Method for planning inspection route in subway station based on COPRA

Abstract

The invention discloses a metro in-station inspection route planning mechanism based on COPRA, and the method comprises the steps: firstly taking cameras in a station as nodes, and constructing a network connection diagram according to the adjacency relation between the cameras; according to the importance of a camera, a weight is set for each edge, an overlapped community structure is found by adopting a COPRA algorithm, and an inspection route is planned. According to the method, effective division and optimization of the camera inspection line in the station can be realized, and the monitoring efficiency and safety are improved.

Description

Technical Field

[0001] This invention is a method for planning inspection routes in subway stations based on COPRA, belonging to the field of urban rail transit. Background Technology

[0002] With the acceleration of urbanization and the rapid development of subway transportation, subway stations, as an important component of urban public transportation, have attracted much attention regarding their safety and operational efficiency. To ensure the safe operation of subway stations and to promptly identify and address potential safety hazards, subway station inspections are particularly important. The inspection route mechanism, as a core part of the inspection work, directly affects the effectiveness of the inspections.

[0003] Traditional methods for planning inspection routes within subway stations have the following drawbacks: (1) lack of flexibility and adaptability; (2) difficulty in ensuring inspection quality. Summary of the Invention

[0004] To address the aforementioned problems, this invention discloses a COPRA-based inspection route planning mechanism for subway stations. This method first treats cameras within the station as nodes and constructs a network connection graph based on the adjacency relationships between cameras. Weights are assigned to each edge according to the importance of the cameras, and the COPRA algorithm is used to discover overlapping community structures and plan inspection routes. This method can effectively divide and optimize camera inspection routes within stations, improving monitoring efficiency and security.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a COPRA-based subway station inspection route planning mechanism, specifically comprising the following steps: S1: Collect information on the layout of cameras within the station; S2: Based on the adjacency relationship and monitoring range of the cameras, construct the connection relationship between the cameras to form a camera network connection diagram; S3: Assign a unique identifier to each camera and initialize an empty tag set to store its possible community affiliation; S4: Set a threshold, calculate the tag frequency of adjacent cameras, and select a tag for the current camera based on the threshold.

[0006] S5: Cameras with the same label belong to the same community, i.e., one inspection route; a camera may have multiple labels, then the camera belongs to multiple communities, i.e., multiple inspection routes.

[0007] S6: Adjust the order of the cameras along the inspection route according to their positions to form the final inspection route.

[0008] Furthermore, S1 specifically involves: acquiring the layout information of cameras within the station, including the location, monitoring range, and number of the cameras.

[0009] Furthermore, S3 specifically involves treating each camera as a separate community. An initial label is assigned to each camera, representing the community it belongs to. Simultaneously, a membership coefficient is introduced for each camera, representing the degree of membership of the node to the community. Initially, the membership coefficient of a node is 1 for its own community and 0 for other communities.

[0010] Furthermore, S4 specifically includes: 1) Calculate the similarity between each camera and other cameras, and set the weight parameters; 2) Camera a will update its own label based on the label of its neighbor camera b. Camera a's new membership coefficient is obtained by weighting the corresponding community membership coefficients of its neighbor camera b (i.e., the weights from camera a to camera b). 3) Delete community information with low membership degree according to the threshold, and normalize the remaining membership degree so that the sum is 1; 4) Repeat the propagation and adjustment steps until the community structure is stable or the preset number of iterations is reached; 5) Adjust the threshold to control the size and overlap of communities to accommodate different needs; 6) Finally, the algorithm outputs the fuzzy community affiliation of each camera, that is, the affiliation coefficient of each camera to each community.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. The COPRA algorithm used in this invention does not require the construction of a complete adjacency matrix, but instead uses sparse representation, which greatly reduces computation and storage costs.

[0012] 2. This invention is efficient, applicable, and flexible in dividing the inspection routes within stations.

[0013] 3. This invention helps to improve the operation and maintenance efficiency and management level of subway stations. Attached Figure Description

[0014] Figure 1 This is a flowchart of a subway station inspection route planning method based on COPRA according to the present invention.

[0015] Figure 2 This invention relates to a camera network connection diagram based on the adjacency relationship and monitoring range of cameras. Detailed Implementation

[0016] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples.

[0017] like Figure 1 As shown, the video analysis strategy mechanism method of the present invention includes: S101: Collect the layout information of cameras (CA) within the station, including the camera's location (L), monitoring range (R), and number (N).

[0018] CA1:[L1,R1,N1,...],CA2:[L2,R2,N2,...],CA3:[L3,R3,N3,...],… S102: Based on the adjacency relationship and monitoring range of the cameras, construct the connection relationship between the cameras to form a camera network connection diagram, such as... Figure 2 As shown.

[0019] S103: Assign a unique identifier to each camera and initialize an empty tag set to store its possible community affiliation.

[0020] (1) Taking camera a as an example, its camera number channelId_a is used as its unique identifier, and its community is initialized as Community_a. Other cameras are similar.

