Attributive characteristic representation-based group behavior identification method

Abstract

The invention discloses an attributive characteristic representation-based group behavior identification method, and mainly solves the problems that in an identification process, preprocessing is complicated and later-period modeling is complicated. The identification process includes acquisition of a characteristic dictionary, acquisition of a video attribute vector and test video behavior prediction. The method includes: dividing an original video sequence into videos containing certain frames, dividing the videos into grid cubes, and extracting grid cube descriptors to obtain the characteristic dictionary; obtaining the descriptors of the videos according to the dictionary, calibrating an attribute vector of trained videos, obtaining an attribute classification model according to the trained videos, and predicting to obtain a test video attribute vector; and using the trained videos to learn and obtain classification models of different actions, and predicting the action type of test videos. The method neither needs to track a human body nor performs attitude estimation, thereby enabling group behavior identification to become simple and practical, and an identification effect is good at the same time, and thus the method has important application in video monitoring.

Description

Technical field [0001] The invention relates to the field of image processing and pattern recognition, in particular to a group behavior recognition method based on attribute feature representation. Background technique [0002] In recent years, due to the increasing demand for video supervision, human-computer interaction, and video-based content retrieval, human behavior recognition has gradually become one of the research hotspots in computational vision and pattern recognition. Current human behavior recognition algorithms are still focused on the recognition and understanding of standard postures and simple behaviors of the human body. In recent years, research on building human behavior models using machine learning tools has made certain progress. But now the recognition is better only on some simple behaviors. For complex group behaviors, there is no simple framework, low model complexity, and easy-to-implement methods. The future development trend is how to use advanced...

AI Technical Summary

Problems solved by technology

Kong Yu applied the attribute to the group behavior recognition method, although it has achieved good results, but it needs to track each person in the interaction behavior, which requires a lot of preprocessing work, and the identification used The model is very complex, parameter adjustment is cumbersome, and it is difficult to achieve real-time performance in practical applications, which will limit its application occasions

[0004] For complex group behavior recognition, the traditional method has the disadvantages of complex preprocessing and high model complexity.

Images