Method and apparatus for tracking plastic waste using data management

Abstract

The invention relates to the technical field of waste tracking, in particular to a plastic waste tracking method and equipment utilizing data management. The method comprises the following steps: acquiring real-time positioning data of the plastic wastes; performing dynamic positioning tracking on the real-time positioning data of the plastic wastes, performing full-process trajectory evolution, and constructing a waste full-process tracking trajectory map; acquiring an omnibearing monitoring image of a plastic waste initial treatment station; waste visual inspection is carried out on the omnibearing monitoring image, waste multi-angle morphological structure analysis is carried out, and a three-dimensional structure model of each waste is constructed; acquiring an omnibearing monitoring image of the next transfer processing station based on the waste whole-process tracking trajectory map; and performing one-by-one form comparison on the omnibearing monitoring image based on the three-dimensional structure model of each waste so as to generate a transfer station waste form comparison result. According to the invention, efficient and accurate plastic waste tracking is realized.

Description

Technical Field

[0001] The present invention relates to the field of waste tracking technology, and in particular to a plastic waste tracking method and device using data management. Background Art

[0002] With the rapid growth of global plastic consumption, the amount of plastic waste generated has continued to rise, and has become one of the main problems of global environmental pollution and resource waste. The management and recycling of plastic waste has become a focus of increasing attention for companies. Traditional plastic waste treatment methods mainly rely on manual classification, manual statistics and traditional recycling methods. However, when faced with massive amounts of plastic waste, these methods often have many problems such as low efficiency, poor accuracy, and low resource recycling rate. With the rapid development of information technology, especially big data, the Internet of Things and artificial intelligence technology, the full-process dynamic tracking method of plastic waste driven by big data has gradually become an effective way to solve this problem.

[0003] The full process management of plastic waste includes not only the collection, transportation, classification, and recycling of waste, but also involves waste source tracing, treatment process supervision, and resource reuse. The existing management system generally has bottlenecks such as waste information islands, imperfect tracking methods, and untimely data analysis, which makes it impossible to achieve refined and dynamic management of the waste treatment process. Therefore, a more intelligent and accurate waste tracking method is needed, which is of great significance for promoting green development and realizing an environmentally friendly society. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, the present invention proposes a plastic waste tracking method and device using data management to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above objectives, the present invention provides a plastic waste tracking method using data management, comprising the following steps: Step S1: obtaining real-time positioning data of plastic waste; dynamically locating and tracking the real-time positioning data of plastic waste, and performing full-process trajectory evolution to construct a full-process tracking trajectory map of waste; Step S2: Obtaining a comprehensive monitoring image of the initial plastic waste processing station; performing visual inspection of the waste on the comprehensive monitoring image, and performing multi-angle morphological structure analysis of the waste to construct a three-dimensional structural model of each waste; Step S3: obtaining a full-range monitoring image of the next transfer and processing station based on the waste full-process tracking trajectory map; performing a morphological comparison of the full-range monitoring image one by one based on the three-dimensional structural model of each waste, thereby generating a waste morphological comparison result of the transfer station; Step S4: Perform abnormal waste analysis based on the waste morphology comparison results of the transfer station to generate correct tracking trajectory and transfer data of abnormal plastic waste; Step S5: based on the data of transporting abnormal plastic waste, the abnormal transport trajectory is traced on the waste full process tracking trajectory map, and secondary monitoring of abnormal waste is performed to generate a secondary monitoring trajectory of abnormal waste; Step S6: Based on the correct tracking trajectory and the secondary monitoring trajectory of abnormal waste, the real-time trajectory rendering parameters are optimized, and dynamic three-dimensional visualization processing is performed to construct a dynamic three-dimensional visualization tracking trajectory model.

[0006] The present invention can help the system to accurately understand the location and movement of waste by acquiring the positioning data of waste in real time. Dynamic positioning tracking and full-process trajectory evolution can help to build a full-process tracking trajectory map of waste, thereby improving the real-time and accuracy of waste management. Visual detection and structural analysis of waste can help the system to accurately detect and identify waste and improve processing efficiency. Building a three-dimensional structural model of waste can help to deeply understand the morphological characteristics of waste and provide a basis for subsequent comparison and analysis. One-by-one morphological comparison of all-round monitoring images can help to confirm the state of waste during transportation and improve the accuracy of tracking. Generating morphological comparison results of waste at the transfer station can help the system to detect abnormal waste and conduct subsequent analysis and processing. Regular waste analysis can promptly detect abnormal situations in treatment stations, help improve the efficiency and quality of waste treatment, and generate correct tracking trajectories and transfer data for abnormal plastic waste, which helps to establish a complete waste tracking system. The traceability and secondary monitoring of abnormal waste help to gain an in-depth understanding of abnormal situations and take appropriate treatment measures. By generating secondary monitoring trajectories for abnormal waste, the system can track the treatment process of abnormal waste and ensure that waste treatment complies with regulations. Real-time trajectory rendering parameter optimization and dynamic 3D visualization processing can make tracking trajectories more vivid and intuitive, improve data display effects, and build dynamic 3D visualization tracking trajectory models to help users more intuitively understand the tracking of waste and improve system visualization and user experience.

[0007] Preferably, step S1 comprises the following steps: Step S11: implanting RFID tags into plastic waste to obtain real-time location data of the plastic waste; Step S12: Dynamically locate and track the real-time location data of plastic waste to generate a dynamic tracking trajectory for each waste; Step S13: performing waste transfer flow analysis on the dynamic tracking trajectory of each waste, thereby generating a dynamic transfer path for each waste; Step S14: Identify the transfer stagnation points of each dynamic transfer path of waste and mark the transfer processing station nodes; Step S15: performing a transfer node spatial distribution analysis on the transfer processing station nodes, thereby generating transfer node spatial distribution data; Step S16: Based on the spatial distribution data of the transfer nodes, the dynamic tracking trajectory of each waste is evolved throughout the entire process, and a waste full-process tracking trajectory map is constructed.

[0008] The present invention can establish a unique identity for each waste through the implantation of RFID tags, realize individual tracking, and obtain positioning data in real time. Through RFID technology, an efficient means is provided to realize the real-time positioning of waste, laying the foundation for subsequent tracking. Dynamic positioning and tracking helps the system to monitor the location and movement of waste in real time, improve the accuracy of waste management, and generate dynamic tracking trajectories for each waste to help track the movement path of the waste and provide data support for subsequent analysis. Transfer flow analysis can help the system understand the flow direction and path of waste during the transfer process and optimize the transfer strategy. Generating a dynamic transfer path for waste helps to identify the transportation situation of waste, provide a basis for subsequent node analysis, and identify transfer stagnation points and markers. Recording the processing station nodes helps to discover bottlenecks and problem points in the transfer process and improve transportation efficiency. Marking nodes can provide key information for subsequent spatial distribution analysis and optimize the waste transfer route planning. The spatial distribution analysis of transfer nodes helps the system to deeply understand the spatial layout and correlation of transfer sites and optimize the transfer network design. Generating spatial distribution data can provide spatial reference for the evolution of the whole process trajectory and help build a complete waste tracking map. The evolution of the whole process trajectory based on the spatial distribution data of transfer nodes can realize the full display of waste tracking, improve the comprehensiveness and accuracy of tracking, and build a full-process waste tracking trajectory map. It can provide system users with intuitive waste tracking information and promote the transparency and precision of waste management.

[0009] Preferably, step S2 comprises the following steps: Step S21: Obtaining a comprehensive monitoring image of the initial plastic waste processing station; Step S22: Performing visual inspection of waste on the omni-directional monitoring image and marking all plastic waste nodes; Step S23: performing semantic segmentation of waste bounding boxes one by one based on all plastic waste nodes, and extracting a full-range bounding box image of each waste; Step S24: performing a multi-angle morphological structure analysis on the omnidirectional boundary frame image of each waste, thereby generating morphological structure data of each waste; Step S25: Perform three-dimensional point cloud modeling on the morphological structure data of each waste to construct a three-dimensional structural model of each waste. The present invention provides an overall perspective of the waste treatment station through all-round monitoring images, providing a comprehensive data basis for subsequent analysis. Real-time monitoring images can help the system observe the treatment of waste in real time, improve the real-time and accuracy of waste management, waste visual detection and node marking can automatically identify and locate waste, reduce manual intervention, and improve processing efficiency. Marking waste nodes is helpful for subsequent individual tracking and analysis of waste, and provides data support for morphological structure analysis. Waste bounding box semantic segmentation can accurately extract the bounding box image of each waste, providing an accurate data basis for subsequent morphological structure analysis. The bounding box images of each waste are helpful for the identification and analysis of individual waste, and improve the accuracy of tracking. Multi-angle morphological structure analysis of waste can deeply understand the appearance characteristics and structure of each waste, provide detailed information for subsequent modeling, and generate morphological structure data to help distinguish the differences between different wastes, providing a basis for subsequent three-dimensional modeling. Three-dimensional point cloud modeling realizes spatial modeling of waste by establishing a three-dimensional structure model of each waste, improves the accuracy of tracking, and constructs a three-dimensional structure model to more intuitively display the morphology and characteristics of waste, providing more three-dimensional data support for full-process tracking.

