Video motion recognition method based on fusion of sorting pooling and spatial features

Abstract

The invention provides a video motion recognition method based on fusion of sorting pooling and spatial features. The method comprises: on the basis of a video local feature descriptor algorithm, a basic visual feature vector set is extracted for each video; multi-scale segmentation is carried out on two-dimensional space for each frame of image in each video to construct a two-dimensional spatialpyramid model; video basic feature vector sets in each sub space in the pyramid model are arranged according to a frame sequence time sequence; smooth operation is carried out on an ordered basic feature vector sequence in each sub space independently; the ordered basic feature vector sequence after the smooth operation in each sub space is processed by using a sorting pooling algorithm and learning is carried out to obtain model parameters belonging to the sub space; the model parameters obtained in all sub space in the pyramid model are connected in series to obtain a feature vector as a final video feature vector; and a classifier is used for classifying the video feature vector and thus the motion type of the video is identified.

Description

technical field [0001] The invention relates to a video recognition technology, in particular to a video action recognition method based on sorting pooling and fusion of spatial features. Background technique [0002] Today's video action recognition technology has been widely used in multimedia content analysis, human-computer interaction, intelligent real-time monitoring and other fields. This technology can be realized by extracting video features to generate feature vectors, and classifying feature vectors with classifiers. In the traditional video action recognition method, the three-dimensional space-time domain of the video is usually taken as a whole to capture the dynamic change characteristics of the video. This approach is one-sided and will result in the loss of a large number of unique change characteristics belonging to the two-dimensional image space domain or the one-dimensional time series domain. Therefore, , the video action recognition technology needs to...

AI Technical Summary

Problems solved by technology

In the traditional video action recognition method, the three-dimensional space-time domain of the video is usually taken as a whole to capture the dynamic change characteristics of the video. This approach is one-sided and will result in the loss of a large number of unique change characteristics belonging to the two-dimensional image space domain or the one-dimensional time series domain. Therefore, , the video action recognition technology needs to process the temporal and spatial structure of the video separately in order to more comprehensively capture the temporal and spatial feature information in the dynamic change of the video. This paper proposes a video action recognition method based on sorting pooling fusion spatial features

Images