Rubbish bag external graphic feature-based violation evidence chain evidence obtaining method and system

Abstract

The invention discloses an illegal evidence chain evidence obtaining method and system based on external graphic features of a garbage bag, and relates to the technical field of garbage classification, and the method comprises the steps: obtaining an illegal putting graph uploaded by an inspection worker; inputting the violation putting image into a target identification model, and obtaining a violation image label; and screening out target video data from a video database according to the illegal image tag, and storing the target video data as law enforcement evidence. According to the invention, the efficiency and accuracy of garbage classification and illegal behavior supervision can be improved, the security, privacy and authenticity of data are ensured, a favorable means based on illegal evidence is provided for supervision of unclassified residents, and conditions are provided for unattended delivery points.

Description

Technical Field

[0001] This invention relates to the field of waste sorting technology, specifically to a method and system for obtaining evidence of violations based on the external graphic features of garbage bags. Background Technology

[0002] The management of timed and fixed-point garbage collection points for household waste sorting is currently mainly achieved through manual supervision. This involves dispatching dedicated personnel to supervise residents at designated times (generally 2-3 hours in the morning and 2-3 hours in the afternoon) to check on their sorting practices and encourage them to sort their waste. The main problems are: (1) Manual supervision lacks effective means to address residents who do not sort their waste, especially in terms of enforcement; (2) The timed opening of collection points inconveniences residents, forcing many collection points to remain open even without supervision; and (3) The financial burden of manual supervision is significant and unsustainable in the long term. Of course, there are also some intelligent supervision solutions, mainly based on intelligent collection equipment. These require residents to register in advance and use garbage bags with markings (such as QR codes) to achieve traceability. However, these solutions suffer from problems such as inconvenience for residents, high operating costs, and data insecurity.

[0003] To address these issues, regulatory measures and a reliable chain of evidence are needed to ensure effective crackdown and management of violations. Therefore, the inventors have proposed a method and system for obtaining evidence of violations based on the external graphic features of garbage bags. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and system for obtaining evidence of violations based on the external graphic features of garbage bags.

[0005] The first aspect involves methods for obtaining evidence of violations based on the external graphic features of garbage bags, including:

[0006] Obtain images of illegally disposed waste uploaded by inspection personnel;

[0007] Input the image of the illegally placed object into the target recognition model to obtain the label of the illegally placed image;

[0008] Target video data is selected from the video database based on the violation image tags, and the target video data is saved as law enforcement evidence.

[0009] Preferably, the method of obtaining images of illegally disposed waste uploaded by inspection personnel includes:

[0010] Obtain the identification of the inspection personnel and the equipment identification of the equipment used by the inspection personnel in the uploaded images of illegally disposed items;

[0011] Based on the identity identifier and device identifier, obtain the identity identifier key parameter and the device identifier key parameter, and combine the identity identifier key parameter and the device identifier key parameter to obtain the encryption key parameter;

[0012] The distance between the current inspection station and the next inspection station of the inspection personnel is obtained. The distance is used to encrypt the encryption key parameter to obtain the encryption key. The encryption key is then used to encrypt the violation image and its corresponding time information, wherein the time information includes the shooting time and the upload time.

[0013] Preferably, obtaining the images of illegally disposed waste uploaded by inspection personnel also includes:

[0014] The illegal image is decrypted to obtain the time of its capture and upload.

[0015] Determine whether the above shooting time is within the first preset time range;

[0016] When the shooting time is within a first preset time range, it is determined whether the difference between the upload time and the shooting time is within a second preset time range.

[0017] Preferably, the illegal delivery image is input into the target segmentation model to obtain the illegal image label, including:

[0018] The illegal placement map is input into the first target recognition model to obtain the illegal recognition box corresponding to the target object;

[0019] Input the violation identification box into the second identification model corresponding to the target identification object to obtain the feature information of each target identification object;

[0020] A violation image label is constructed based on the location information corresponding to the violation identification box and the feature information.