[0010] Preferably, the specific steps of step S24 are: Perform pixel-level edge contour recognition on each waste object in its full-range boundary frame image, and extract pixel-level edge contour lines of each waste object; Marking a plurality of edge feature points based on each waste pixel-level edge contour line; Calculate the positioning coordinates of multiple edge feature points; Performing three-dimensional geometric dimension calculation based on the positioning coordinates to obtain the three-dimensional geometric dimension characteristics of each waste; Performing visual recognition of the surface texture of each waste on the omnidirectional bounding box image to generate surface texture feature data of each waste; The surface texture feature data of each waste and the three-dimensional geometric size characteristics of each waste are subjected to multi-angle morphological structure analysis to generate the morphological structure data of each waste.

[0011] The present invention can accurately extract the edge features of each waste through pixel-level edge contour recognition, providing a basis for subsequent feature extraction and analysis. The extraction of edge contour lines helps to accurately locate the shape boundary of the waste, providing accurate data support for subsequent feature point marking and three-dimensional geometric dimension calculation. Marking multiple edge feature points can better describe the shape features of the waste, providing detailed data support for subsequent three-dimensional geometric dimension calculation and surface texture recognition. The marking of edge feature points helps to extract the key features of the waste, laying a foundation for subsequent morphological structure analysis. By calculating the positioning coordinates of the edge feature points, the shape and structure of the waste can be accurately described, providing an accurate data basis for subsequent three-dimensional geometric dimension calculation. The calculation of the positioning coordinates helps to quantify the morphological features of the waste, providing detailed data support for morphological structure analysis. Calculation of three-dimensional dimensions can accurately obtain the three-dimensional characteristics of each waste, including length, width, height and other information, providing a basis for subsequent analysis and modeling. The calculation of three-dimensional geometric dimensions helps to gain a deep understanding of the spatial characteristics of the waste, and provides data support for morphological structure analysis and surface texture recognition. Surface texture visual recognition can help identify the surface characteristics of the waste, including texture, smoothness, etc., and provide data support for subsequent feature analysis and recognition. Generating surface texture feature data helps to distinguish the differences between different wastes and provide more detailed information for morphological structure analysis and recognition. Through multi-angle morphological structure analysis, the three-dimensional geometric dimension characteristics and surface texture characteristics of the waste can be comprehensively considered, and the overall characteristics of the waste can be deeply understood. The generation of morphological structure data helps to comprehensively describe the morphological characteristics of the waste and provide more detailed data support for real-time and accurate tracking.

[0012] Preferably, step S3 specifically comprises the following steps: Step S31: Identify the next transfer and processing station node based on the waste full-process tracking trajectory map, and obtain a full-range monitoring image of the next transfer and processing station; Step S32: performing waste identification on the all-round monitoring image of the next transfer and processing station, and extracting all plastic waste data; Step S33: Sequentially encode and mark all plastic waste data to obtain plastic waste coding data; Step S34: performing waste form analysis based on the plastic waste coding data, and extracting each coded waste form data; Step S35: performing a morphological comparison on each coded waste morphological data one by one based on the three-dimensional structural model of each waste, thereby generating a waste morphological comparison result of the transfer station.

[0013] The present invention can realize the continuity of waste tracking by identifying the next transfer and processing station node, ensure the integrity of waste process tracking, obtain all-round monitoring images to help monitor the location and status of waste in the processing station in real time, and provide a basis for subsequent data extraction and analysis. Waste identification can accurately extract plastic waste in the monitoring image, provide accurate objects for subsequent data processing and analysis, extract all plastic waste data to help fully understand the distribution of waste in the processing station, and provide data support for subsequent coding and morphological analysis. Sequential coding and marking waste data can ensure the orderliness and uniqueness of data, and facilitate subsequent data management and comparative analysis. Morphological analysis based on coded data helps to systematically describe the structural characteristics of waste and provide an accurate data basis for morphological comparison. Waste morphological analysis can deeply understand the appearance characteristics and morphological structure of waste, and provide detailed data support for subsequent comparison and identification. Extracting the morphological data of each coded waste helps to establish a waste feature database, and provides a basis for morphological comparison and result generation. Morphological comparison one by one can analyze whether the waste is normally transferred to the next transfer station, generate morphological comparison results, and analyze whether each waste has completed the correct transfer, so as to prevent the waste from being lost midway and causing unnecessary environmental hazards.

[0014] Preferably, the specific steps of step S4 are: Step S41: When the waste form comparison result of the transfer station is successful, the dynamic tracking trajectory of the next transfer and processing station is determined as the correct tracking trajectory; Step S42: When the waste form comparison result of the transfer station is a comparison failure, an abnormal transfer warning process is performed to generate an abnormal transfer processing station warning signal; Step S43: performing abnormal waste analysis on the plastic waste coding data based on the abnormal warning signal of the transfer and processing station to generate transfer abnormal plastic waste data; The present invention ensures the consistency and accuracy of waste tracking by confirming that the dynamic tracking trajectory of the next transfer and processing station is the correct tracking trajectory when the waste form comparison is successful. The determination of the correct tracking trajectory helps to reduce misjudgment and erroneous tracking, and improves the reliability and accuracy of the waste tracking system. When the waste form comparison fails, the transfer abnormality early warning processing is timely performed, and an abnormal early warning signal is generated to timely investigate and handle abnormal situations. The transfer abnormality early warning processing helps to timely discover and solve problems in the waste tracking system, ensure the normal operation of the waste treatment process and the reliability of data. Abnormal waste analysis of plastic waste coded data based on abnormal early warning signals helps to identify and analyze the characteristics and causes of abnormal waste. The generation of transfer abnormal plastic waste data can help improve the waste treatment process, optimize the waste tracking system, and improve the efficiency and accuracy of abnormal situation handling.

[0015] Preferably, the specific steps of step S5 are: Step S51: marking abnormal transfer points on the waste full-process tracking trajectory map based on the abnormal transfer plastic waste data, thereby extracting abnormal transfer processing station nodes; Step S52: Tracing the historical transfer trajectory of the abnormal transfer processing station node, thereby extracting the abnormal node traceability trajectory; Step S53: Identify the transit change trajectory points of the abnormal node traceability trajectory and extract multiple transit change trajectory points; Step S54: extracting the transit timestamps of multiple transit change trajectory points; Step S55: analyzing the abnormal waste transfer flow direction according to the transfer timestamp to generate abnormal waste transfer flow direction data; Step S56: Perform secondary monitoring of abnormal waste on the abnormal waste transfer flow data to generate a secondary monitoring trajectory of abnormal waste.

[0016] The present invention can quickly identify abnormal nodes in the transfer process by marking abnormal transfer points, which is helpful to locate and handle problems in the waste tracking system. Extracting abnormal transfer processing station nodes is helpful to establish an abnormal node library, providing data support for subsequent abnormal processing and improvement. Through the tracing of historical transfer trajectories, we can deeply understand the formation causes and transfer paths of abnormal nodes, providing historical data support for abnormal processing. Extracting abnormal node tracing trajectories is helpful to establish a detailed historical record of the evolution of abnormal nodes, providing a basis for problem analysis and solution. Identifying transfer change trajectory points can accurately capture the transfer changes at abnormal nodes, providing key data points for further analysis of abnormal trajectories. Extracting multiple transfer change trajectory points is helpful to reveal the transfer change trends and patterns at abnormal nodes, providing a more comprehensive perspective for problem analysis. Taking the transfer timestamp can record the time information of abnormal waste at each transfer change point, help analyze the time series characteristics of the abnormal transfer process, and obtain the transfer timestamp to help establish the abnormal waste transfer timeline, providing data support for subsequent time-related analysis. Analyzing the transfer flow of abnormal waste can reveal the path and flow of abnormal waste in the transfer process, which helps to identify problem points and improvement directions. Generating abnormal waste transfer flow data helps to establish an abnormal waste transfer route map, providing data support for abnormal tracking and processing. Through the generation of secondary monitoring trajectories for abnormal waste, abnormal waste can be monitored and tracked again to ensure further processing and management of abnormal waste. Generating secondary monitoring trajectories for abnormal waste helps to monitor the treatment process of abnormal waste and improve the transparency and efficiency of waste treatment.

