Human action recognition method based on multi-feature motion-in-depth diagram

Abstract

The invention discloses a human action recognition method based on a multi-feature motion-in-depth diagram. The method specifically includes steps of (1), projecting all the frames of a depth video tofront, side and top orthogonal planes; (2), stacking the absolute pixel differences of two continuous projection frames on each plane to form the motion-in-depth diagram (DMM{v=f, s and t}), and respectively extracting LBP characteristics, GIST characteristics and HOG characteristics to form characteristic descriptors corresponding the three directions; (3), using a relative entropy principal component analysis method to perform characteristic fusion and dimensionality reduction on the three different types of the characteristic descriptors; (4), calculating the sparse reconstruction errors of the characteristics of each type of action training samples under an l1 norm and an l2 norm after the fusion and dimensionality reduction, and using an entropy weight method to perform adaptive weighted fusion on the two types of reconstruction errors to design an error-fusion-based classifier for action recognition. By the method, the accuracy of human action recognition can be improved.

Description

technical field [0001] The invention belongs to the fields of artificial intelligence and pattern recognition, and in particular relates to human body behavior recognition based on multi-feature depth motion maps. Background technique [0002] Human behavior recognition has been widely used in abnormal behavior analysis, intelligent monitoring, and home security. Human action recognition has been an active research area in the past few decades, and the research mainly focuses on RGB video image sequences. For example: because the spatio-temporal interest points have the characteristics of rich motion information, in the three-dimensional space-time space, the Harris detector is used to detect the interest points in the three-dimensional space-time space, use the interest points to describe the action and identify the behavior; by tracking the optical flow of each frame sampling point Dense trajectory features formed by information have been widely used in human action recog...

AI Technical Summary

Problems solved by technology

[0007] b. Based on the depth motion map, the fusion features generated by fusing the depth motion maps of the three projection directions through the direct concatenation method are not only highly redundant, but also weak in describing local detail features;

[0008] c. Only a single sparse reconstruction error is considered for the classification of test samples, which can easily cause misidentification of similar behaviors (such as running and walking)

Images