A Complex Behavior Recognition Method Based on Video Basic Unit Analysis

Abstract

The invention discloses a complex behavior recognition method based on video basic unit analysis. This method splits video behavior recognition into temporal atomic behaviors, spatially extracts object and background information in the video based on target detection and scene recognition, and sends the extracted semantic information to a temporal model for analysis. Compared with the previous video behavior recognition, this method decomposes the video into basic tasks in time and space for detection and recognition, which is more interpretable. At the same time, based on this method, the required basic unit information can be selectively extracted for different task situations, and the flexibility of complex behavior recognition tasks is enhanced through the method of splitting.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a complex behavior recognition method based on video basic unit analysis. Background technique [0002] Understanding human behavior from video is a fundamental research problem in the field of computer vision. It has broad application prospects in human-computer interaction, video recommendation, etc. [0003] The current behavior recognition is mainly divided into two methods, the behavior recognition method based on skeleton points and the behavior recognition method based on video. The behavior recognition method based on skeleton points can reduce the interference of the external environment, but it lacks the interaction information with the environment and objects, so the recognition rate in complex scenes is limited. Video-based behavior recognition methods include two-stream methods and 3DCNN methods. The above methods can extract complex semantic information, but are sus...

AI Technical Summary

Problems solved by technology

The behavior recognition method based on skeletal points can reduce the interference of the external environment, but it lacks interactive information with the environment and objects, so the recognition rate in complex scenes is limited.

Video-based behavior recognition methods, including two-stream methods, 3DCNN methods, the above methods can extract complex semantic information, but are susceptible to interference from surrounding complex environments, lighting and other information

Video-based behavior recognition method Because the information contained in the video is too complex, it is difficult to pay attention to the key information when performing video behavior recognition. At the same time, the same behavior of different people is complex and diverse, and the same behavior varies greatly within the same category.

Images