Human movement identification method through fusion of deep neural network model and binary system Hash

Abstract

The present invention provides a human movement identification method through fusion of a deep neural network model and binary system Hash, belonging to the technical field of mode identification. Themethod comprises the steps of: performing preprocessing of a movement identification database, dividing the movement identification database into frame sequences, calculating an optical flow graph, employing an attitude estimation algorithm to calculate coordinates of human joint points, and employing result coordinates to extract video area frames; employing a pre-training VGC-16 network model to extract FC (Full-Convolutional) features of RGB flows and optical flows of the videos, selecting key frames from the video frame sequences, and obtaining a difference of the FC features corresponding to the key frames; performing binary processing of the difference; employing a binary-hashing method to obtain uniform feature expression of each video; employing a plurality of normalization methods such as L1 and L2 to obtain feature expressions of the videos after the fusion of the uniform feature expressions and the PCNN features; and finally, employing a support vector machine algorithm totrain a classifiers to identify the human movement videos. The human movement identification method through fusion of the deep neural network model and the binary system Hash has a high movement identification correct rate.

Description

Technical field [0001] The invention belongs to the technical field of image and video processing, and particularly relates to a human body action recognition method based on a deep neural network model combined with binary hash. Background technique [0002] In recent years, human action recognition has made great progress in the field of pattern recognition, image processing and analysis, and some human action recognition systems have been put into practical use. Human action recognition algorithms mainly include two steps: action representation and action classification. How to encode human action information is a very critical step for subsequent action classification. Ideally, the action representation algorithm must not only change the appearance, scale, complex background, and action speed of the human body, but also contain enough information to provide the classifier to classify the action types. However, the complex background and the variability of the human body have...

AI Technical Summary

Problems solved by technology

Obviously, using a single frame is not enough to effectively capture the dynamics of the action, and a large number of frames requires a large number of parameters, which leads to model overfitting, requires a larger training set, and has higher computational complexity.

Images