[0017] Preferably, the specific steps of step S6 are: Step S61: predicting the arrival time of each transfer processing station for the correct tracking trajectory, and obtaining the predicted arrival time of multiple processing stations; Step S62: optimizing the real-time trajectory rendering parameters of the waste full-process tracking trajectory map based on the predicted arrival time of multiple processing stations and the secondary monitoring trajectory of abnormal wastes, and constructing a rendering optimized tracking trajectory map; Step S63: Perform dynamic three-dimensional visualization processing on the rendering optimized tracking trajectory map, so as to construct a dynamic three-dimensional visualization tracking trajectory model. The present invention helps to optimize the timeline of full-process waste tracking by predicting the arrival time of the treatment station, making preparations in advance, and ensuring the efficiency and timeliness of the waste transfer process. The predicted arrival times of multiple treatment stations can provide time parameter support for subsequent trajectory optimization and rendering, and realize the spatiotemporal integration of the tracking trajectory. Based on the predicted arrival time of the treatment station and the secondary monitoring trajectory of abnormal waste, the rendering parameters of the tracking trajectory map are optimized to accurately display the real-time location and status of the waste, improve the tracking accuracy, and construct a rendering optimized tracking trajectory map to help enhance the user's visualization experience of the waste tracking system, making the tracking process more intuitive and easy to understand. Dynamic three-dimensional visualization processing can present the tracking trajectory map as a vivid three-dimensional model, enhance the user's understanding and perception of the waste tracking process, and construct a dynamic three-dimensional visualization tracking trajectory model to help achieve a three-dimensional display of waste tracking, and provide a more intuitive and accurate waste tracking display effect. In this specification, a plastic waste tracking device using data management is provided, which is used to perform the plastic waste tracking method using data management as described above, including: Dynamic positioning and tracking module, used to obtain real-time positioning data of plastic waste; dynamically locate and track the real-time positioning data of plastic waste, and perform full-process trajectory evolution to build a full-process tracking trajectory map of waste; A three-dimensional structure module is used to obtain a full-range monitoring image of the initial plastic waste processing station; perform visual inspection of the waste on the full-range monitoring image, and perform multi-angle morphological structure analysis of the waste to construct a three-dimensional structure model of each waste; The morphology comparison module is used to obtain the omnidirectional monitoring image of the next transfer and treatment station based on the waste full-process tracking trajectory map; perform morphology comparison on the omnidirectional monitoring image one by one based on the three-dimensional structure model of each waste, so as to generate the morphology comparison result of the waste at the transfer station; The abnormal transfer module is used to analyze abnormal waste based on the waste morphology comparison results of the transfer station, generate correct tracking trajectories and transfer abnormal plastic waste data; The abnormal trajectory tracing module is used to trace the abnormal transportation trajectory of the waste full process tracking trajectory map based on the abnormal plastic waste transportation data, and conduct secondary monitoring of abnormal waste to generate abnormal waste secondary monitoring trajectory; The three-dimensional visualization module is used to optimize the real-time trajectory rendering parameters based on the correct tracking trajectory and the secondary monitoring trajectory of abnormal waste, and perform dynamic three-dimensional visualization processing to build a dynamic three-dimensional visualization tracking trajectory model.

[0018] The present invention helps to track the real-time position of the logistics process by acquiring the positioning data of plastic waste in real time, thereby improving the efficiency of supervision and management. The dynamic positioning tracking and full-process trajectory evolution construct a waste full-process tracking map, which provides an overall perspective for the system and helps users to fully understand the flow direction and status of the waste. It obtains all-round monitoring images of the initial processing station and conducts visual detection and multi-angle morphological structure analysis of the waste, which helps to establish a three-dimensional structural model of each waste and provide more comprehensive waste information. Through the construction of the three-dimensional structure model, the morphology of the waste can be more accurately described and presented, providing a basis for subsequent morphological comparison. By using the full-process tracking trajectory map and the three-dimensional structure model, morphological comparison can be performed, which can accurately identify the state changes of the waste at different transfer stations, help monitor and control the flow direction of the waste, and generate the transfer station waste morphological comparison results to help discover abnormal situations, handle them in time and conduct subsequent tracking to ensure the waste treatment process. Accuracy. Through abnormal waste analysis, abnormal situations can be discovered and handled in a timely manner to ensure the smooth progress of the waste treatment process and improve the accuracy and timeliness of tracking. Generating correct tracking trajectories and abnormal plastic waste transfer data helps to provide detailed data support and provide a basis for subsequent abnormal trajectory tracing. Through abnormal transfer trajectory tracing and abnormal waste secondary monitoring, abnormal waste conditions can be tracked and treatment measures can be adjusted in a timely manner to ensure the standardization and safety of the waste treatment process. Generating abnormal waste secondary monitoring trajectories helps to fully understand the causes and processes of abnormal situations and provide a reference for system improvement. Through real-time trajectory rendering parameter optimization and dynamic 3D visualization processing, a dynamic 3D visualization tracking trajectory model is constructed, which can vividly display the waste treatment process and improve the user's visualization experience and understanding. The realization of dynamic 3D visualization helps to present the details and changes of the waste transportation process and provide users with intuitive and comprehensive waste tracking information. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic flow chart of the steps of a method for tracking plastic waste using data management according to the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0021] The present application example provides a method and device for tracking plastic waste using data management. The execution subjects of the method and device for tracking plastic waste using data management include but are not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0022] See also Figures 1 to 4 The present invention provides a plastic waste tracking method using data management, the plastic waste tracking method using data management comprising the following steps: Step S1: obtaining real-time positioning data of plastic waste; dynamically locating and tracking the real-time positioning data of plastic waste, and performing full-process trajectory evolution to construct a full-process tracking trajectory map of waste; Step S2: Obtaining a comprehensive monitoring image of the initial plastic waste processing station; performing visual inspection of the waste on the comprehensive monitoring image, and performing multi-angle morphological structure analysis of the waste to construct a three-dimensional structural model of each waste; Step S3: obtaining a full-range monitoring image of the next transfer and processing station based on the waste full-process tracking trajectory map; performing a morphological comparison of the full-range monitoring image one by one based on the three-dimensional structural model of each waste, thereby generating a waste morphological comparison result of the transfer station; Step S4: Perform abnormal waste analysis based on the waste morphology comparison results of the transfer station to generate correct tracking trajectory and transfer data of abnormal plastic waste; Step S5: based on the data of transporting abnormal plastic waste, the abnormal transport trajectory is traced on the waste full process tracking trajectory map, and secondary monitoring of abnormal waste is performed to generate a secondary monitoring trajectory of abnormal waste; Step S6: Based on the correct tracking trajectory and the secondary monitoring trajectory of abnormal waste, the real-time trajectory rendering parameters are optimized, and dynamic three-dimensional visualization processing is performed to construct a dynamic three-dimensional visualization tracking trajectory model.

[0023] The present invention can help the system to accurately understand the location and movement of waste by acquiring the positioning data of waste in real time. Dynamic positioning tracking and full-process trajectory evolution can help to build a full-process tracking trajectory map of waste, thereby improving the real-time and accuracy of waste management. Visual detection and structural analysis of waste can help the system to accurately detect and identify waste and improve processing efficiency. Building a three-dimensional structural model of waste can help to deeply understand the morphological characteristics of waste and provide a basis for subsequent comparison and analysis. One-by-one morphological comparison of all-round monitoring images can help to confirm the state of waste during transportation and improve the accuracy of tracking. Generating morphological comparison results of waste at the transfer station can help the system to detect abnormal waste and conduct subsequent analysis and processing. Regular waste analysis can promptly detect abnormal situations in treatment stations, help improve the efficiency and quality of waste treatment, and generate correct tracking trajectories and transfer data for abnormal plastic waste, which helps to establish a complete waste tracking system. The traceability and secondary monitoring of abnormal waste help to gain an in-depth understanding of abnormal situations and take appropriate treatment measures. By generating secondary monitoring trajectories for abnormal waste, the system can track the treatment process of abnormal waste and ensure that waste treatment complies with regulations. Real-time trajectory rendering parameter optimization and dynamic 3D visualization processing can make tracking trajectories more vivid and intuitive, improve data display effects, and build dynamic 3D visualization tracking trajectory models to help users more intuitively understand the tracking of waste and improve system visualization and user experience.

