Target tracking and semantic segmentation method and device for sports video, and plug-in

Abstract

The invention discloses a target tracking and semantic segmentation method and device for a sports video and a plug-in. The method comprises the steps: extracting a feature map according to an input video frame and target initialization position information, and obtaining feature map information; positioning the target according to the feature map information to obtain target position information;performing feature fusion on the feature map information and the target position information, and filtering background information of a non-target area; and performing decoding operation according tothe fusion features and the feature map information, and finally forming a semantic mask of the target. The device comprises a backbone network encoder, a prediction network unit, a feature fusion network unit and a decoder. The plug-in comprises a video information assembly, a video preview assembly, a video playing assembly, a newly-built target assembly, a tracking adjustment assembly and a special effect assembly. According to the invention, the tracking precision in the sports video with the problems of target deformation, rotation, shielding and the like can be improved.

Description

Technical field[0001]The present invention relates to the technical field of computer vision, in particular to a method, device and plug-in for target tracking and semantic segmentation of sports videos.Background technique[0002]In recent years, the rapid development of the mobile Internet, especially the 5G industry, has given birth to a wide range of digital entertainment applications. Among them, the target tracking algorithm is widely used in the fields of video special effects editing, human-computer interaction, video surveillance, television broadcasting, autonomous driving and scientific analysis.[0003]Target tracking algorithm is a basic subject in the field of computer vision. Early tracking algorithms often search based on manually specified target features, or calculate optical flow to determine the displacement of the target. Tracking algorithms based on this idea tend to have high time complexity and poor robustness, so the application range is narrow. After that, the ...

AI Technical Summary

Problems solved by technology

[0006] Different from the data for general target tracking and semantic segmentation, sports videos have the following characteristics: the camera position of the video often overlooks the entire sports field from an oblique downward angle, and the length of the player is about 100 pixels, so low The resolution is easy to cause the failure of tracking and semantic segmentation; secondly, athletes on the field often wear two kinds of uniforms, and there will be a large number of similar-looking instances around the tracking target, which is a test of the ability of the tracking algorithm to distinguish; thirdly, due to the When playing and running on the field, there will be severe body movement, deformation, rotation, occlusion, camera lenses will also appear blurred, shaking, etc., the performance of existing algorithms will be significantly degraded in these scenarios

[0007] It is worth mentioning that existing algorithms often regard object tracking and video semantic segmentation as two independent modules, which limits their scope of use and also affects the speed of the entire process

Images