[0021] S104: Set a threshold, calculate the tag frequency of adjacent cameras, and select a tag for the current camera based on the threshold.

[0022] Calculate the similarity between each camera and other cameras, and set the weight parameters;

[0023] in, Indicates camera and cameras Similarity, i.e., camera and The weights between them. and These represent cameras. and The set of neighboring nodes. Indicates camera and The number of common neighbor nodes. Indicates camera and The size of the union of the neighboring node sets.

[0024] Camera A will update its own tag based on the tag of its neighbor Camera B. Camera A's new membership coefficient is obtained by a weighted average of the corresponding community membership coefficients of its neighbor Camera B.

[0025] in, This indicates the number of neighboring cameras of camera a.

[0026] Delete community information with low membership degree based on the threshold, and normalize the remaining membership degree so that the sum is 1;

[0027] 4) Repeat the propagation and adjustment steps until the community structure is stable or the preset number of iterations is reached;

[0028] Where m is the number of edges in the network; Let be an element in the adjacency matrix A. If nodes i and j are connected, then =1, otherwise =0; For the community to which node i belongs, Let i be the community to which node j belongs; when i and j belong to the same community, =1, otherwise 0; This represents the degree of node i (i.e., the number of edges to node i). This indicates the possibility that there is an edge between node i and node j in the network.

[0029] 5) Adjust the threshold to control the size and overlap of communities to accommodate different needs; 6) Finally, the algorithm outputs the fuzzy community affiliation of each camera, that is, the affiliation coefficient of each camera to each community.

[0030] S105: Cameras with the same label belong to the same community, i.e., one inspection route; a camera may have multiple labels, then the camera belongs to multiple communities, i.e., multiple inspection routes.

[0031] S106: Adjust the order of the cameras along the inspection route according to their positions to form the final inspection route.

[0032] The above embodiments are merely illustrative of the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made to the technical solution based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention. Technologies not covered in this invention can be implemented using existing technologies.

Claims

1. A COPRA-based inspection route planning mechanism for subway stations, characterized in that: The following steps are involved: S1: Collect information on the layout of cameras within the station; S2: Based on the adjacency relationship and monitoring range of the cameras, construct the connection relationship between the cameras to form a camera network connection diagram; S3: Assign a unique identifier to each camera and initialize an empty tag set to store its possible community affiliation; S4: Set a threshold, calculate the tag frequency of adjacent cameras, and select a tag for the current camera based on the threshold; S5: Cameras with the same label belong to the same community, i.e., a patrol route; If a camera has multiple tags, then the camera belongs to multiple communities, i.e., multiple patrol routes; S6: Adjust the order of the cameras along the inspection route according to their positions to form the final inspection route.

2. The COPRA-based subway station inspection route planning mechanism according to claim 1, characterized in that: The S1 collects information on the layout of cameras within the station, including the location, monitoring range, and number of the cameras.

3. The COPRA-based subway station inspection route planning mechanism according to claim 1, characterized in that: In S3, each camera is treated as a separate community, and an initial label is assigned to each camera to indicate the community to which it belongs. At the same time, a membership coefficient is introduced for each camera to indicate the degree of membership of the node to the community. Initially, the membership coefficient of the node is 1 for its own community and 0 for other communities.

4. The COPRA-based subway station inspection route planning mechanism according to claim 1, characterized in that: Specifically, S4 is: S4.1: Calculate the similarity between each camera and other cameras, and set the weight parameters; ， in, Indicates camera and cameras Similarity, i.e., camera and Weights between them; and These represent cameras. and The set of neighboring nodes; Indicates camera and The number of common neighbor nodes; Indicates camera and The size of the union of the neighboring node sets; S4.2: Camera a will update its own label based on the label of its neighbor camera b; the new membership coefficient of camera a is obtained by weighted average of the corresponding community membership coefficients of neighbor camera b; ， in, This indicates the number of neighboring cameras of camera a; S4.3: Delete community information with low membership degree according to the threshold, and normalize the remaining membership degree so that the sum is 1; ， S4.4: Repeat the propagation and adjustment steps until the community structure is stable or the preset number of iterations is reached; ， Where m is the number of edges in the network; Let be an element in the adjacency matrix A. If nodes i and j are connected, then =1, otherwise =0; For the community to which node i belongs, Let i be the community to which node j belongs; when i and j belong to the same community, =1, otherwise 0; Indicates the degree of node i. This indicates the probability that there is an edge between node i and node j in the network; S4.5: Adjust the threshold to control the size and overlap of communities to suit different needs; S4.6: Finally, the algorithm outputs the fuzzy community affiliation of each camera, that is, the affiliation coefficient of each camera to each community.

5. A COPRA-based subway station inspection route planning mechanism according to claim 4, characterized in that: The new membership coefficient of camera a is obtained by weighted average of the corresponding community membership coefficients of neighboring camera b, that is, the weight from camera a to camera b.

Images