[0024] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a plastic waste tracking method using data management of the present invention. In this example, the steps of the plastic waste tracking method using data management include: Step S1: obtaining real-time positioning data of plastic waste; dynamically locating and tracking the real-time positioning data of plastic waste, and performing full-process trajectory evolution to construct a full-process tracking trajectory map of waste; In this embodiment, GPS positioning devices or RFID tags are installed in the generation, collection and treatment of plastic waste. These devices can record the location data of the waste in real time. IoT (Internet of Things) devices can be used to obtain real-time data through sensors. The positioning device sends the collected location data to the central server through a wireless network (such as 4G / 5G, LoRa, Wi-Fi, etc.) to ensure the security and stability of data transmission. Encryption technology is used to protect data. A database (such as MySQL, MongoDB) is set on the central server to store real-time positioning data. The database should be able to support high-concurrency access to cope with the real-time update requirements of a large amount of data. A real-time monitoring system is developed, and data visualization tools (such as Grafana, Tableau) are used to display the real-time location of the waste. The system should have a real-time update function that can display the current location and status of the waste. Each location update is recorded as a trajectory to form a time series data set. Data processing tools (such as Apache Develop analytical algorithms, process positioning data, identify waste movement patterns and trends, apply machine learning models, predict waste flows, optimize collection and processing processes, integrate trajectory data from all links to form a complete waste flow chain, including data from the generation, collection, transportation, and processing stages, use ETL (extraction, transformation, loading) tools to integrate data, develop visualization tools to display trajectory evolution throughout the entire process, use GIS (geographic information system) software to draw trajectory maps, design user-friendly interfaces that allow users to select different time periods and areas for queries, generate reports regularly, analyze waste flows, processing efficiency, and environmental impacts, use data analysis tools (such as Python's Pandas and Matplotlib) to generate charts and visualization reports, use map APIs (such as Google Maps API and OpenStreetMap) to overlay trajectory data on maps, and ensure that maps have responsive designs and are compatible with a variety of devices (PCs and mobile phones).

[0025] Step S2: Obtaining a comprehensive monitoring image of the initial plastic waste processing station; performing visual inspection of the waste on the comprehensive monitoring image, and performing multi-angle morphological structure analysis of the waste to construct a three-dimensional structural model of each waste; In this embodiment, high-resolution cameras are installed at key locations of the processing station (such as the feed port, storage area, and around the processing equipment). Cameras with night vision and wide viewing angles are selected to ensure that images can be effectively captured under various lighting conditions. The cameras are configured to take timed photos or record in real time to ensure that different viewing angles of the plastic waste are fully covered. Video streaming technology is used to transmit image data in real time to a central server for processing. A dedicated storage space is set up on the central server. A high-capacity storage solution (such as NAS or cloud storage) is used to save monitoring images. Data is backed up regularly to ensure data security and integrity. The acquired images are pre-processed, including denoising, contrast enhancement, and brightness adjustment, to improve the accuracy of subsequent analysis. An image processing library (such as OpenCV) is used to standardize the images. A deep learning model (such as YOLO, Faster R-CNN) is applied to detect plastic waste in the images. Annotated data sets are used when training the models to improve the accuracy of waste detection. The detected waste is classified to identify different types of plastics (such as PET, HDPE, PVC etc.), use machine learning algorithms (such as support vector machines and decision trees) to further classify and process the waste, use multiple cameras or rotating platforms to obtain images of the same waste at different angles to form complete morphological data, ensure that the images at each angle have sufficient overlap for subsequent 3D reconstruction, use image processing technology to extract the edge, contour and shape features of the waste, apply feature extraction algorithms (such as Canny edge detection) to obtain clear morphological features, use structured light, stereo vision or multi-view geometry and other technologies to convert multi-angle images into 3D models, use 3D reconstruction software (such as Meshroom and COLMAP) to process image data, generate high-precision 3D structural models, optimize the generated 3D models, repair defects (such as holes and noise), use 3D modeling software (such as Blender and Maya) for detail adjustment and texture mapping, store the final 3D model in a database for subsequent query and use, design a user interface to allow operators to easily access and manage the 3D model, use the 3D model for further analysis, such as morphological research, material recovery efficiency evaluation, etc., combine data analysis tools to generate reports to help optimize the waste treatment process.

[0026] Step S3: obtaining a full-range monitoring image of the next transfer and processing station based on the waste full-process tracking trajectory map; performing a morphological comparison of the full-range monitoring image one by one based on the three-dimensional structural model of each waste, thereby generating a waste morphological comparison result of the transfer station; In this embodiment, multiple high-resolution surveillance cameras are installed at key locations of the transfer and processing station (such as the container area and the loading and unloading area) to ensure all-round monitoring of the waste. The camera should have a 360-degree rotation capability to obtain real-time images from different angles. The camera is configured to take pictures at regular intervals or record in real time, and transmit the surveillance images to the central processing server in real time to ensure the stability and security of data transmission. An encrypted channel is used to prevent data leakage. A dedicated database (such as SQL, NoSQL) is established to store the surveillance images of the transfer station. A data management strategy is implemented, and expired data is regularly backed up and cleared to maintain data availability. A three-dimensional structural model of each waste obtained from the previous step is obtained to ensure the integrity and accuracy of the model. The three-dimensional model is saved in a suitable file format (such as STL, OBJ) for subsequent processing. The obtained all-round surveillance images of the transfer station are pre-processed, including noise removal, contrast enhancement, etc., to improve the accuracy of subsequent comparisons. An image processing library (such as OpenCV) is used for standardization processing, and an object detection algorithm (such as YOLO, Faster) is applied. R-CNN) is used to identify and extract waste in monitoring images, obtain the bounding box information of each waste in the monitoring image for subsequent analysis, and compare the morphology of the extracted waste in the monitoring image with the corresponding 3D model. A shape matching algorithm (such as ICP (Iterative Closest Point)) is used to calculate the similarity between the waste in the monitoring image and the 3D model. A morphological comparison report is generated based on the comparison results, including similarity scores, comparison success rates and other information. For the identified waste, the corresponding relationship between the mark and the 3D model is provided to provide visual feedback on the morphological changes.

[0027] Step S4: Perform abnormal waste analysis based on the waste morphology comparison results of the transfer station to generate correct tracking trajectory and transfer data of abnormal plastic waste; In this embodiment, the previously generated morphological comparison results are collected, including the morphological characteristics of each waste, the comparison similarity and the marked abnormal information, and the monitoring images, three-dimensional models and comparison results are integrated to build a unified data set. The appropriate anomaly detection algorithm is selected to identify wastes with significantly different characteristics from normal wastes. Commonly used algorithms include: statistical analysis method: by analyzing the distribution of waste characteristics, samples beyond the normal range are identified; machine learning method: such as isolation forest (Isolation Forest) Forest) or support vector machine (SVM) is used to train the model to identify anomalies, extract key features such as shape, size, color and material type from the comparison results, standardize the features to ensure that different features have the same importance, analyze the extracted feature data using the selected anomaly detection algorithm, identify abnormal wastes, record detailed information for each identified abnormal waste, including its monitoring image at the transfer station, comparison results and related features, integrate the identified abnormal waste with its monitoring data at the transfer station, including tracking the abnormal waste, record its movement path and timestamp at the transfer station, analyze the movement trajectory of the abnormal waste, identify processing process problems or bottlenecks, and use trajectory analysis tools (such as ArcGIS, QG IS) visualizes the movement path of waste, writes analysis reports, summarizes the characteristics, tracking trajectories and existing problems of abnormal waste, and the reports should include data visualization charts to show the specific situation and analysis results of abnormal waste. Establish a database specifically for storing detailed data of abnormal waste, including its characteristics, comparison results and tracking trajectories, ensure that the data structure can support efficient query and analysis, design a user interface to facilitate operators to query and manage abnormal waste data, provide search and filtering functions, allowing users to find abnormal data according to specific conditions (such as time, type, status), and formulate subsequent monitoring measures based on the results of abnormal waste analysis, optimize the waste treatment process of the transfer station, continuously monitor the waste flow of the transfer station, and ensure that abnormal situations are discovered and handled in a timely manner.