[0021] Preferably, the video database is used to store video data collected by intelligent monitoring equipment installed at various waste collection sites.

[0022] Preferably, filtering target video data from the video database based on the violation image tags includes:

[0023] The video data is analyzed to obtain the image tag set corresponding to the video data;

[0024] Calculate the similarity between the label of the violating image and the labels in the image label set, and determine the target image based on the similarity.

[0025] Video data of adjacent durations to the target image are selected from the video database as target video data.

[0026] Preferably, storing the target video data as law enforcement evidence includes:

[0027] The upload time and the shooting time are encrypted using the encryption key to obtain the encrypted time;

[0028] The shooting time is encrypted using the encryption key, and the upload time is encrypted using the encrypted shooting time to obtain the target encryption key;

[0029] The target video data is encrypted using the target encryption key to obtain an encrypted video;

[0030] The encryption time and the encrypted video are stored together.

[0031] Secondly, the evidence collection system for violations based on the external graphic features of garbage bags includes:

[0032] The acquisition module is used to acquire images of illegally disposed items uploaded by inspection personnel;

[0033] The identification module is used to input the illegal delivery image into the target identification model to obtain the illegal image label;

[0034] The matching module is used to filter target video data from the video database based on the violation image tags, and save the target video data as law enforcement evidence.

[0035] Thirdly, a computer device includes a processor and a memory, the memory storing a computer-readable storage medium that, when executed by the processor, implements the evidence chain method for obtaining evidence based on the external graphic features of garbage bags as described in any of the preceding claims.

[0036] Fourthly, a computer-readable storage medium storing a computer program that, when executed, implements the method for obtaining evidence chains of violations based on the external graphic features of garbage bags as described in any of the preceding claims.

[0037] The beneficial effects of this invention are as follows: This invention provides a method for obtaining evidence of violations based on the external graphic features of garbage bags. It can acquire evidence of violations by capturing images of illegal disposal using smart devices, and ensures the security and authenticity of the data through encryption and decryption technologies, thereby guaranteeing the safe use of the data. Simultaneously, this method also uses a target recognition model to filter target video data from a video database, which is then stored as law enforcement evidence. This achieves intelligent matching between images of illegal disposal and video data of residents' disposal, thus enabling the traceability of responsibility when littering or unsorted garbage bags are found at disposal points. It can be used as law enforcement evidence, providing a powerful enforcement tool for supervising residents who do not sort their garbage, and also facilitating unmanned disposal points. Attached Figure Description

[0038] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0039] Figure 1 A flowchart illustrating a method for obtaining evidence of violations based on the external graphic features of garbage bags, as provided in an embodiment of the present invention.

[0040] Figure 2 This is a schematic diagram of the structure of the evidence collection system for illegal evidence chains based on the external graphic features of garbage bags provided in an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0042] The embodiments of the technical solution of the present invention will now be described in detail with reference to the accompanying drawings. These embodiments are merely illustrative of the technical solution of the present invention and are therefore intended to limit the scope of protection of the present invention.

[0043] It should be noted that, unless otherwise stated, the technical or scientific terms used in this application should have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0044] like Figure 1 As shown in the figure, this application provides a method for obtaining evidence of violations based on the external graphic features of garbage bags, including:

[0045] Step 1: Obtain images of illegally disposed waste uploaded by inspection personnel;

[0046] Specifically, inspectors can conduct random checks on various waste sites based on their inspection tasks. When inspectors discover any illegal disposal, they can use smart devices to capture images of the illegal disposal for subsequent evidence collection. Illegal disposal can include unsorted waste, misdisposal, or littering. Smart devices can include mobile phones, tablets, etc.

