Infrared behavior identification method based on adaptive fusion of artificial design feature and depth learning feature

Abstract

The invention relates to an infrared behavior identification method based on adaptive fusion of an artificial design feature and a depth learning feature. The method comprises: S1, improved dense track feature extraction is carried out on an original video by using an artificial design feature module; S2, feature coding is carried out on the extracted artificial design feature; S3, with a CNN feature module, optic flow information extraction is carried out on an original video image sequence by using a variation optic flow algorithm, thereby obtaining a corresponding optic flow image sequence; S4, CNN feature extraction is carried out on the optic flow sequence obtained at the S3 by using a convolutional neural network; and S5, a data set is divided into a training set and a testing set; and weight learning is carried out on the training set data by using a weight optimization network, weight fusion is carried out on probability outputs of a CNN feature classification network and an artificial design feature classification network by using the learned weight, an optimal weight is obtained based on a comparison identification result, and then the optimal weight is applied to testing set data classification. According to the method, a novel feature fusion way is provided; and reliability of behavior identification in an infrared video is improved. Therefore, the method has the great significance in a follow-up video analysis.

Description

technical field [0001] The invention belongs to the technical field of image processing and computer vision, and relates to an infrared behavior recognition method based on adaptive fusion of artificial design features and deep learning features. Background technique [0002] In recent years, behavior recognition in images and videos has become an important task in the field of computer vision. Behavior recognition in videos is of great significance to video surveillance, video information retrieval, and human-computer interaction. As various behavior recognition algorithms continue to refresh the recognition accuracy of various public data sets, the behavior recognition task in videos has made great progress. However, most of the current datasets are based on visible light video, and there are relatively few behavior recognition works based on infrared video. [0003] The current mainstream behavior recognition algorithms mainly involve two types of descriptors: artificial...

AI Technical Summary

Problems solved by technology

[0005] However, at present, there are relatively few researches on behavior recognition based on infrared video. In video surveillance work, if encountering rain, fog and other bad weather with low visibility or nighttime conditions, visible light video surveillance will lose its meaning.

Images