[0028] Step S5: based on the data of transporting abnormal plastic waste, the abnormal transport trajectory is traced on the waste full process tracking trajectory map, and secondary monitoring of abnormal waste is performed to generate a secondary monitoring trajectory of abnormal waste; In this embodiment, the transfer trajectory of abnormal plastic waste is marked on the full-process tracking trajectory map, and the abnormal data is superimposed on the trajectory map using GIS tools (such as ArcGIS, QGIS), and the algorithm (such as DBSCAN) is used to identify the abnormal data. Clustering) identifies patterns of abnormal transfer trajectories, such as abnormal stops, deviations from routes, etc., analyzes the temporal and spatial characteristics of abnormal trajectories, determines the starting and ending points of abnormal transfers, identifies the causes of interruptions or delays in the transfer process, such as equipment failures, operational errors, etc., formulates a secondary monitoring plan for abnormal waste based on abnormal transfer trajectories and related data, determines the time, frequency and key monitoring areas for monitoring, ensures the effectiveness and pertinence of monitoring, deploys additional monitoring equipment (such as cameras, sensors) at key nodes of abnormal waste transfer (such as container areas, loading and unloading areas), ensures that the equipment can capture the dynamic changes of abnormal waste in real time, such as volume, weight, shape, etc., conducts secondary monitoring, and records the state changes of abnormal waste in real time, uses data processing tools (such as Python, R) to clean and analyze the collected data, extracts key features, integrates the secondary monitoring data with the original transfer trajectory, generates a complete secondary monitoring trajectory for abnormal waste, uses time series analysis methods to mark the timestamp of each monitoring point, forms a dynamic trajectory, and uses data visualization tools (such as Tableau, Power BI) Display the secondary monitoring trajectory of abnormal waste on the map to facilitate analysis and decision-making, generate charts and reports, display monitoring results, highlight abnormal situations and key data, write detailed monitoring reports, summarize the monitoring process, results and problems found of abnormal waste, and promote the optimization of waste treatment processes. Based on the results of secondary monitoring, establish a continuous monitoring mechanism for abnormal waste, regularly evaluate and update monitoring strategies, combine real-time data, dynamically adjust monitoring frequency and area, ensure timely response to abnormal situations, use the collected secondary monitoring data for in-depth analysis, identify potential abnormal patterns and trends, and combine machine learning technology to continuously optimize the anomaly detection algorithm to improve the accuracy of subsequent monitoring.

[0029] Step S6: Based on the correct tracking trajectory and the secondary monitoring trajectory of abnormal waste, the real-time trajectory rendering parameters are optimized, and dynamic three-dimensional visualization processing is performed to construct a dynamic three-dimensional visualization tracking trajectory model.

[0030] In this embodiment, data of the correct tracking trajectory and the secondary monitoring trajectory of abnormal wastes, including information such as location, timestamp, speed, etc., are collected and integrated into a unified data format (such as JSON, CSV) to ensure the readability and compatibility of the data. The integrated trajectory data is analyzed to identify key points and turning points to determine the dynamic change characteristics of the trajectory, calculate the smoothness and continuity of the trajectory, and identify the existing abnormal fluctuations. According to the trajectory analysis results, the rendering parameters are adjusted, such as the thickness, transparency, color and animation speed of the line, etc., and the parameters are adjusted using a graphics rendering library (such as Three.js, D3.js) to enhance the visualization effect of the trajectory. A basic three-dimensional scene model is constructed using three-dimensional modeling software (such as Blender, Maya) or a three-dimensional visualization library (such as Three.js), and backgrounds, light sources and other environments are added to the scene. Elements are used to improve the visual effect. The optimized trajectory data is imported into the 3D visualization environment. Appropriate rendering techniques (such as wireframe rendering and point cloud rendering) are used to display the trajectory. Real-time dynamic rendering is achieved. The trajectory position is dynamically updated according to the timestamp to present the movement process of the waste. Dynamic effects such as flow effects, color gradients or particle effects are added to the trajectory to enhance the visual expression. Animation libraries (such as GSAP and Anime.js) are used to achieve smooth animation transitions and transformation effects. User interaction functions such as zooming, rotating, and panning are added to the visualization interface to allow users to freely explore the 3D model and realize data interaction functions. Users can click on the trajectory or waste to view detailed information (such as type, time, status, etc.). The data update mechanism is set to ensure that the visualization model can reflect the latest tracking trajectory and monitoring data in real time. WebSocket is used Or other real-time communication technologies to maintain the timeliness and accuracy of data, generate dynamic 3D visualization tracking trajectory models, and display them on the user interface for relevant personnel to monitor and analyze. It provides export functions, allowing users to save visualization results as videos or static images to facilitate subsequent reporting and sharing. It also performs performance evaluation on dynamic 3D visualization models, checks rendering speed, fluency, and system resource usage, and further optimizes rendering algorithms and data processing processes based on the evaluation results to ensure visualization efficiency and fluency.

[0031] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: implanting RFID tags into plastic waste to obtain real-time location data of the plastic waste; Step S12: Dynamically locate and track the real-time location data of plastic waste to generate a dynamic tracking trajectory for each waste; Step S13: performing waste transfer flow analysis on the dynamic tracking trajectory of each waste, thereby generating a dynamic transfer path for each waste; Step S14: Identify the transfer stagnation points of each dynamic transfer path of waste and mark the transfer processing station nodes; Step S15: performing a transfer node spatial distribution analysis on the transfer processing station nodes, thereby generating transfer node spatial distribution data; Step S16: Based on the spatial distribution data of the transfer nodes, the dynamic tracking trajectory of each waste is evolved throughout the entire process, and a waste full-process tracking trajectory map is constructed.

[0032] In this embodiment, RFID tags suitable for plastic waste are selected, and environmental factors such as temperature resistance and corrosion resistance are considered. Necessary equipment, including RFID readers and tag programmers, are prepared. RFID tags are implanted on each plastic waste. The tags should contain a unique identification code (ID) and related information (such as type, weight, etc.), ensuring that the tags are safely and reliably affixed or fixed to the waste to prevent loss or damage. The ID and related data of each tag are entered into a central database using an RFID programmer, and an association between waste and RFID tags is established. RFID readers are deployed in key areas of waste storage and transportation (such as warehouses, transfer stations, and transport vehicles), and the system is configured to collect signals emitted by RFID tags in real time, record their locations and timestamps, collect data from RFID readers in real time, and update the location information of each waste in the database. Dynamic positioning data of each waste is generated through software processing, including position changes and time series. The dynamic positioning data of each waste is integrated to form a complete trajectory record, including each location and its time information. The trajectory data is analyzed using data analysis tools (such as Python and R). Identify the transfer direction of each waste, determine the waste transfer path (such as from the storage location to the transfer station) based on the location change and time interval, generate dynamic transfer path data for each waste, record the nodes and time information passed in the path, analyze the transfer path data, identify the time points when the waste stagnates at certain locations, set stagnation thresholds (such as staying at the same location for more than a certain time) to determine the stagnation points, mark the identified stagnation points as transfer and processing station nodes, and record their location information, update the transfer path of each waste in the database, add stagnation point information, collect the location information of all transfer and processing station nodes, including their latitude and longitude and other relevant data (such as processing capacity, processing type, etc.), use geographic information system (GIS) tools (such as ArcGIS, QGIS) to perform spatial distribution analysis on transfer station nodes, generate a spatial distribution map of transfer nodes, display the distribution density and relative position relationship of different nodes, record the analysis results, generate transfer node spatial distribution data for subsequent use, integrate the dynamic tracking trajectory data of each waste and the location information of the transfer node, and use data visualization tools (such as Tableau, Power BI) visualizes the integrated data and generates a full-process tracking trajectory map, showing the starting point, transfer path, stagnation point and end point of each waste, providing a clear tracking view, ensuring that the trajectory map is updated in real time to reflect the latest tracking data and transfer path, and publishing the generated tracking trajectory map to the management platform for relevant personnel to view and analyze in real time.