[0047] In this embodiment of the invention, obtaining the illegal placement image uploaded by the inspection personnel includes: obtaining the identity identifier of the inspection personnel and the device identifier of the device used by the inspection personnel to upload the illegal placement image; obtaining the identity identifier key parameter and the device identifier key parameter based on the identity identifier and the device identifier, and combining the identity identifier key parameter and the device identifier key parameter to obtain the encryption key parameter; obtaining the distance between the current inspection station and the next inspection station of the inspection personnel, encrypting the encryption key parameter using the distance to obtain the encryption key, and encrypting the illegal placement image and its corresponding time information using the encryption key, wherein the time information includes the shooting time and the upload time.

[0048] To ensure data security and authenticity, this embodiment also requires encryption of the uploaded data. Existing encryption methods generally use a pre-set encryption key unique to the inspector or equipment. This fixed-key method has a low encryption level and the data is easily tampered with. Therefore, this embodiment considers both fixed and dynamic keys. Since the inspector's inspection tasks and time are not fixed, and the distance between the current inspection station and the next inspection station is also not fixed, this application uses the distance between the current station and the next station as a dynamic key. When encrypting the data uploaded by the inspector, multiple encryption is performed using distance, inspector identification, and the identification of the equipment used by the inspector, which greatly improves data security.

[0049] In this embodiment of the invention, obtaining the image of illegal placement uploaded by the inspection personnel further includes: decrypting the illegal image to obtain the shooting time and upload time of the illegal image; determining whether the shooting time is within a first preset time range; and if the shooting time is within the first preset time range, determining whether the difference between the upload time and the shooting time is within a second preset time range.

[0050] Encryption and decryption technologies ensure data security, preventing theft and tampering, thus guaranteeing data safety. Verifying the shooting and uploading times confirms the legality of data use, preventing illegal misuse or alteration, thereby ensuring data accuracy and reliability. Assessing the difference between uploading time and data usage time confirms the validity of data use, preventing misuse or abuse, thus ensuring the legality and validity of data usage.

[0051] Step 2: Input the illegally deployed image into the target recognition model to obtain the illegal image label;

[0052] In this embodiment of the invention, inputting the illegal delivery map into a target segmentation model to obtain illegal image labels includes: inputting the illegal delivery map into a first target recognition model to obtain illegal recognition boxes corresponding to target objects; inputting the illegal recognition boxes into a second recognition model corresponding to target objects to obtain feature information of each target object; and constructing illegal image labels based on the location information corresponding to the illegal recognition boxes and the feature information.

[0053] Specifically, before inputting the illegally placed image into the target recognition model, the illegally placed image needs to be preprocessed. The preprocessing methods include, but are not limited to, image denoising, image enhancement, image scaling, and image normalization.

[0054] Specifically, the first target recognition model is a YOLOv3 target segmentation model, which can identify the location of garbage bags and garbage cans from the illegal disposal map, and then obtain the positional relationship between garbage bags and garbage cans based on their positions, thereby obtaining complete location information.

[0055] Specifically, each label corresponds to a target identification object. For example, label 1: garbage bag, green, oval, sealed, located directly in front of garbage can 1, etc.; label 2: garbage can 2, green, open, located directly behind garbage bag 1, with stains in the middle of the can, etc.

[0056] By using the location and feature information corresponding to the violation identification box, tags can be constructed for violation images, which facilitates subsequent management and use, and also provides convenience for subsequent data analysis and mining. At the same time, these tags can also be used for the review and tracking of violations, effectively maintaining social order, good customs, safety and stability.

[0057] In this embodiment of the invention, the video database is used to store video data collected by intelligent monitoring equipment installed at various waste collection sites.

[0058] Specifically, the video surveillance equipment is a common device used in existing smart waste disposal sites, which can be a multi-angle monitoring camera, and will not be elaborated further in this embodiment of the invention. Collecting video data of waste disposal at the corresponding site through multi-angle monitoring cameras facilitates subsequent tracing of illegal disposal behavior.

