A detection method for abnormal crowd density in train carriages

Abstract

The invention discloses a train carriage abnormal crowd density detection method. The method includes the following steps that a plurality of carriage sample images with different crowd density grades are collected, and multimodal fusion characteristics of the images are obtained; a crowd density classifier is obtained through training; multimodal fusion characteristics of an image to be detected are obtained; according to the crowd density classifier, the crowd density grade of a carriage corresponding to the image to be detected is obtained, and accordingly whether the crowd density in the carriage is abnormal or not is judged; abnormal information of related crowd density is recorded automatically. According to the method, the multimodal fusion characteristics are used, abnormal crowd density scenes are learned and identified automatically, and therefore abnormal crowd density can be identified and recorded automatically in a real-time mode in the running process of a train. The method is insensitive to train scene crowd shielding, illumination and slight deformation of a camera, and is suitable for train abnormal crowd density detection through 360 cameras or bolt cameras.

Description

technical field [0001] The invention belongs to the technical field of video processing, and in particular relates to a method for automatically and real-time analyzing whether there is an abnormal crowd density based on the video of a train carriage. Background technique [0002] At present, almost all subway trains in China are equipped with video image monitoring systems. When the train is running, the video surveillance system automatically records the condition of the carriage and stores the relevant video. The current situation of train monitoring is: the daily passenger flow of subway trains varies greatly at different time periods, the train carriages are relatively closed, the environment inside the train carriages is relatively complex, video image acquisition is limited, the light changes rapidly according to environmental conditions, and the camera has 360° Cameras and bolt-action cameras have a large amount of image data storage. The video data volume of a trai...

AI Technical Summary

Problems solved by technology

However, when the crowd density reaches medium-to-high density for a single texture feature, the ability to distinguish the crowd density is significantly reduced, the judgment accuracy is low, and a large number of training samples is required to obtain appropriate results.

However, the train carriages may be commuting, commuting, or for a certain period of time, and the crowd density is at a medium-to-high density for a long time. At this time, it is difficult to detect abnormalities.

Images