A personnel identification monitoring system and method in a cable tunnel
A cable tunnel and personnel identification technology, which is applied in the field of monitoring equipment, can solve the problem of inability to track foreign personnel, identify foreign personnel who have not been fingerprinted, and cannot monitor foreign intrusion or intrusion without receiving a temporary label. people and other issues to achieve the effect of ensuring stability and safety
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0051] Personnel identification and monitoring system in the cable tunnel, including ARM10 processor and Megvii, Face++ face recognition module connected to the processor, C417M-D communication module, tracking module and D203S pyroelectric infrared sensor detection module;
[0052] Processor: Accept the trigger signal sent by the pyroelectric infrared sensor detection module, start the face detection module after receiving the trigger signal; accept the intrusion signal sent by the face recognition module, and start the tracking module after receiving the intrusion signal;
[0053] Face recognition module: collect images of cable tunnels, judge whether there is a face in the image, and when a face appears, perform face recognition to judge whether it is the face image of a tunnel worker, if it is a face image of a tunnel worker image, the module enters dormancy, if it is not a face image of a tunnel worker, the face recognition module sends an intrusion signal to the processor...
Embodiment 2
[0059] The difference between this embodiment and Embodiment 1 is that the face recognition module includes an image acquisition unit, a face detection unit, a feature extraction unit and a feature matching unit;
[0060] Image acquisition unit: collect video images in the tunnel, and send the video images to the face detection unit;
[0061] Face detection unit: detect whether there is a human face in the image collected by the image acquisition unit, and send the face image to the feature extraction unit;
[0062] Feature extraction unit: the feature extraction unit extracts the facial features of the face image to generate the feature vector of the face;
[0063] Feature matching unit: The feature vector extracted by the feature extraction unit of the machine is matched with the pre-entered facial feature vector of the tunnel worker, and the matching similarity result is output. When the similarity is greater than the set threshold, the face recognition module is controlled...
Embodiment 3
[0075] A method for identifying and monitoring personnel in a cable tunnel, comprising the following steps:
[0076] A. Install the pyroelectric infrared sensor detection module in the tunnel, set the trigger wavelength range of the pyroelectric infrared sensor detection module, connect the tracking module to the tunnel robot, and start the system;
[0077] B. The pyroelectric infrared sensor detection module continuously monitors the tunnel to determine whether there is an infrared source within the trigger wavelength range in the tunnel. When there is an infrared source within the trigger wavelength range, enter step C. If there is no trigger wavelength range When the infrared source inside, repeat step B;
[0078] C. The face recognition module starts, collects images in the tunnel, and judges whether the intruder is a tunnel worker. If it is a tunnel worker, go to step B. If not, go to step D;
[0079] D. The tracking module starts, and the tracking module controls the tu...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com