Tunnel intrusion object detection method and device
A technology for object detection and tunneling, applied in instruments, character and pattern recognition, computer parts, etc., can solve problems affecting the normal operation of the early warning system, false alarms, etc., to eliminate hidden safety hazards, accurate detection, and reduce the probability of misjudgment. Effect
Pending Publication Date: 2021-04-20
INST OF COMPUTING TECH CHINA ACAD OF RAILWAY SCI +2
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the frequent passage of rail vehicles in the tunnel and irregular construction by maintenance personnel, the tunnel environment will change, so the existing background difference method will cause a large number of false alarms and seriously affect the normal operation of the early warning system.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0046] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention , but not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0047] figure 1 It is a schematic flowchart of the tunnel intrusion object detection method provided by the present invention. refer to figure 1 , the tunnel intrusion object detection method provided by the present invention may include:
[0048] S110. Process key frames of the tunnel surveillance video based on a lightweight feature extraction network to extract multi-scale feature maps ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a tunnel invasion object detection method and device. The method comprises the steps of processing a key frame of a tunnel monitoring video based on a lightweight feature extraction network to extract a multi-scale feature map of the tunnel monitoring video; processing the multi-scale feature map based on a multi-scale feature fusion network to obtain rail vehicle and pedestrian information in the multi-scale feature map; processing the key frame based on a background difference algorithm to obtain position information of a moving object; and according to the rail vehicle and pedestrian information and the moving object position information, determining whether an invasion object exists in the tunnel. According to the tunnel invasion object detection method and device, the tunnel invasion object can be accurately detected, the misjudgment probability of the invasion object in the tunnel is greatly reduced, and a guarantee is provided for rapidly eliminating potential safety hazards in the tunnel.
Description
technical field [0001] The invention relates to the technical field of rail transit safety, in particular to a method and device for detecting tunnel intrusion objects. Background technique [0002] For railway tunnels built between steep mountains, they are vulnerable to geological disasters. Once a safety accident occurs, it will be extremely difficult to rescue, which will seriously threaten the safety of tunnel traffic and passengers. [0003] Due to the suddenness and unpredictability of tunnel disasters, regular manual maintenance and safety inspection measures can no longer meet the current safety needs. With the rapid development of computer vision and artificial intelligence, there have been researches based on intelligent video analysis technology instead of manual detection and judgment of intruding foreign objects. [0004] At present, the method of background difference is commonly used to analyze the monitoring video of the tunnel. However, due to the frequen...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/00G06K9/46G06K9/62
Inventor 杨恩泽刘玉鑫刘硕研方凯王明哲李超王瑞徐成伟关则彬李隆胡昊李洵张煜山樊楠金久强
Owner INST OF COMPUTING TECH CHINA ACAD OF RAILWAY SCI