[0059] Step 3: Filter target video data from the video database based on the violation image tags, and save the target video data as law enforcement evidence.

[0060] In this embodiment of the invention, selecting target video data from a video database based on the violation image tags includes: analyzing the video data to obtain an image tag set corresponding to the video data; calculating the similarity between the violation image tags and the tags in the image tag set, and determining the target image based on the similarity; and selecting video data of adjacent durations to the target image from the video database as the target video data.

[0061] Specifically, each of the violation image tags and image tags corresponds to at least one garbage bag. The method for calculating the similarity between the violation image tag and the tags in the image tag set includes: obtaining the first text corresponding to the violation image tag and the second text corresponding to the image tag, generating the corresponding text feature vectors, and using the cosine similarity algorithm to calculate the similarity between the two vectors.

[0062] In this embodiment of the invention, storing the target video data as law enforcement evidence includes: encrypting the upload time and the shooting time using the encryption key to obtain an encrypted time; encrypting the shooting time using the encryption key, and encrypting the upload time using the encrypted shooting time to obtain a target encryption key; encrypting the target video data using the target encryption key to obtain an encrypted video; and storing the encrypted time and the encrypted video together.

[0063] By encrypting the upload time and shooting time, this sensitive information can be protected from being stolen and viewed by unauthorized personnel, effectively ensuring the security and confidentiality of video data. At the same time, by using the upload time, shooting time, and encryption key together to construct the target encryption key for the corresponding target video data, the level of encryption protection can be effectively improved, preventing attackers from cracking the encrypted information and further reducing the possibility of video leakage and tampering.

[0064] In summary, this invention provides a method for obtaining evidence of violations based on the external graphic features of garbage bags. It can acquire evidence of violations by capturing images of illegal waste disposal using smart devices, and ensures data security and authenticity through encryption and decryption technologies, thereby guaranteeing the safe use of the data. Furthermore, by determining the shooting and uploading times, the legality of data use can be verified, ensuring the accuracy and credibility of the data. In addition, this method uses a target recognition model to filter target video data from a video database and saves it as law enforcement evidence, improving the accuracy and reliability of evidence of violations. This invention can improve the efficiency and accuracy of garbage sorting and violation supervision, ensure data security, privacy, and authenticity, and provide strong support for urban environmental and social governance.

[0065] like Figure 2As shown in the figure, this application provides a system for obtaining evidence of violations based on the external graphic features of garbage bags, including: an acquisition module 401 for acquiring images of illegal dumping uploaded by inspection personnel; an identification module 402 for inputting the images of illegal dumping into a target identification model to obtain violation image tags; and a matching module 403 for filtering target video data from a video database according to the violation image tags and saving the target video data as law enforcement evidence.

[0066] It should be understood that the evidence collection system for illegal evidence chains based on the external graphic features of garbage bags provided in this embodiment of the invention and the evidence collection method for illegal evidence chains based on the external graphic features of garbage bags provided in the above embodiments are based on the same inventive concept. For more specific working principles of each module in this embodiment of the invention, please refer to the above embodiments. In this embodiment of the invention, they will not be described in detail.

[0067] like Figure 3 As shown, this application provides an electronic device 800, including: a processor 810, a memory 820 and a bus 830. The processor is connected to the memory via the bus. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, they are used to implement the method as described in any one of the above embodiments. For details, please refer to the description in the above method embodiments. To avoid repetition, detailed descriptions are appropriately omitted here.

[0068] The bus is used to enable direct communication between these components. In this embodiment, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application-Specific Integrated Circuit (ASIC), an On-Premises Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in this embodiment. The general-purpose processor can be a microprocessor or any conventional processor.

[0069] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory stores computer-readable instructions, which, when executed by the processor, can perform the methods described in the above embodiments.

[0070] Understandable. Figure 3 The structure shown is for illustrative purposes only and may include structures larger than those shown. Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown. Figure 3 The components shown can be implemented using hardware, software, or a combination thereof.

