Method and system capable of identifying medical waste stealing action

Abstract

The invention discloses a method and system capable of identifying medical waste stealing actions, and the method comprises the steps: firstly obtaining visual information of a loading and unloading region through an omnibearing real-time video, carrying out the preprocessing of video data, and removing interference factors to enhance the definition and accuracy of an image; and then distance estimation is carried out on the preprocessed video, the moving distance of the human body to the transfer trolley is analyzed, and whether an abnormal approaching behavior exists or not is judged. If the system recognizes the abnormal approaching behavior, the arm action of the human body is further analyzed, and whether the abnormal action exists or not is judged according to the angle change of the arm. If the arm angle is detected to be abnormal and the system recognizes that medical waste is possibly held in the hand, the system automatically triggers an early warning mechanism. The method effectively overcomes the defects that traditional manual monitoring is low in efficiency and poor in judgment accuracy, abnormal behaviors can be accurately found in real time, and intelligent support is provided for safety management of medical waste.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical waste theft identification, and in particular relates to a method and system capable of identifying medical waste theft actions. Background Art

[0002] In the monitoring scene of the medical waste loading and unloading area, a spherical camera is needed to capture all-round real-time video and transmit the video data to the background. The system needs to use a deep learning model to accurately identify and analyze the postures of multiple people in the video, especially the distance the human body moves to the transfer vehicle and the change in the angle of the arm, in order to determine whether there is abnormal approach and theft. . A key technical issue here is how to use posture recognition technology to accurately analyze the angle changes of key parts of the human body, such as the arm, in complex loading and unloading scenes. Due to the large number of people in the loading and unloading area and the frequent human movement and occlusion, it is difficult for traditional posture recognition algorithms to accurately capture the angle changes of the arm. In addition, the lighting conditions in the loading and unloading area may be poor, which will also affect the accuracy of posture recognition. Therefore, it is necessary to study how to use deep learning technology to optimize the posture recognition model, improve its robustness and accuracy in complex scenes, and realize accurate analysis of the angle changes of the human arm. At the same time, it is also necessary to explore how to combine posture analysis with object recognition technology to determine whether the suspicious person holds medical waste in his hand, so as to further improve the accuracy of theft recognition. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a method and system for identifying medical waste theft actions to solve the above problems in the prior art.

[0004] To achieve the above object, the present invention provides a method for identifying medical waste theft, comprising the following steps:

[0005] Obtain all-round real-time video of the medical waste loading and unloading area and pre-process the video;

[0006] Distance estimation is performed on the pre-processed video to analyze the distance the human body moves toward the transfer vehicle and determine whether there is abnormal approach behavior;

[0007] If abnormal approach behavior is identified, the arm movement will be further analyzed. If the arm angle changes abnormally and medical waste is detected in the hand, the system will trigger an early warning.

[0008] Optionally, the process of obtaining a full range of real-time video of the medical waste loading and unloading area includes:

[0009] Use spherical cameras to collect all-round real-time video of the medical waste loading and unloading area to obtain high-resolution video data;

[0010] Through real-time video streaming technology, the video data collected by the spherical camera is transmitted to the background in real time.

[0011] Optionally, preprocessing the video includes:

[0012] After receiving the real-time video data, the background preprocesses the video frames, including image denoising, enhancement and normalization.

[0013] Optionally, perform distance estimation on the preprocessed video, analyze the distance the human body moves toward the transfer vehicle, and determine whether there is abnormal approach behavior:

[0014] The YOLOv5 target detection algorithm is used to process the image in real time, and the human targets in the image are identified with a confidence threshold of 9, and the pixel-level bounding box coordinates (x, y, w, h) of each target are obtained;

[0015] Based on the feedback information from the transfer vehicle's RFID positioning system, the real-time position coordinates (X, Y) of the transfer vehicle are obtained, and the coordinates of the center point of the human body's bounding box (x+w / 2, y+h / 2) and the transfer vehicle's coordinates (X, Y) are substituted into the Euclidean distance formula to calculate the straight-line distance d between the human body and the transfer vehicle;

[0016] If d is less than the preset threshold of 3 meters, it is determined that the human body is moving towards the transfer vehicle and that abnormal approach behavior exists.

