Behavior recognition method and device and computer storage medium

Abstract

The invention discloses a behavior recognition method and device and a computer storage medium. The method comprises the following steps of: acquiring a to-be-identified image, and inputting the to-be-identified image into a pre-trained neural network; obtaining outputs of the neural network, wherein the outputs comprise a first output representing the probability that a character behavior is normal in the to-be-recognized image, a second output representing the probability that the character is performing a first behavior, and a third output representing the probability that the character isperforming a second behavior; and determining the behavior of the person according to the outputs. Visibly, according to the embodiment of the invention, the behavior of the person in the to-be-identified image can be determined by using the pre-trained neural network, and specifically, the neural network can extract rich visual features and can pay attention to the specific behavior of the personin the to-be-identified image, so that the accuracy of behavior identification is higher. Moreover, the behavior recognition method provided by the embodiment of the invention can meet the real-timerequirement, and can perform real-time operation, thereby meeting the recognition requirements of various different application fields.

Description

technical field [0001] Embodiments of the present invention relate to the field of image processing, and more specifically, relate to a method, device and computer storage medium for behavior recognition. Background technique [0002] Behavior recognition can refer to a technology that analyzes and recognizes human behavior. For example, it is possible to analyze and identify human behavior in images (for example, video frame data). This technology can extract relevant frame data from video sequences and extract rich visual features, so as to analyze human behavior. express and explain. [0003] In the field of artificial intelligence (AI), behavior recognition has a very wide range of applications in many aspects such as video surveillance and automatic driving. For example, in the field of driving, there are many traffic accidents caused by drivers’ distracted behaviors. In order to reduce the accident rate, behavior recognition technology can be used to detect drivers’ ...

AI Technical Summary

Problems solved by technology

[0004] However, due to the influence of many factors, the accuracy and robustness of current behavior recognition cannot fully meet the requirements in the application field.

Images