Group behavior identification method based on pseudo 3D convolutional neural network

Abstract

The invention discloses a group behavior recognition method based on a pseudo 3D convolutional neural network. The group behavior recognition method comprises the following steps: (1) carrying out human body posture estimation and target tracking by utilizing an OpenPose posture estimation algorithm; (2) extracting spatial and temporal features of each person by using a P3D ResNet (pseudo 3D residual network), and classifying the spatial and temporal features by using a softmax classifier to complete single person behavior recognition; (3) constructing a human body target interaction graph byutilizing the position information and the appearance characteristics of the human body target, and performing graph reasoning and training by utilizing a graph convolution network; and (4) performinggroup behavior identification according to the human body target interaction graph. According to the scheme, features are extracted based on a P3D convolutional network; parameters of the model are reduced and identification precision is improved. Through the technology, a computer can judge the state change of the interested human body target in the public area in real time, automatic human bodybehavior recognition is carried out, the recognition precision is high, and the application field is wide.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a group behavior recognition method based on a pseudo 3D convolutional neural network. Background technique [0002] With the continuous development of hardware technology, surveillance cameras are ubiquitous, such as airports, supermarkets, banks, hospitals, schools and other public places; in the face of such a large-scale camera surveillance network, relying solely on manpower is no longer capable of monitoring video. a job. Group behavior recognition is an important research content in the field of computer vision, which is mainly used in the fields of intelligent monitoring system, video retrieval and human-computer interaction; For activities completed by individuals, group behavior recognition methods are divided into two methods based on graph models and graph-free models. [0003] There are various schemes for group behavior recognition in the prior...

AI Technical Summary

Problems solved by technology

[0008] The present invention proposes a group behavior recognition method based on a pseudo 3D convolutional neural network to solve the problem of poor group behavior recognition accuracy in video surveillance, and to judge the state changes of interested human targets in public areas in real time and perform automatic human body detection. Behavior recognition provides technical support

Images