[0017] Optionally, if an abnormal approach behavior is identified, the arm movement is further analyzed. If the arm angle changes abnormally and it is detected that the hand may hold medical waste, the system will trigger an early warning process including:

[0018] The target tracking algorithm is used to continuously track people who make abnormal approach behaviors and obtain subsequent movement trajectories and action changes;

[0019] According to the movement trajectory and angle change of the hand during tracking, the action sequence of the arm from bending to stretching and then bending again is determined;

[0020] Combined with the hand movement trajectory and body movement distance, it is determined whether the person has stolen items from the box.

[0021] Optionally, also include:

[0022] Send warning information and detailed data of suspicious persons to monitoring personnel, including location information and type of handheld objects;

[0023] The system automatically saves video screenshots and posture analysis data of suspicious persons, and uses data encryption technology to ensure information security.

[0024] Optionally, the system automatically saves video screenshots and posture analysis data of suspicious persons, and uses data encryption technology to ensure information security including:

[0025] The video is encrypted and stored using the AES-256 encryption algorithm; a digital watermark is embedded in the video screenshot, including timestamp and location information, and hashed using the SHA-256 algorithm.

[0026] The present invention also provides a system capable of identifying the theft of medical waste, which is used to implement a method capable of identifying the theft of medical waste, the system comprising:

[0027] Panoramic video acquisition module, used to capture all-round real-time video of the medical waste loading and unloading area;

[0028] Video transmission module, used to send video data to the background through real-time video streaming technology;

[0029] Intelligent visual analysis module, which uses deep learning models and real-time processing capabilities to identify human posture in videos;

[0030] The abnormal behavior detection module is used to analyze the distance the human body moves toward the transfer vehicle to determine whether there is abnormal approach behavior, and use angle change detection technology to analyze the movement of the arm to analyze whether there is theft behavior;

[0031] The early warning and data transmission module is used to send early warning information and detailed data of suspicious persons to monitoring personnel, and automatically save video screenshots and posture analysis data of suspicious persons;

[0032] The data security module is used to save data using data encryption technology.

[0033] The present invention also provides a computer terminal device, comprising:

[0034] one or more processors;

[0035] A memory, coupled to the processor, for storing one or more programs;

[0036] When the one or more programs are executed by the one or more processors, the one or more processors implement the steps of a method for identifying medical waste theft.

[0037] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of a method for identifying the theft of medical waste are implemented.

[0038] Compared with the prior art, the present invention has the following advantages and technical effects:

[0039] The present invention discloses an intelligent monitoring method and system for medical waste loading and unloading areas. First, visual information of the loading and unloading area is obtained through all-round real-time video, and the video data is preprocessed to remove interference factors to enhance image clarity and accuracy. Then, the distance of the preprocessed video is estimated, and the distance moved by the human body to the transfer vehicle is analyzed to determine whether there is abnormal approach behavior. If the system identifies abnormal approach behavior, the human body's arm movement is further analyzed to determine whether there is abnormal movement through changes in the arm angle. If an abnormal arm angle is detected and the system identifies that medical waste may be held in the hand, the system will automatically trigger an early warning mechanism. This method effectively overcomes the defects of low efficiency and poor judgment accuracy of traditional manual monitoring, and can detect abnormal behavior in real time and accurately, providing intelligent support for the safe management of medical waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0041] Figure 1 This is a flow chart of a method according to Embodiment 1 of the present invention;

[0042] Figure 2 This is a schematic diagram of the system structure of the second embodiment of the present invention. DETAILED DESCRIPTION

[0043] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0044] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0045] Embodiment 1

[0046] like Figure 1 As shown, a method for identifying the theft of medical waste in this embodiment may specifically include:

[0047] Step S101, using the panoramic shooting capability and high-resolution video output of the spherical camera, capture all-round real-time video of the medical waste loading and unloading area. These video data are sent to the backend through real-time video streaming technology.

