Behavior identification method based on multi feature fusion

Abstract

The invention discloses a behavior identification method based on multi feature fusion. The behavior identification method comprises the steps that S1, preprocessing is carried out on videos of a training set and a test set; S2, feature point detection is carried out on the videos which are preprocessed in the step of S1; S3, descriptors which represent different information is extracted from feature cubes in the videos, so as to form comprehensive descriptors; S4, the descriptors, which are extracted in the step of S3, of the training set are used, and a K-SVD algorithm is used to train a dictionary; and S5, feature fusion is carried out on the descriptors, which are extracted in the step of S3, of the test set, and classification is carried out through a cascade dictionary classification algorithm. According to the invention, multi feature fusion is carried out on energy information, spatial information and time information; essential motion features are abstracted; comprehensive descriptor information extracting is realized; and the system robustness is great.

Description

technical field [0001] The invention relates to the technical field of image recognition and processing, in particular to a behavior recognition method based on multi-feature fusion. Background technique [0002] In the field of computer vision, behavior recognition has increasingly high application value in the field of intelligent video surveillance with the development of human motion analysis. However, due to: 1) the environment of data collection is complex and diverse, the behavior sequence background segmentation technology is not perfect; 2) on the time scale and spatial scale, the same behavior or similar behavior usually have different meanings; 3) due to the classifier The learning ability of the video is limited and several methods of interest point extraction have advantages and disadvantages, so the same video behavior is judged as belonging to several categories at the same time. All these factors make human action recognition a very challenging research fiel...

AI Technical Summary

Problems solved by technology

However, due to: 1) the environment of data collection is complex and diverse, the behavior sequence background segmentation technology is not perfect; 2) on the time scale and spatial scale, the same behavior or similar behavior usually have different meanings; 3) due to the classifier limited learning ability and several methods of interest point extraction have advantages and disadvantages, so it often happens that the same video behavior is judged to belong to several categories at the same time

All of the above factors make human action recognition a very challenging research field.

Images