Human action recognition method based on noise reduction automatic encoder and particle filter

Abstract

The invention belongs to the field of computer vision and specifically relates to a human action recognition method based on a noise reduction automatic encoder and particle filter. The human action recognition method randomly divides a to-be-sorted action video set into a training video set and a test video set, the training video set and the test video set are respectively used for calculating training tracks and test tracks of the action, distances between the training tracks and the test tracks are calculated, a track distance set is obtained and is inputted to a support vector machine, and a sort result of the action is obtained. According to the invention, the method has an advantage of substantial human action recognition effect, accuracy of action recognition can be effectively improved, and the method has certain robustness on shielding and view change and can further be used for human body abnormal behavior recognition in video monitoring.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a human action recognition method based on a noise reduction automatic encoder and a particle filter. Background technique [0002] Human action recognition is an important research direction of computer vision, pattern recognition, image processing and artificial intelligence. It has great application value and theoretical significance in the fields of human-computer interaction, intelligent monitoring and medical treatment. It mainly analyzes and processes moving image sequences containing people, extracts features, and classifies moving objects, so as to realize the recognition and understanding of human individual actions, interactions between people and between people and the external environment. [0003] In recent years, many action recognition methods based on human skeletons have been proposed. The basic principle of these methods is to use the key posture feat...

AI Technical Summary

Problems solved by technology

[0005] This method significantly improves the accuracy of action recognition, but due to the complex spatiotemporal features of bones, it is difficult to propose robust motion features, so more researchers are currently working on establishing effective models to extract features

On the other hand, if the skeleton data is inaccurate due to occlusion or perspective changes, it will also have a great impact on the recognition results

Images