[0048] A spherical camera is used to collect all-round real-time video of the medical waste loading and unloading area to obtain high-resolution video data.

[0049] Through real-time video streaming technology, the video data collected by the spherical camera is transmitted to the background in real time.

[0050] Specifically, a spherical camera with a pixel of 4096×2160 was installed in the medical waste loading and unloading area, and the real-time video stream was transmitted to the background at an average speed of 50 frames per second through H. 265 encoding and 5G network.

[0051] Step S102: After receiving the video data, the background uses the deep learning model and real-time processing capabilities to accurately identify the human posture in the video. The system uses multi-person posture recognition technology to analyze the movements of all people in the scene.

[0052] The background receives the video surveillance image data transmitted in real time by the spherical camera, and uses video preprocessing technology to denoise and enhance the image to obtain a clear surveillance image.

[0053] Specifically, after the background receives the high-definition video surveillance image data transmitted in real time by the spherical camera, it first uses the median filtering algorithm to denoise the image, and then uses the histogram equalization technology to enhance the image contrast, making the surveillance image clearer.

[0054] Step S103, by detecting abnormal behavior and estimating the distance, analyzing the distance the human body moves toward the transfer vehicle, and determining whether there is abnormal approach behavior. If the distance is too short, it is considered that there may be theft.

[0055] Acquire video surveillance screen data, use a human body detection algorithm to identify human targets in the screen, and obtain the human body position coordinates; calculate the distance between the human body and the transfer vehicle based on the human body position coordinates and the transfer vehicle position coordinates, and determine whether the human body is moving in the direction of the transfer vehicle;

[0056] Specifically, after the background receives the 1080P high-definition video surveillance screen data transmitted in real time by the spherical camera, the YOLOv5 target detection algorithm is first used to process the screen in real time, and the human targets in the screen are identified with a confidence threshold of 9, and the pixel-level bounding box coordinates (x, y, w, h) of each target are obtained. At the same time, the background obtains the real-time position coordinates (X, Y) of the transfer vehicle based on the feedback information of the transfer vehicle RFID positioning system. Substitute the coordinates of the center point of the human body bounding box (x+w / 2, y+h / 2) and the transfer vehicle coordinates (X, Y) into the Euclidean distance formula to calculate the straight-line distance d between the human body and the transfer vehicle. If d is less than the preset threshold of 3 meters, it is judged that the human body is moving in the direction of the transfer vehicle, and it is judged that abnormal approach behavior is identified.

[0057] Step S104: for the identified abnormal approach behavior, further use the angle change detection technology to analyze the arm movement. If the arm angle changes abnormally and the object recognition technology detects that the hand is holding medical waste, an early warning will be triggered.

[0058] Key point detection technology is used to estimate the posture of each human target, obtain the spatial coordinates of the key points of the human skeleton, and determine the posture and movement of the human body.

[0059] If suspicious behavior is detected, the target tracking algorithm will continue to track the person and obtain their subsequent movement trajectory and action changes.

[0060] According to the movement trajectory and angle change of the hand during tracking, the action sequence of the arm from bending to stretching and then bending again is determined.

[0061] Combined with the hand movement trajectory and body movement distance, it is determined whether the person has stolen items from the box.

[0062] As an optional implementation, the YOLOv5 target detection algorithm is used to process the image in real time, and the human targets in the image are identified with a confidence threshold of 9, and the pixel-level bounding box coordinates and size of each target are obtained, so as to determine the spatial distribution of people in the monitoring scene. For each human target detected, the background uses the OpenPose key point detection algorithm to extract the pixel coordinates of the 18 skeletal key points of the human body, and judge the posture and movement of the human body at the moment according to the relative position relationship of the key points such as the shoulder, elbow, and wrist. By analyzing the changes in the human posture in each frame, if a human target is found to move more than 20 cm toward the vehicle body in 5 consecutive frames, and the hand key point enters the 120° fan-shaped area at the entrance of the box, it is determined that the person has suspicious behavior.

