Urban rail transit gate passing control method based on binocular camera behavior detection

Abstract

The invention discloses an urban rail transit gate passing control method based on binocular camera behavior detection. Gate machine installation and monitoring channel number calibration are carriedout through a binocular camera. performing internal and external parameter calibration and three-dimensional reconstruction of the camera; Passenger passing behavior data acquisition and preprocessing, passenger passing behavior data acquisition and preprocessing, motion area detection, moving object gait feature extraction, time sequence analysis model training and inspection, time sequence analysis model updating and real-time passenger passing behavior detection and identification are carried out, and real-time detection, identification and response to passenger passing behaviors are realized. Meanwhile, changes of camera parameters and classification labels are responded in time, parameters of the time sequence analysis model are trained and updated, the recognition accuracy and the control effectiveness are improved, the user experience in the technical field of rail transit intelligence is greatly improved, and actual requirements are met.

Description

[0001] Field [0002] The invention relates to the technical field of urban rail transit intelligence, in particular to a method for controlling access of urban rail transit turnstiles based on binocular camera behavior detection. Background technique [0003] With the rapid development of the rail transit industry, the use of traffic gates is becoming more and more extensive. At present, the gates in the domestic and foreign markets are mainly scissor doors / flapping gates with more than 16 sets of cross-beam sensors for traffic logic control. Type gates, the design mainly includes: pedestrian shape detection, object occlusion detection, luggage detection, passing speed detection, delay detection, etc., and there are deceptive detections such as intrusion detection and tailgating detection. The control method, the number of sensors, the layout of the sensors, and the sensitivity of the sensors will all affect the execution effect of the algorithm, and continuous optimization i...

AI Technical Summary

Problems solved by technology

[0006] The present invention is aimed at the lack of logical control of gates in and out of stations by rail transit operations in the prior art, and provides an urban rail transit gate traffic control method based on binocular camera behavior detection. Machine installation and monitoring channel calibration, camera internal and external parameter calibration and 3D reconstruction, passenger traffic behavior data collection and preprocessing, passenger traffic behavior data collection and preprocessing, motion area detection, moving object gait feature extraction, time series analysis model training and Inspection, time series analysis model update and real-time passenger traffic behavior detection and identification, to realize real-time detection, recognition and response to passenger traffic behavior; at the same time respond to changes in camera parameters and classification labels in a timely manner, train and update time series analysis model parameters, improve It improves the accuracy of recognition and the effectiveness of control, greatly improves the user experience in the field of rail transit intelligent technology, and meets the actual needs

Images