[0071] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed, it implements any of the methods described in all the above embodiments. For details, please refer to the description in the above method embodiments. To avoid repetition, detailed descriptions are appropriately omitted here.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for obtaining evidence of violations based on the external graphic features of garbage bags, characterized in that, include: Obtain images of illegally disposed waste uploaded by inspection personnel; Input the image of the illegally placed object into the target recognition model to obtain the label of the illegally placed image; Target video data is selected from the video database based on the violation image tags, and the target video data is saved as law enforcement evidence.

2. The method for obtaining evidence of violations based on the external graphic features of garbage bags according to claim 1, characterized in that, Obtain images of illegally disposed waste uploaded by inspection personnel, including: Obtain the identification of the inspection personnel and the equipment identification of the equipment used by the inspection personnel in the uploaded images of illegally disposed items; Based on the identity identifier and device identifier, obtain the identity identifier key parameter and the device identifier key parameter, and combine the identity identifier key parameter and the device identifier key parameter to obtain the encryption key parameter; The distance between the current inspection station and the next inspection station of the inspection personnel is obtained. The distance is used to encrypt the encryption key parameter to obtain the encryption key. The encryption key is then used to encrypt the violation image and its corresponding time information, wherein the time information includes the shooting time and the upload time.

3. The method for obtaining evidence of violations based on the external graphic features of garbage bags according to claim 2, characterized in that, Obtaining images of illegally disposed waste uploaded by inspection personnel also includes: The illegal image is decrypted to obtain the time of its capture and upload. Determine whether the above shooting time is within the first preset time range; When the shooting time is within a first preset time range, it is determined whether the difference between the upload time and the shooting time is within a second preset time range.

4. The method for obtaining evidence of violations based on the external graphic features of garbage bags according to claim 3, characterized in that, The illegal delivery image is input into the target segmentation model to obtain the illegal image label, including: The illegal placement map is input into the first target recognition model to obtain the illegal recognition box corresponding to the target object; Input the violation identification box into the second identification model corresponding to the target identification object to obtain the feature information of each target identification object; A violation image label is constructed based on the location information corresponding to the violation identification box and the feature information.

5. The method for obtaining evidence of violations based on the external graphic features of garbage bags according to claim 4, characterized in that, The video database is used to store video data collected by intelligent monitoring equipment installed at various waste collection sites.

6. The method for obtaining evidence of violations based on the external graphic features of garbage bags according to claim 5, characterized in that, Target video data is filtered from the video database based on the aforementioned violation image tags, including: The video data is analyzed to obtain the image tag set corresponding to the video data; Calculate the similarity between the label of the violating image and the labels in the image label set, and determine the target image based on the similarity. Video data of adjacent durations to the target image are selected from the video database as target video data.

7. The method for obtaining evidence of violations based on the external graphic features of garbage bags according to claim 6, characterized in that, The target video data is stored as law enforcement evidence, including: The upload time and the shooting time are encrypted using the encryption key to obtain the encrypted time; The shooting time is encrypted using the encryption key, and the upload time is encrypted using the encrypted shooting time to obtain the target encryption key; The target video data is encrypted using the target encryption key to obtain an encrypted video; The encryption time and the encrypted video are stored together.

8. A system for obtaining evidence of violations based on the external graphic features of garbage bags, characterized in that, include: The acquisition module is used to acquire images of illegally disposed items uploaded by inspection personnel; The identification module is used to input the illegal delivery image into the target identification model to obtain the illegal image label; The matching module is used to filter target video data from the video database based on the violation image tags, and save the target video data as law enforcement evidence.

9. A computer device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer-readable storage medium that, when executed by the processor, implements the evidence chain method for obtaining evidence of violations based on the external graphic features of garbage bags as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method for obtaining evidence of violations based on the external graphic features of garbage bags as described in any one of claims 1-7.

Images