[0063] Specifically, for suspicious persons, the background automatically switches to the target tracking mode, uses the Kalman filter algorithm to predict their movement trajectory in real time, and continuously tracks and monitors them. During the tracking process, if the angle between the upper arm and the shoulder changes from less than 30° to greater than 150°, and the wrist key point is higher than the elbow key point, it is judged that the arm has completed a movement from bending to stretching; if the arm changes from the stretched state to the bent state within 2 seconds, and the wrist key point is lower than the elbow key point, and the human body moves more than 50 cm away from the vehicle body, and it is judged that there is an object in the hand, it is judged that the person has completed a theft of the object from the box. If the arm changes from the stretched state to the bent state within 2 seconds, and the wrist key point is lower than the elbow key point, and the human body moves more than 50 cm away from the vehicle body, and there is no object in the hand, it will eventually be judged as a normal behavior operation.

[0064] As an optional implementation, an object recognition algorithm based on a convolutional neural network is used to detect and classify handheld objects. The algorithm is trained on the ImageNet dataset and can recognize more than 200 common objects with an accuracy rate of more than 90%, including handheld objects such as syringes, infusion bags and other medical waste.

[0065] Step S105, sending the warning information and detailed data of the suspicious person to the monitoring personnel, including the location information and the type of the handheld object.

[0066] If the result of the judgment is that there is a suspected dangerous action, the analysis result will be transmitted back to the on-board intelligent module, and the alarm signal and related data will be sent to the supervision screen;

[0067] Through real-time data interaction between intelligent modules, background servers and large monitoring screens, an intelligent medical waste monitoring system is formed to curb the occurrence of theft incidents.

[0068] Specifically, if it is determined that there is a suspected dangerous action, the analysis result will be transmitted back to the on-board intelligent module within 5 seconds, and the alarm signal and related data will be sent to the supervision screen through the MQTT protocol. After receiving the alarm data, the WebSocket server on the supervision screen uses WebGL technology to render the location of the event, character actions and other information in a three-dimensional scene, intuitively presenting the dangerous situation, so that supervisors can take timely measures. The entire medical waste intelligent supervision system uses real-time data interaction between intelligent modules, background servers, and supervision screens, with an average end-to-end delay of 20ms, to achieve rapid discovery and response to suspicious theft behaviors, effectively curbing the occurrence of medical waste theft incidents.

[0069] Step S106, automatically save the video screenshots and posture analysis data of the suspicious person, use data encryption technology to ensure information security, and provide evidence support for possible subsequent investigations.

[0070] If suspicious behavior is detected, the video screenshot and posture analysis data saving operation will be automatically triggered, and the relevant information will be stored in the system database in an encrypted manner. Digital watermark technology is used to mark the saved video screenshots, embed metadata information such as timestamps and locations, and ensure the authenticity and integrity of the video evidence. By analyzing the movement trajectory of the suspicious person, the range of activities and movement routes are obtained to provide a reference for subsequent investigation and evidence collection. The encrypted video screenshots and posture analysis data are associated with the identity information of the suspicious person to establish a complete chain of evidence. Blockchain technology is used to store evidence information, and its non-tamperable and traceable characteristics are used to ensure the credibility of the evidence. Through access control and permission management mechanisms, the access and use of evidence information are strictly controlled to prevent evidence leakage or illegal tampering, and ensure the security of evidence information.

[0071] Specifically, when suspicious behavior is identified through posture analysis, a screenshot is automatically triggered and the posture analysis data is saved. These data are encrypted and stored using the AES-256 encryption algorithm to ensure information security. At the same time, a digital watermark, including timestamp and location information, is embedded in the video screenshot, and hashed using the SHA-256 algorithm to ensure the authenticity and integrity of the video evidence. By analyzing the movement trajectory of suspicious persons, a map of their movement routes within the monitoring area can be automatically drawn with an accuracy of ±5 meters, providing a detailed path of action for subsequent investigations. All related data, such as video screenshots, posture analysis data, and identity information, are stored on the chain through blockchain technology, using the immutability and traceability of blockchain to enhance the legal effect of evidence. There is also a strict access control and authority management mechanism to ensure that only authorized personnel can access these sensitive data, effectively preventing information leakage or illegal tampering.

