Posture-recognition-based method for human movement classification

Abstract

The invention discloses a posture-recognition-based method for human movement classification. The method comprises: step one, posture recognition is carried out on upper part movement of a human body to obtain skeleton characteristics capable of expressing locations, directions and sizes of all parts of the upper part of the human body; step two, normalization processing is carried out on the data in the skeleton characteristics obtained at the step one; step three, the skeleton characteristics after normalization processing are trained by using a multi-class SVM to obtain a classifier capable of classifying different motions; and step four, the classifier trained at the step three classifies input movements. An experiment is carried out by using collected human body movement pictures as testing data; and the experiment result demonstrates that the classification accuracy can reach 97.78% and the human body movements can be classified well.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a gesture recognition-based human action classification method. Background technique [0002] The rapid development of computer network technology and multimedia technology has created convenient conditions for the storage and transmission of massive visual information such as images, and people can obtain a large amount of picture information from the Internet. However, the increasing amount of data also makes it difficult for people to find the pictures they want. For the website, it is necessary to manage this large amount of picture information, classify the pictures, and build an index, so that users can easily obtain the required content. For the majority of users, it is also hoped that they can find the picture information they need quickly and effectively, so as to reduce unnecessary waste of time. Therefore, classifying pictures has important practical signifi...

AI Technical Summary

Problems solved by technology

In terms of feature expression based on visual capture technology, human body contours were initially used as pose feature expressions. However, contour features describe poses from an overall perspective, ignoring the details of each part of the body, and cannot accurately represent rich and colorful human poses.

Images