[0033] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: Obtaining a comprehensive monitoring image of the initial plastic waste processing station; Step S22: Performing visual inspection of waste on the omni-directional monitoring image and marking all plastic waste nodes; Step S23: performing semantic segmentation of waste bounding boxes one by one based on all plastic waste nodes, and extracting a full-range bounding box image of each waste; Step S24: performing a multi-angle morphological structure analysis on the omnidirectional boundary frame image of each waste, thereby generating morphological structure data of each waste; Step S25: Perform three-dimensional point cloud modeling on the morphological structure data of each waste to construct a three-dimensional structural model of each waste. In this embodiment, a high-resolution omnidirectional monitoring camera is installed at the initial plastic waste processing station to ensure that the entire processing area can be covered, and the camera parameters (such as resolution, frame rate, viewing angle, etc.) are configured to obtain clear monitoring images, set timed shooting or real-time video stream recording, collect omnidirectional monitoring images of plastic waste in the processing station, ensure that image collection is carried out in different time periods to capture the dynamic changes of waste, store the collected image data in a central database to ensure that the data format is unified and convenient for subsequent processing, pre-process the obtained omnidirectional monitoring images, including denoising, contrast enhancement and brightness adjustment, to improve the accuracy of subsequent detection, and use deep learning models (such as YOLO, Faster Use R-CNN) to perform visual inspection of waste, train the model to identify plastic waste, mark all plastic waste nodes in the image, manually review the inspection results to ensure that all marked waste nodes are accurate, store the marking results in the database for subsequent processing and analysis, generate a corresponding bounding box for each marked plastic waste node, determine its position and size in the image, apply semantic segmentation models (such as U-Net, DeepLab) to perform pixel-by-pixel segmentation within the bounding box of each waste, extract clear boundary areas, ensure that the segmentation results contain the complete outline of the waste, eliminate background interference, extract the omnidirectional bounding box image of each waste from the omnidirectional monitoring image, save it as an independent image file, and perform morphological analysis on the extracted bounding box image of each waste, including: shape features (such as contour, area, circumference), structural features (such as convex hull, concave), use image processing tools (such as OpenCV, scikit-image) to calculate the morphological features of each waste and generate morphological structure data, record the characteristic data of each waste, including shape, size, volume and other information, collect the morphological structure data of each waste, determine the parameters required for its 3D modeling (such as size, shape characteristics), use 3D modeling software (such as Blender, MeshLab) to generate a 3D point cloud model of each waste according to the morphological structure data, apply algorithms (such as structured light, laser scanning) to obtain the surface point cloud data of the waste, optimize the generated 3D point cloud, including denoising and smoothing, to ensure the fineness and accuracy of the model, and save the final 3D structure model in a standard format (such as PLY, OBJ) for subsequent use and analysis.

[0034] In this embodiment, the specific steps of step S24 are: Perform pixel-level edge contour recognition on each waste object in its full-range boundary frame image, and extract pixel-level edge contour lines of each waste object; Marking a plurality of edge feature points based on each waste pixel-level edge contour line; Calculate the positioning coordinates of multiple edge feature points; Performing three-dimensional geometric dimension calculation based on the positioning coordinates to obtain the three-dimensional geometric dimension characteristics of each waste; Performing visual recognition of the surface texture of each waste on the omnidirectional bounding box image to generate surface texture feature data of each waste; The surface texture feature data of each waste and the three-dimensional geometric size characteristics of each waste are subjected to multi-angle morphological structure analysis to generate the morphological structure data of each waste.

[0035] In this embodiment, the bounding box image is grayed and denoised (such as by using Gaussian blur) to improve the effect of edge detection, an image enhancement technique (such as histogram equalization) is used to improve the contrast of the image, an edge detection algorithm (such as the Canny edge detection algorithm) is applied to identify the pixel-level edge contour of the waste, and edge detection parameters (such as thresholds) are adjusted to ensure the accuracy of edge recognition. The edge contour is extracted using the findContours function in the OpenCV library to obtain a contour point set for each waste, and multiple feature points (such as corner points, edge midpoints, etc.) are selected on the extracted edge contour. Harris corner point detection or Shi-Tomasi method can be used to select representative feature points by analyzing the rate of change of the contour, and the marked edge feature points and their coordinates are stored in a database for subsequent calculation and analysis. The pixel coordinates (x, y), convert pixel coordinates into actual coordinates (such as centimeters or meters) through the resolution and scale of the image, store the actual coordinates of each feature point in the database for subsequent calculation, calculate the three-dimensional geometric dimensions (such as length, width, height, volume) of the waste according to the positioning coordinates of the edge feature points by using triangulation or other geometric calculation methods, combine the edge feature points and the acquired three-dimensional point cloud data to make a more accurate geometric dimension estimation, store the calculated three-dimensional geometric dimension features in the database, including the size information of each waste, pre-process the bounding box image, including denoising and enhancement, so as to facilitate subsequent texture feature extraction, apply texture analysis algorithms (such as LBP, Gabor filter, Haralick feature) to extract surface texture features from the bounding box image, calculate the statistical features of the texture (such as contrast, uniformity, entropy, etc.), collect the three-dimensional geometric dimension features and surface texture feature data of each waste, combine the geometric dimension features with the texture features, and conduct a comprehensive morphological structure analysis, use statistical analysis methods (such as principal component analysis) or machine learning algorithms (such as decision trees, random forests) to identify and classify the morphological features of the waste, generate the morphological structure data of each waste, and record its geometric features, texture features and comprehensive features.

[0036] In this embodiment, refer to Figure 4, is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: Identify the next transfer and processing station node based on the waste full-process tracking trajectory map, and obtain a full-range monitoring image of the next transfer and processing station; Step S32: performing waste identification on the all-round monitoring image of the next transfer and processing station, and extracting all plastic waste data; Step S33: Sequentially encode and mark all plastic waste data to obtain plastic waste coding data; Step S34: performing waste form analysis based on the plastic waste coding data, and extracting each coded waste form data; Step S35: performing a morphological comparison on each coded waste morphological data one by one based on the three-dimensional structural model of each waste, thereby generating a waste morphological comparison result of the transfer station.

[0037] In this embodiment, the latest transfer path data is extracted from the waste full process tracking trajectory map, the current location and status of the waste are identified, and the path analysis algorithm (such as Dijkstra algorithm) is used to determine the next transfer processing station node. By accessing the monitoring system of the next transfer processing station, a full-range monitoring image of the station is obtained to ensure that the obtained image is of high quality and good clarity to facilitate subsequent waste identification. The obtained full-range monitoring image is pre-processed, including noise removal, contrast enhancement and brightness adjustment, to improve the accuracy of subsequent identification, and a deep learning model (such as YOLO or Faster Use R-CNN (R-CNN) to identify waste in images, train the model to identify plastic waste and extract its location information and related data (such as quantity, type, etc.), manually review the identification results to ensure that all plastic waste data is accurate, store the identified plastic waste data in the database for subsequent processing, formulate sequential coding rules for plastic waste, such as coding according to the order of entry, type or other characteristics, sequentially encode each extracted plastic waste, generate unique coding data, associate the coding results with relevant information about the waste (such as location, type, status), extract its morphological characteristics, including size, shape, weight, etc. for each coded plastic waste, and use image processing tools (such as OpenCV ) calculate relevant morphological features (such as area, perimeter, shape index, etc.), organize and analyze the extracted morphological feature data, generate morphological data for each coded waste, record the morphological feature information of each waste for subsequent comparison, obtain the three-dimensional model of each coded waste from the previously constructed three-dimensional structure model library, use the morphological comparison algorithm (such as ICP algorithm, Hausdorff distance) to compare the morphological data and three-dimensional model of each coded waste one by one, calculate the similarity between the morphological features, identify wastes with similar morphology, record the results of the morphological comparison, including the similarity score and comparison status (match / mismatch) of each waste, store the comparison results in the database, and generate a waste morphology comparison report for the transfer station.

[0038] In this embodiment, step S4 includes the following steps: Step S41: When the waste form comparison result of the transfer station is successful, the dynamic tracking trajectory of the next transfer and processing station is determined as the correct tracking trajectory; Step S42: When the waste form comparison result of the transfer station is a comparison failure, an abnormal transfer warning process is performed to generate an abnormal transfer processing station warning signal; Step S43: Perform abnormal waste analysis on the plastic waste coding data based on the abnormal warning signal of the transfer and processing station to generate transfer abnormal plastic waste data.

[0039] In this embodiment, the morphological comparison status of each plastic waste is extracted from the comparison result database, the list of wastes that have been successfully compared is confirmed, the dynamic tracking trajectory of the wastes that have been successfully compared is updated to the "correct tracking trajectory", and the status of the tracking trajectory is recorded in the database to ensure that subsequent data analysis and management are based on the latest status. The list of wastes that failed to be compared is extracted from the comparison result database, and relevant information (such as coding, morphological characteristics, etc.) is recorded. For the wastes that failed to be compared, the abnormal warning processing mechanism is triggered, an abnormal warning signal of the transfer and processing station is generated, and the warning information, including the time, location and the waste codes involved, is recorded. The abnormal warning signal is sent to the real-time monitoring system and relevant personnel (such as Operators and managers) ensure timely response, use message queues or push notification mechanisms to ensure rapid information delivery, extract plastic waste coding data related to matching failures from the database according to abnormal warning signals, form a list of waste to be analyzed, apply data analysis methods (such as cluster analysis, anomaly detection algorithms) to analyze the extracted waste data, identify potential abnormal waste characteristics, combine historical data and morphological characteristics, identify items that are significantly different from normal waste, record analysis results, generate and transport abnormal plastic waste data, including coding, morphological characteristics, abnormal causes and other information, and store the generated abnormal waste data in the database for subsequent processing and decision support.