[0072] Based on this, the present invention provides an intelligent monitoring method for medical waste loading and unloading areas. First, a spherical camera is used to capture all-round real-time video of the loading and unloading area, and the data is sent to the background processing system through real-time video streaming technology. The system uses a deep learning model to accurately identify the human posture in the video, and combines algorithms such as multi-person posture recognition, abnormal behavior detection and distance estimation to analyze the moving distance of the human body to the transfer vehicle in real time to determine whether there is abnormal approach behavior. For the detected abnormal approach behavior, the system further analyzes the human body movement through the arm angle change detection technology, and combines the object recognition technology to detect whether the hand holds medical waste. If the abnormal behavior is confirmed, the system will automatically trigger an early warning and send the relevant detailed information and analysis data to the monitoring personnel. At the same time, the system automatically saves the video screenshots and posture analysis data of the suspicious person, and uses data encryption technology to ensure information security, providing strong evidence for subsequent investigations. The present invention significantly improves the safety monitoring efficiency of the medical waste loading and unloading area, can accurately and real-time detect abnormal behaviors such as theft, and effectively ensures the safe management and disposal of medical waste.

[0073] Embodiment 2

[0074] like Figure 2 As shown, based on the same general inventive concept, the present invention also provides a system capable of identifying medical waste theft actions. The system capable of identifying medical waste theft actions provided by the present invention is described below. The system capable of identifying medical waste theft actions described below and the method capable of identifying medical waste theft actions described above can be referred to each other. The system includes:

[0075] Panoramic video acquisition module, used to capture all-round real-time video of the medical waste loading and unloading area;

[0076] Video transmission module, used to send video data to the background through real-time video streaming technology;

[0077] Intelligent visual analysis module, which uses deep learning models and real-time processing capabilities to identify human posture in videos;

[0078] The abnormal behavior detection module is used to analyze the distance the human body moves toward the transfer vehicle to determine whether there is abnormal approach behavior, and use angle change detection technology to analyze the movement of the arm to analyze whether there is theft behavior;

[0079] The early warning and data transmission module is used to send early warning information and detailed data of suspicious persons to monitoring personnel, and automatically save video screenshots and posture analysis data of suspicious persons;

[0080] The data security module is used to save data using data encryption technology.

[0081] The present invention provides an intelligent monitoring system for medical waste loading and unloading areas, aiming to improve the safety monitoring capabilities of the area. The system first captures all-round real-time video of the medical waste loading and unloading area through a panoramic video acquisition module to ensure no blind spot monitoring. Subsequently, the video transmission module sends the collected video data to the background through real-time video streaming transmission technology, providing real-time data support for subsequent analysis.

[0082] In the background, the intelligent visual analysis module uses deep learning models and powerful real-time processing capabilities to accurately identify human postures in the video and analyze the dynamic behaviors of the participants. The abnormal behavior detection module further analyzes the distance the human body moves to the transfer vehicle to determine whether there is abnormal approach behavior, and uses angle change detection technology to analyze arm movements to identify possible theft behaviors.

[0083] Once the system detects abnormal behavior, the early warning and data transmission module will immediately send the early warning information and detailed data of the suspicious person to the monitoring personnel, and automatically save the video screenshots and posture analysis data of the suspicious person to provide necessary evidence support for subsequent investigations. In addition, the data security module uses data encryption technology to ensure the safe storage of all sensitive information and prevent data leakage.

[0084] The present invention effectively solves the pain points of security monitoring in medical waste loading and unloading areas, greatly improves the detection and early warning capabilities of theft through real-time monitoring and intelligent analysis, ensures the safe disposal of medical waste, and enhances the overall protection effectiveness of the system.

[0085] It should be understood that the system capable of identifying medical waste theft provided by the embodiment of the present invention has all the advantages of the method capable of identifying medical waste theft provided by the above-mentioned embodiment.

[0086] The present invention also provides a computer terminal device, comprising:

[0087] one or more processors;

[0088] A memory, coupled to the processor, for storing one or more programs;

[0089] When the one or more programs are executed by the one or more processors, the one or more processors implement the steps of a method for identifying medical waste theft.

