Human body behavior identification method adopting non-supervision multiple-view feature selection

Abstract

The invention discloses a human body behavior identification method adopting non-supervision multiple-view feature selection. The method includes the steps that firstly, a plurality of types of visual feature expression are extracted from sets of video data, including different human body behavior types, collected in advance to acquire a multi-view feature data matrix; then, in terms of each view, a visual sense similarity graph and a geometric Laplacian matrix which are related to the corresponding view are built so as to build a target function for solving a multi-view feature selection matrix and solving a data clustering type matrix; the multi-view feature selection matrix is optimized and calculated through the iteration gradient descent method, and a two-value feature selection matrix is acquired according to the line sequencing result of W; finally, video data to be identified are converted into corresponding multi-view feature data, distances between data to be identified after feature selection and multi-view feature data collected in advance are compared, and a video to be identified is identified as the human body behavior type in the jth video data collected in advance, wherein j is the serial number of video data, corresponding to the minimum distance of each list of multi-view feature data, collected in advance. The method is high in calculation speed and has high identification accurate rate and noise and interference resistance ability.

Description

technical field [0001] The present invention relates to the subjects of unsupervised learning, multi-view learning, feature selection and human behavior recognition in machine learning and computer vision research, and in particular to a human behavior recognition method for unsupervised multi-view feature selection. Background technique [0002] With the rapid improvement of modern computer computing performance and the development of computer vision technology, especially feature extraction technology, people will extract different types of visual feature expressions for video and image processing objects. For example, for images, global features, such as color histograms, texture features, and contour features, and local features, such as SIFT, LBP, and GLOH, are often extracted. For video objects, in addition to appearance features (such as color, texture, edge) and motion features (such as motion history map and motion energy map features), local moment features (such a...

AI Technical Summary

Problems solved by technology

Therefore, when performing feature selection, traditional feature selection methods cannot give full play to the advantages of multi-view features.

[0005] On the other hand, in the research of video-based human behavior recognition, although various types of visual features have been continuously proposed, how to combine and apply multiple features has also been researched and discussed in some literatures, but for There are relatively few studies on how to perform fast and effective feature selection among multiple features.

Images