Human movement significant trajectory-based video classification method

Abstract

The invention relates to a human movement significant trajectory-based video classification method. The human movement significant trajectory-based video classification method comprises the following steps that: a video set M is divided into a training set Mt and a test set Mv, and human movement information in each video is tracked in a multi-scale space by using SIFT and dense optical flow technologies, so that movement significant trajectories in each video can be obtained; feature description vectors of each trajectory are extracted; redundant information in the feature description vectors are eliminated through using a PCA method, and dimension reduction is performed on each class of feature description vectors; the feature description vectors in the training set Mt are clustered by suing a Gauss mixture model, and then, Fisher vectors of each video in the video set M are generated by using a Fisher Vector method; a linear SVM classification model is constructed on the training set Mt; and on the test set Mv, videos in the test set are classified through using the linear SVM classification model. Compared with the prior art, the human movement significant trajectory-based video classification method of the invention has the advantages of excellent robustness, higher computational efficiency and the like.

Description

technical field [0001] The invention relates to a video recognition method, in particular to a video classification method based on the significant trajectory of human motion. Background technique [0002] With the wide application of multimedia technology and computer network, a large amount of video data appears on the network. In order to effectively manage these video files and provide users with better experience services, it is becoming more and more important to automatically recognize human behavior in videos. [0003] Trajectory-based technology can effectively capture motion information in video, and has a very high ability to represent video features, so this technology has achieved relatively good experimental results on some video data sets. At present, the technology still has the following problems: [0004] First, human behavior in videos can be confused by background or camera motion. Especially camera motion will interfere with actual human motion inform...

AI Technical Summary

Problems solved by technology

However, when tracking motion trajectories, high sampling density will consume more CPU resources and increase the computational complexity of the algorithm

[0006] Third, in real life, the accuracy of human behavior recognition on videos is not high due to the large variance within human behavior categories

Images