Behavior identification method based on recurrent neural network and human skeleton movement sequences

Abstract

The invention discloses a behavior identification method based on a recurrent neural network and human skeleton movement sequences. The method comprises the following steps of normalizing node coordinates of extracted human skeleton posture sequences to eliminate influence of absolute space positions, where a human body is located, on an identification process; filtering the skeleton node coordinates through a simple smoothing filter to improve the signal to noise ratio; sending the smoothed data into the hierarchic bidirectional recurrent neural network for deep characteristic extraction and identification. Meanwhile, the invention provides a hierarchic unidirectional recurrent neural network model for coping with practical real-time online analysis requirements. The behavior identification method based on the recurrent neural network and the human skeleton movement sequences has the advantages of designing an end-to-end analyzing mode according to the structural characteristics and the motion relativity of human body, achieving high-precision identification and meanwhile avoiding complex computation, thereby being applicable to practical application. The behavior identification method based on the recurrent neural network and the human skeleton movement sequence is significant to the fields of intelligent video monitoring based on the depth camera technology, intelligent traffic management, smart city and the like.

Description

technical field [0001] The invention relates to the technical fields of computer vision, pattern recognition and neural network, in particular to an end-to-end behavior recognition method based on human skeleton movement sequence by using a recursive neural network. Background technique [0002] With the development of artificial intelligence technology, intelligent robots, such as Google's unmanned cars, Baidu's unmanned bicycles, etc., will soon enter people's lives, as well as smart cities, intelligent transportation and intelligent monitoring fields, all of which require computers Automated analysis of human behavior. In recent years, depth camera technology combined with high-precision human skeleton estimation algorithms can provide skeleton motion information corresponding to the human body movement process, and accurate behavior recognition can be performed based on skeleton motion sequences. [0003] The current behavior recognition algorithm based on skeleton node...

AI Technical Summary

Problems solved by technology

[0003] The current behavior recognition algorithm based on skeleton nodes is mainly to design a classifier on the basis of manual feature extraction to realize behavior recognition, and the manual extraction of motion dynamic information is very troublesome, which is not conducive to practical application

Moreover, the training and testing of traditional methods are mostly carried out on small data sets. When the amount of data increases, the overall computational complexity will be unbearable for general hardware conditions, and it is difficult to play the role of skeleton-based behavior recognition in practical applications. value

Images