Human Action Recognition Method Based on Convolutional Neural Network Feature Coding

Abstract

The invention proposes a human action recognition method based on convolutional neural network feature coding, which mainly solves the problems of complex calculation and low accuracy in the prior art. The implementation plan is: use TV-L1 to obtain the video optical flow graph; respectively perform convolutional neural network, local feature accumulation encoding, dimensionality reduction and whitening processing, and VLAD vector processing from the video space direction and the optical flow action direction to obtain the spatial direction VLAD vector and Action direction VLAD vector; combine the two direction information of video space and optical flow action to obtain human action classification data, and then perform classification processing. The invention performs local feature accumulation encoding on the convolution features, which improves the recognition rate and reduces the amount of calculation when processing complex background data, and the features obtained by fusing video and optical flow VLAD vectors have higher robustness to environmental changes , can be used in areas such as residential areas, shopping malls, and confidential places to detect and recognize human movements in surveillance videos.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to human action recognition based on deep learning, specifically a method for human action recognition based on convolutional neural network feature coding, which can be used in areas such as residential areas, hotels, shopping malls, and confidential places. Human motion detection and recognition in surveillance video. Background technique [0002] With the rapid development of science and technology and the continuous improvement of people's living standards, people are paying more and more attention to safety issues in life. Nowadays, video surveillance equipment is becoming more and more popular, and video surveillance equipment is installed in many places such as residential quarters, hotels, parking lots, shopping malls, intersections, companies, and confidential places. As the scale of video surveillance equipment continues to expand, the demand for more intel...

AI Technical Summary

Problems solved by technology

The shortcomings of this method are that the calculation is large, resulting in slow speed, poor real-time performance, and the problem of trajectory drift.

The disadvantage of this method is that the time complexity is high, and it is easily affected by occlusion and human body differences, so the accuracy is not high, and it is suitable for the recognition of simple actions.

The disadvantage of this method is that the process is complex and is easily affected by occlusion and human body differences.

The existing human action recognition methods have high time complexity, large amount of calculation, poor real-time performance, and are easily affected by occlusion, light intensity changes and human body differences.

Images