Target tracking method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a target tracking method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a first target frame of at least one target object in a current image frame of a target video; performing overlapping region marking on the first target frame to obtain a shielding condition of the first target frame; obtaining an optical flow tracking point set of the current image frame according to the shielding condition of the first target frame and the category of the target object; performing sparse optical flow calculationon the optical flow tracking point set to obtain a target tracking point corresponding to each optical flow tracking point in the optical flow tracking point set in a next image frame of the currentimage frame; and obtaining a second target frame of the target object in the next image frame according to the target tracking point. The embodiment of the invention is beneficial to improving the efficiency and effect of tracking multiple targets in the video.

Description

technical field [0001] The present application relates to the technical field of video object tracking, and in particular to an object tracking method, device, electronic equipment and storage medium. Background technique [0002] With the development of machine vision theory and technology, the recognition and understanding of video content has become a research hotspot, especially after the launch of video-based single target tracking related products, the demand for tracking multiple targets in video has become increasingly strong. Currently, there are many video-based target tracking methods, such as the method of associating targets in adjacent video frames according to physical indicators such as the distance from the target center point and the intersection ratio of the target area, but these methods are not applicable in some scenarios ; Moreover, the optical flow tracking method is widely used now, but it is mostly used to track a single target in a video image, and...

AI Technical Summary

Problems solved by technology

Currently, there are many video-based target tracking methods, such as the method of associating targets in adjacent video frames according to physical indicators such as the distance from the target center point and the intersection and union ratio of the target area, but these methods are not applicable in some scenarios ; Moreover, the optical flow tracking method is widely used now, but it is mostly used to track a single target in a video image, and the method of uniformly selecting tracking points will inevitably make the background pixels also be used as tracking points. It can be seen that , the current optical flow tracking method has poor tracking efficiency and the tracking effect is not significant when performing multi-target tracking

Images