Motion history image and convolutional neural network-based behavior identification method

Abstract

The invention discloses a motion history image and convolutional neural network-based behavior identification method. The method comprises the following steps of S1, obtaining an input original videoimage, and processing the input original video image through a motion history image-based behavior sequence feature extraction method; and S2, performing behavior identification on a local motion history image by adopting a deep convolutional neural network-based method to obtain a behavior type classifier, and finally outputting a behavior identification result through the behavior type classifier. The motion history image is calculated in an original video sequence, so that the to-be-processed information amount is reduced and key time-space information in behavior identification is extracted; and by taking the motion history image as an input, a deep convolutional neural network is established, then the network is trained by utilizing a stochastic gradient descent method and a Dropout policy, and finally behavior type identification is realized. The method can be effectively applied to online real-time behavior identification.

Description

technical field [0001] The invention relates to the field of behavior recognition, in particular to a behavior recognition method based on motion history images and convolutional neural networks. Background technique [0002] Human behavior recognition technology based on computer vision is widely used in robotics, video surveillance, virtual reality and other fields. The methods to solve human behavior recognition problems are mainly divided into traditional algorithms and recognition algorithms based on deep learning. The traditional algorithm uses the method of "feature extraction and expression + feature matching" to recognize human behavior, while the recognition algorithm based on deep learning learns the characteristics of the object through the neural network and directly outputs the final recognition result. At present, a lot of research focuses on improving the accuracy rate, ignoring the real-time nature of the algorithm, and in various practical applications, the...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to solve the defect that the accuracy of behavior recognition using traditional feature descriptors as a feature expression method in the prior art is low, and that directly using the original video as the input of the neural network will bring about a decrease in algorithm speed, and provide A behavior recognition method based on motion history images and convolutional neural networks. The present invention uses a deep learning method based on the adjusted AlexNet network for behavior recognition to improve the accuracy of the algorithm, and uses motion history images as the input of the neural network to improve the accuracy of the algorithm. algorithm speed

Images