Video-based behavior recognition method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a video-based behavior recognition method and device, electronic equipment and a storage medium. The method comprises the steps: determining an image sequenceof a to-be-recognized video; inputting the image sequence into a behavior recognition model to obtain a behavior recognition result output by the behavior recognition model, wherein the behavior recognition model is obtained by training based on a sample image sequence of a sample video and a sample behavior recognition result, the behavior recognition model is used for encoding the image features, the time features and the motion features of the continuous images in the image sequence to obtain the spatial-temporal features of the continuous images, and performing behavior recognition based on the spatial-temporal features of the continuous images, and the time features and the motion features are determined based on the image features of the continuous images. According to the method anddevice, the electronic equipment and the storage medium provided by the embodiment of the invention, while high-precision behavior recognition is ensured, the calculation amount of space-time featurecoding is reduced to a great extent, and the behavior recognition efficiency is improved.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a video-based behavior recognition method, device, electronic equipment and storage medium. Background technique [0002] With the enhancement of computer processing power, video-based behavior recognition technology emerges at the historic moment, and has broad application prospects in video surveillance, robotics and other fields. [0003] At present, most video-based behavior recognition methods are implemented based on Convolutional Neural Networks (CNN). Among them, 3D CNN can learn the spatial-temporal feature expression from the original video, but the calculation of the spatio-temporal feature expression has the problems of large amount of calculation and long inference time, which makes it difficult to put into practical application. Contents of the invention [0004] Embodiments of the present invention provide a video-based behavior recognition metho...

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a video-based behavior recognition method, device, electronic equipment, and storage medium to solve the problems of large computation and long reasoning time in existing video-based behavior recognition

Images