[0040] In this embodiment, the specific steps of step S5 are: Step S51: marking abnormal transfer points on the waste full-process tracking trajectory map based on the abnormal transfer plastic waste data, thereby extracting abnormal transfer processing station nodes; Step S52: Tracing the historical transfer trajectory of the abnormal transfer processing station node, thereby extracting the abnormal node traceability trajectory; Step S53: Identify the transit change trajectory points of the abnormal node traceability trajectory and extract multiple transit change trajectory points; Step S54: extracting the transit timestamps of multiple transit change trajectory points; Step S55: analyzing the abnormal waste transfer flow direction according to the transfer timestamp to generate abnormal waste transfer flow direction data; Step S56: Perform secondary monitoring of abnormal waste on the abnormal waste transfer flow data to generate a secondary monitoring trajectory of abnormal waste.

[0041] In this embodiment, data on abnormal plastic waste transfer is extracted from the database, including the coding, location and status information of the relevant waste, and abnormal transfer points are marked on the waste full-process tracking trajectory map. Different colors or symbols are used to indicate abnormal status, ensuring that the marked information includes detailed information on the abnormal waste for subsequent analysis, extracting and recording all marked abnormal transfer and processing station nodes, updating the information about the abnormal nodes in the database, querying the historical transfer trajectory data related to the abnormal transfer and processing station nodes, obtaining all transfer records of the node, performing a traceability analysis on the extracted historical transfer trajectory, identifying the transfer path and treatment status of the waste before the abnormal node, recording the results of the traceability analysis in the database, forming the traceability trajectory data of the abnormal node, applying a time series analysis method, analyzing the traceability trajectory data, identifying change points in the transfer process (such as changes in transfer methods, abnormal stagnation time, etc.), extracting multiple transfer change trajectory points, including the specific time, location and status of the change, and extracting the corresponding information from each transfer change trajectory point. The timestamp corresponding to each change is recorded, and the specific time of each change is recorded. These timestamps are organized into structured data to ensure that they correspond to the change trajectory point information. The extracted timestamp data is stored in the database for subsequent flow analysis. The extracted transfer change trajectory points and timestamp data are collected to provide basic data for flow analysis. Flow analysis algorithms (such as Markov chain and path analysis) are used to analyze the transfer flow of abnormal wastes, identify the change patterns and trends of the flow, generate abnormal waste transfer flow data, record information such as pollution sources, pathways and final destinations, and store the analysis results in the database for subsequent query and analysis. A secondary monitoring plan for abnormal waste transfer flows is designed, including the time, location and method of monitoring. Monitoring equipment (such as RFID readers and cameras) are deployed at key nodes of abnormal flows to monitor the flow of wastes in real time. Secondary monitoring data is collected, including information such as flow direction, time and location. The secondary monitoring data is organized into trajectory data to record the changes and timestamps of each monitoring point.

[0042] In this embodiment, the specific steps of step S6 are: Step S61: predicting the arrival time of each transfer processing station for the correct tracking trajectory, and obtaining the predicted arrival time of multiple processing stations; Step S62: optimizing the real-time trajectory rendering parameters of the waste full-process tracking trajectory map based on the predicted arrival time of multiple processing stations and the secondary monitoring trajectory of abnormal wastes, and constructing a rendering optimized tracking trajectory map; Step S63: Perform dynamic three-dimensional visualization processing on the rendering optimized tracking trajectory map, so as to construct a dynamic three-dimensional visualization tracking trajectory model. In this embodiment, data related to the correct tracking trajectory is extracted from the database, including the current waste location, the distance to each transfer and treatment station, and the historical transfer time. An appropriate time prediction model (such as linear regression, time series analysis model, machine learning model, etc.) is selected to observe the time pattern in the historical data. If the historical data is rich enough, a machine learning model (such as random forest or neural network) can be used for more complex time prediction. The distance between the current waste location and each transfer and treatment station and the historical transfer time are used as input to calculate the predicted arrival time, record the predicted arrival time of each treatment station, and store it in the database. The predicted arrival time of multiple treatment stations is output to provide basic data for subsequent trajectory rendering optimization. According to the predicted arrival time and the secondary monitoring trajectory of abnormal waste, the trajectory rendering parameters (such as speed, color, line type, etc.) are analyzed and determined. Consider using different rendering parameters to represent the trajectories of normal and abnormal transfers. For example, red is used to represent abnormal paths and green is used to represent normal paths. GIS software or custom Visualization tools can instantly render the waste tracking trajectory map of the entire process through input parameters, update the trajectory map in real time, ensure that the latest dynamic information is reflected within the scheduled time, optimize the map based on the rendering results, including adjusting the viewing angle, zoom level and detail level to enhance the visualization effect, select appropriate 3D modeling and visualization tools (such as Blender, Unity, Three.js, etc.) for dynamic 3D visualization, import the optimized rendering trajectory data and related geographic information into the 3D modeling software, build a 3D scene, use animation technology, update the trajectory model based on real-time data, and display the dynamic flow of waste. User interaction functions can be realized in the visualization environment, such as zooming in, zooming out, and rotating the viewing angle to view the trajectory information at different angles. The constructed dynamic 3D visualization tracking trajectory model can be output as an interactive application or visualization report to facilitate viewing and analysis by relevant personnel, and the dynamic model and visualization results can be stored in a database or cloud platform for subsequent access and sharing.

[0043] In this embodiment, a plastic waste tracking device using data management is provided, which is used to perform the plastic waste tracking method using data management as described above, including: Dynamic positioning and tracking module, used to obtain real-time positioning data of plastic waste; dynamically locate and track the real-time positioning data of plastic waste, and perform full-process trajectory evolution to build a full-process tracking trajectory map of waste; A three-dimensional structure module is used to obtain a full-range monitoring image of the initial plastic waste processing station; perform visual inspection of the waste on the full-range monitoring image, and perform multi-angle morphological structure analysis of the waste to construct a three-dimensional structure model of each waste; The morphology comparison module is used to obtain the omnidirectional monitoring image of the next transfer and treatment station based on the waste full-process tracking trajectory map; perform morphology comparison on the omnidirectional monitoring image one by one based on the three-dimensional structure model of each waste, so as to generate the morphology comparison result of the waste at the transfer station; The abnormal transfer module is used to analyze abnormal waste based on the waste morphology comparison results of the transfer station, generate correct tracking trajectories and transfer abnormal plastic waste data; The abnormal trajectory tracing module is used to trace the abnormal transportation trajectory of the waste full process tracking trajectory map based on the abnormal plastic waste transportation data, and conduct secondary monitoring of abnormal waste to generate abnormal waste secondary monitoring trajectory; The three-dimensional visualization module is used to optimize the real-time trajectory rendering parameters based on the correct tracking trajectory and the secondary monitoring trajectory of abnormal waste, and perform dynamic three-dimensional visualization processing to build a dynamic three-dimensional visualization tracking trajectory model.

[0044] The present invention helps to track the real-time position of the logistics process by acquiring the positioning data of plastic waste in real time, thereby improving the efficiency of supervision and management. The dynamic positioning tracking and full-process trajectory evolution construct a waste full-process tracking map, which provides an overall perspective for the system and helps users to fully understand the flow direction and status of the waste. It obtains all-round monitoring images of the initial processing station and conducts visual detection and multi-angle morphological structure analysis of the waste, which helps to establish a three-dimensional structural model of each waste and provide more comprehensive waste information. Through the construction of the three-dimensional structure model, the morphology of the waste can be more accurately described and presented, providing a basis for subsequent morphological comparison. By using the full-process tracking trajectory map and the three-dimensional structure model, morphological comparison can be performed, which can accurately identify the state changes of the waste at different transfer stations, help monitor and control the flow direction of the waste, and generate the transfer station waste morphological comparison results to help discover abnormal situations, handle them in time and conduct subsequent tracking to ensure the waste treatment process. Accuracy. Through abnormal waste analysis, abnormal situations can be discovered and handled in a timely manner to ensure the smooth progress of the waste treatment process and improve the accuracy and timeliness of tracking. Generating correct tracking trajectories and abnormal plastic waste transfer data helps to provide detailed data support and provide a basis for subsequent abnormal trajectory tracing. Through abnormal transfer trajectory tracing and abnormal waste secondary monitoring, abnormal waste conditions can be tracked and treatment measures can be adjusted in a timely manner to ensure the standardization and safety of the waste treatment process. Generating abnormal waste secondary monitoring trajectories helps to fully understand the causes and processes of abnormal situations and provide a reference for system improvement. Through real-time trajectory rendering parameter optimization and dynamic 3D visualization processing, a dynamic 3D visualization tracking trajectory model is constructed, which can vividly display the waste treatment process and improve the user's visualization experience and understanding. The realization of dynamic 3D visualization helps to present the details and changes of the waste transportation process and provide users with intuitive and comprehensive waste tracking information.