[0090] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of a method for identifying the theft of medical waste are implemented.

[0091] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for identifying the theft of medical waste, characterized in that: The following steps are involved: Obtain all-round real-time video of the medical waste loading and unloading area and pre-process the video; Distance estimation is performed on the pre-processed video to analyze the distance the human body moves toward the transfer vehicle and determine whether there is abnormal approach behavior; If abnormal approach behavior is identified, the arm movement will be further analyzed. If the arm angle changes abnormally and medical waste is detected in the hand, the system will trigger an early warning.

2. The method according to claim 1, characterized in that The process of obtaining a 360-degree, real-time video of the medical waste loading and unloading area includes: Use spherical cameras to collect all-round real-time video of the medical waste loading and unloading area to obtain high-resolution video data; Through real-time video streaming technology, the video data collected by the spherical camera is transmitted to the background in real time.

3. The method according to claim 1, characterized in that Video preprocessing includes: After receiving the real-time video data, the background preprocesses the video frames, including image denoising, enhancement and normalization.

4. The method according to claim 1, characterized in that: Distance estimation is performed on the preprocessed video to analyze the distance the human body moves toward the transfer vehicle and determine whether there is abnormal approach behavior: The YOLOv5 target detection algorithm is used to process the image in real time, and the human targets in the image are identified with a confidence threshold of 9, and the pixel-level bounding box coordinates (x, y, w, h) of each target are obtained; Based on the feedback information from the transfer vehicle's RFID positioning system, the real-time position coordinates (X, Y) of the transfer vehicle are obtained, and the coordinates of the center point of the human body's bounding box (x+w / 2, y+h / 2) and the transfer vehicle's coordinates (X, Y) are substituted into the Euclidean distance formula to calculate the straight-line distance d between the human body and the transfer vehicle; If d is less than the preset threshold of 3 meters, it is determined that the human body is moving towards the transfer vehicle and that abnormal approach behavior exists.

5. The method according to claim 1, characterized in that If abnormal approach behavior is identified, the arm movement is further analyzed. If the arm angle changes abnormally and medical waste is detected in the hand, the system will trigger an early warning process including: The target tracking algorithm is used to continuously track people who make abnormal approach behaviors and obtain subsequent movement trajectories and action changes; According to the movement trajectory and angle change of the hand during tracking, the action sequence of the arm from bending to stretching and then bending is determined; Combined with the hand movement trajectory and body movement distance, it is determined whether the person has stolen items from the box.

6. The method according to claim 1, characterized in that Also includes: Send warning information and detailed data of suspicious persons to monitoring personnel, including location information and type of handheld objects; The system automatically saves video screenshots and posture analysis data of suspicious persons, and uses data encryption technology to ensure information security.

7. The method according to claim 6, characterized in that Using data encryption technology to ensure information security includes: The video is encrypted and stored using the AES-256 encryption algorithm; a digital watermark is embedded in the video screenshot, including timestamp and location information, and hashed using the SHA-256 algorithm.

8. A system capable of identifying the theft of medical waste, characterized in that: A method for implementing the identifiable medical waste theft action according to any one of claims 1 to 7, the system comprising: Panoramic video acquisition module, used to capture all-round real-time video of the medical waste loading and unloading area; Video transmission module, used to send video data to the background through real-time video streaming technology; Intelligent visual analysis module, which uses deep learning models and real-time processing capabilities to identify human posture in videos; The abnormal behavior detection module is used to analyze the distance the human body moves toward the transfer vehicle to determine whether there is abnormal approach behavior, and use angle change detection technology to analyze the movement of the arm to analyze whether there is theft behavior; The early warning and data transmission module is used to send early warning information and detailed data of suspicious persons to monitoring personnel, and automatically save video screenshots and posture analysis data of suspicious persons; The data security module is used to save data using data encryption technology.

9. A computer terminal device, characterized in that: include: one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the various steps of the method for identifying medical waste theft as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying medical waste theft as described in any one of claims 1 to 7 are implemented.

Images