Personnel violation behavior identification model training method, personnel violation behavior identification method and computer equipment

Abstract

The invention discloses a personnel violation behavior identification model training method, a personnel violation behavior identification method and computer equipment. The model training method mainly comprises the following steps: carrying out global semantic expression of video clips on local spatial-temporal features and human body posture features of training set samples; based on global semantic expression training of the video clips, obtaining first multi-classifiers of which the number is equal to that of the feature types; sending the verification set sample into multiple classifiersto obtain corresponding three-dimensional probability score matrixes, generating an evidence source of a DS evidence theory of each behavior category according to each three-dimensional probability score matrix, and calculating an identification sensitivity weight vector of each feature belonging to each behavior category in combination with a preset evidence synthesis strategy; performing globalsemantic expression of the video clips on the local spatial-temporal features and the human body posture features of all the video samples, and performing training based on the global semantic expression of the video clips to obtain a second multi-classifier; and constructing a personnel violation behavior identification model according to the identification sensitivity weight vector and the second multi-classifier.

Description

technical field [0001] The invention relates to the technical field of behavior recognition, in particular to a method for training a personnel violation behavior recognition model, a recognition method and computer equipment. Background technique [0002] In view of the urgent needs of behavior recognition technology in the fields of industrial and agricultural production, people's life, and national defense technology, experts and scholars at home and abroad have proposed many effective implementation plans for related difficult problems. Current behavior recognition methods can be divided into methods based on handcrafted features and methods based on deep learning according to different feature extraction methods. The former is committed to extracting robust behavioral features from videos, and completes the recognition task by training a classifier with strong discriminative properties. Considering the different sources of features, this type of method can be divided in...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a training method, a recognition method, and a computer device for personnel violation behavior recognition models, so as to solve the problem that the accuracy rate of behavior recognition of existing local spatiotemporal features is not very high

Images