[0045] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0046] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for tracking plastic waste using data management, characterized in that: The following steps are involved: Step S1: obtaining real-time positioning data of plastic waste; dynamically locating and tracking the real-time positioning data of plastic waste, and performing full-process trajectory evolution to construct a full-process tracking trajectory map of waste; Step S2: Obtaining a comprehensive monitoring image of the initial plastic waste processing station; performing visual inspection of the waste on the comprehensive monitoring image, and performing multi-angle morphological structure analysis of the waste to construct a three-dimensional structural model of each waste; Step S3: obtaining a full-range monitoring image of the next transfer and processing station based on the waste full-process tracking trajectory map; performing a morphological comparison of the full-range monitoring image one by one based on the three-dimensional structural model of each waste, thereby generating a waste morphological comparison result of the transfer station; Step S4: Perform abnormal waste analysis based on the waste morphology comparison results of the transfer station to generate correct tracking trajectory and transfer data of abnormal plastic waste; Step S5: based on the data of transporting abnormal plastic waste, the abnormal transport trajectory is traced on the waste full process tracking trajectory map, and secondary monitoring of abnormal waste is performed to generate a secondary monitoring trajectory of abnormal waste; Step S6: Based on the correct tracking trajectory and the secondary monitoring trajectory of abnormal waste, the real-time trajectory rendering parameters are optimized, and dynamic three-dimensional visualization processing is performed to construct a dynamic three-dimensional visualization tracking trajectory model.

2. The method for tracking plastic waste using data management according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: implanting RFID tags into plastic waste to obtain real-time location data of the plastic waste; Step S12: Dynamically locate and track the real-time location data of plastic waste to generate a dynamic tracking trajectory for each waste; Step S13: performing waste transfer flow analysis on the dynamic tracking trajectory of each waste, thereby generating a dynamic transfer path for each waste; Step S14: Identify the transfer stagnation points of each dynamic transfer path of waste and mark the transfer processing station nodes; Step S15: performing a transfer node spatial distribution analysis on the transfer processing station nodes, thereby generating transfer node spatial distribution data; Step S16: Based on the spatial distribution data of the transfer nodes, the dynamic tracking trajectory of each waste is evolved throughout the entire process, and a waste full-process tracking trajectory map is constructed.

3. The method for tracking plastic waste using data management according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: Obtaining a comprehensive monitoring image of the initial plastic waste processing station; Step S22: Performing visual inspection of waste on the omni-directional monitoring image and marking all plastic waste nodes; Step S23: performing semantic segmentation of waste bounding boxes one by one based on all plastic waste nodes, and extracting a full-range bounding box image of each waste; Step S24: performing a multi-angle morphological structure analysis on the omnidirectional boundary frame image of each waste, thereby generating morphological structure data of each waste; Step S25: Perform three-dimensional point cloud modeling on the morphological structure data of each waste to construct a three-dimensional structural model of each waste.

4. The method for tracking plastic waste using data management according to claim 3, characterized in that: The specific steps of step S24 are: Perform pixel-level edge contour recognition on each waste object in its full-range boundary frame image, and extract pixel-level edge contour lines of each waste object; Marking a plurality of edge feature points based on each waste pixel-level edge contour line; Calculate the positioning coordinates of multiple edge feature points; Performing three-dimensional geometric dimension calculation based on the positioning coordinates to obtain the three-dimensional geometric dimension characteristics of each waste; Performing visual recognition of the surface texture of each waste on the omnidirectional bounding box image to generate surface texture feature data of each waste; The surface texture feature data of each waste and the three-dimensional geometric size characteristics of each waste are subjected to multi-angle morphological structure analysis to generate the morphological structure data of each waste.

5. The method for tracking plastic waste using data management according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: Identify the next transfer and processing station node based on the waste full-process tracking trajectory map, and obtain a full-range monitoring image of the next transfer and processing station; Step S32: performing waste identification on the all-round monitoring image of the next transfer and processing station, and extracting all plastic waste data; Step S33: Sequentially encode and mark all plastic waste data to obtain plastic waste coding data; Step S34: performing waste form analysis based on the plastic waste coding data, and extracting each coded waste form data; Step S35: performing a morphological comparison on each coded waste morphological data one by one based on the three-dimensional structural model of each waste, thereby generating a waste morphological comparison result of the transfer station.

6. The method for tracking plastic waste using data management according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: When the waste form comparison result of the transfer station is successful, the dynamic tracking trajectory of the next transfer and processing station is determined as the correct tracking trajectory; Step S42: When the waste form comparison result of the transfer station is a comparison failure, an abnormal transfer warning process is performed to generate an abnormal transfer processing station warning signal; Step S43: Perform abnormal waste analysis on the plastic waste coding data based on the abnormal warning signal of the transfer and processing station to generate transfer abnormal plastic waste data.

7. The method for tracking plastic waste using data management according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: marking abnormal transfer points on the waste full-process tracking trajectory map based on the abnormal transfer plastic waste data, thereby extracting abnormal transfer processing station nodes; Step S52: Tracing the historical transfer trajectory of the abnormal transfer processing station node, thereby extracting the abnormal node traceability trajectory; Step S53: Identify the transit change trajectory points of the abnormal node traceability trajectory and extract multiple transit change trajectory points; Step S54: extracting the transit timestamps of multiple transit change trajectory points; Step S55: analyzing the abnormal waste transfer flow direction according to the transfer timestamp to generate abnormal waste transfer flow direction data; Step S56: Perform secondary monitoring of abnormal waste on the abnormal waste transfer flow data to generate a secondary monitoring trajectory of abnormal waste.

8. The method for tracking plastic waste using data management according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: predicting the arrival time of each transfer processing station for the correct tracking trajectory, and obtaining the predicted arrival time of multiple processing stations; Step S62: optimizing the real-time trajectory rendering parameters of the waste full-process tracking trajectory map based on the predicted arrival time of multiple processing stations and the secondary monitoring trajectory of abnormal wastes, and constructing a rendering optimized tracking trajectory map; Step S63: Perform dynamic three-dimensional visualization processing on the rendering optimized tracking trajectory map, so as to construct a dynamic three-dimensional visualization tracking trajectory model.

9. A plastic waste tracking device using data management, characterized in that, A method for performing plastic waste tracking using data management as claimed in claim 1, comprising: Dynamic positioning and tracking module, used to obtain real-time positioning data of plastic waste; dynamically locate and track the real-time positioning data of plastic waste, and perform full-process trajectory evolution to build a full-process tracking trajectory map of waste; A three-dimensional structure module is used to obtain a full-range monitoring image of the initial plastic waste processing station; perform visual inspection of the waste on the full-range monitoring image, and perform multi-angle morphological structure analysis of the waste to construct a three-dimensional structure model of each waste; The morphology comparison module is used to obtain the omnidirectional monitoring image of the next transfer and treatment station based on the waste full-process tracking trajectory map; perform morphology comparison on the omnidirectional monitoring image one by one based on the three-dimensional structure model of each waste, so as to generate the morphology comparison result of the waste at the transfer station; The abnormal transfer module is used to analyze abnormal waste based on the waste morphology comparison results of the transfer station, generate correct tracking trajectories and transfer abnormal plastic waste data; The abnormal trajectory tracing module is used to trace the abnormal transportation trajectory of the waste full process tracking trajectory map based on the abnormal plastic waste transportation data, and conduct secondary monitoring of abnormal waste to generate abnormal waste secondary monitoring trajectory; The three-dimensional visualization module is used to optimize the real-time trajectory rendering parameters based on the correct tracking trajectory and the secondary monitoring trajectory of abnormal waste, and perform dynamic three-dimensional visualization processing to build a dynamic three-dimensional visualization tracking trajectory model.

Images