered area changes to predict the change trend of the non-vegetation covered area and generate trend prediction results for a period of time in the future includes: Using the relationship model between the different environmental parameters and the changes in non-vegetation covered areas, selecting an appropriate machine learning or statistical model, training the change data of the non-vegetation covered areas, and constructing a prediction model that captures the temporal and spatial variation patterns; According to the requirements of the prediction model that captures temporal and spatial variation patterns, the pre-processed multi-dimensional spatiotemporal data are integrated, and the non-vegetation covered area change data including historical periods and the latest observations are used as input to generate an input dataset suitable for prediction; Based on the input data set suitable for prediction, different future scenario assumptions are set to simulate the changing trends of different non-vegetation covered areas that may occur in the future, and generate multiple prediction scenarios covering best-case scenarios, most likely scenarios, and worst-case scenarios. The different future scenario assumptions include different paths of climate change and changes in the intensity of human activities; By using the multiple prediction scenarios covering the best case, the most likely case and the worst case, the short-term and long-term change trends of the non-vegetation covered area are predicted and processed to generate trend prediction results at a series of future time points.

8. The method according to claim 2, characterized in that The dynamic information reflecting the changes of green space over time is vectorized based on the land use boundary information recorded in the historical geographic information system and stipulated by law to establish a digital model as a reference for the green space boundary. The digital model is superimposed and compared with the latest remote sensing imagery to obtain a corrected green space boundary, including: Using historical geographic information system records and legally required land use boundary information, vectorize the dynamic information reflecting the changes of green space over time to obtain vector data that accurately represents the changes of green space and the legal boundaries of green space changes; Based on the vector data accurately representing the green space changes and the legal boundaries of the green space changes, a digital model is established and used as a reference for the green space boundaries, converted into a digital format, and a high-precision digital model of the green space changes and boundary locations is generated; Acquire the latest remote sensing images with high resolution, high precision and high timeliness, use image registration technology to make the coordinate system of the digital model consistent with that of the latest remote sensing images, and perform superposition and comparison processing to obtain the detection results of green space boundary changes; Based on the detection results of the green space boundary changes, combined with field investigations or other auxiliary data sources, the dynamic information reflecting the changes of the green space over time is adjusted and corrected to generate a corrected green space boundary.

9. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for identifying encroachment and degradation of urban green space based on computer vision recognition as described in any one of claims 2 to 8.

10. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, the method for identifying encroachment and degradation of urban green space based on computer vision recognition as described in any one of claims 2 to 8 is implemented.

Images