Perspective-independent behavior recognition method based on deep learning network

Abstract

The present invention proposes a view-independent behavior recognition method based on a deep learning network, which includes the following steps: input a video frame image under a certain view, and use deep learning to extract and process bottom-level features; Modeling, the cube model is obtained in chronological order; the cube model of all views is converted into a view-invariant cylinder feature space map, and then input into the classifier for training to obtain a video behavior view-independent classifier. The technical solution of the present invention uses a deep learning network to analyze human behavior under multiple perspectives, which improves the robustness of the classification model; it is especially suitable for training and learning based on big data, and can give full play to its advantages.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a view-independent behavior recognition method based on a deep learning network. Background technique [0002] With the rapid development of information technology, computer vision has ushered in the best development period with the emergence of concepts such as VR, AR and artificial intelligence. As the most important video behavior analysis in the field of computer vision, it has also been increasingly recognized by domestic and foreign scholars. favor. In a series of fields such as video surveillance, human-computer interaction, medical care, and video retrieval, video behavior analysis occupies a large proportion. For example, in the popular self-driving car project, video behavior analysis is very challenging. Due to the complexity and diversity of human body movements, coupled with the influence of human body self-occlusion, multi-scale, viewing angle rotation, an...

AI Technical Summary

Problems solved by technology

[0006] The behavior analysis method based on spatio-temporal feature points and skeleton information has achieved remarkable results in the traditional single-view or single-person mode, but it is not suitable for areas with relatively large pedestrian traffic such as streets, airports, and stations, or human body occlusion and light changes. The emergence of a series of complex problems such as , viewing angle transformation, etc., the simple use of these two analysis methods often fails to meet people's requirements in real life, and sometimes the robustness of the algorithm is also very poor

Images