A Video-Based Pedestrian and Crowd Behavior Recognition Method

Abstract

The invention discloses a video-based pedestrian and crowd behavior recognition method. The whole framework includes a single-person limb part network, a single-person overall and limb joint network, and a multi-person network. The framework aims to jointly learn joint co-occurrence and temporal evolution in an end-to-end manner, by exploiting the ability of CNN global aggregation, the CNN model can be used simply and effectively to learn joint co-occurrence features of skeleton sequence information. In this method, the point-level features of each joint are learned independently, and then the features of each joint are regarded as channels of convolutional layers to learn hierarchical co-occurrence features. The most important thing is to use multi-part limb network features to integrate into single pedestrian motion features in the designed single pedestrian behavior recognition joint network structure to strengthen the behavior recognition of a single pedestrian. In addition, in the designed crowd interaction behavior recognition network, the characteristics of single-person behavior are used to strengthen the characteristics of group behavior. Group behavior involves the behavior of multiple people, such as hugging and shaking hands.

Description

technical field [0001] The invention belongs to the field of deep learning for extracting facial features by deep neural network, relates to technologies such as neural network and pattern recognition, and particularly relates to a training and testing method for pedestrian and crowd behavior recognition models based on human skeleton information. Background technique [0002] The analysis of human actions such as action recognition and detection is one of the fundamental and challenging tasks in computer vision. In the behavior recognition technology with the human body as the main research object, most motion recognition methods use the method of target segmentation, but limited by factors such as the number of human bodies in the image and the size of the target, the effect is not ideal, resulting in unsatisfactory follow-up recognition work . Therefore, many research works often omit the process of moving target detection, and directly extract behavioral features from t...

AI Technical Summary

Problems solved by technology

Interference factors such as illumination changes, camera motion, and target occlusion in real scenes make this type of behavior recognition method less robust and less accurate.

Images