Object tracking method, system, and device based on appearance and depth features

Abstract

The invention belongs to the technical field of computer vision tracking, and specifically relates to a target tracking method, system, and device based on appearance features and depth features, aiming to solve the problem of low tracking accuracy caused by existing target tracking methods ignoring depth information of target scenes. The method of this system includes obtaining the target area and the search area of ​​the image of the tth frame of the target to be tracked according to the target position of the t-1 frame and the preset target size; extracting the target area and searching for the target area through the apparent feature and depth feature extraction network respectively. The apparent features and depth features of the area; based on the preset weights, the weighted average of the apparent features and depth features of the target area and the search area are respectively obtained to obtain their respective fusion features; according to the fusion features of the target area and the search area, through correlation The filter obtains the response graph of the target; the position corresponding to the peak value of the response graph is used as the target position of the tth frame. The invention extracts the depth information of the target scene and improves the precision of target tracking.

Description

technical field [0001] The invention belongs to the technical field of computer vision tracking, and in particular relates to a target tracking method, system and device based on appearance features and depth features. Background technique [0002] Object tracking is one of the most fundamental problems in the field of computer vision, and its task is to estimate the motion trajectory of objects or image regions in video sequences. Object tracking has a very wide range of applications in real-world scenarios, often as a component in a larger computer vision system. For example, autonomous driving and vision-based active safety systems both rely on tracking the location of vehicles, cyclists and pedestrians. In robotic systems, tracking objects of interest is a very important aspect of visual perception to extract high-level information from camera sensors for decision-making and navigation. In addition to robotics-related applications, object tracking is often used in auto...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above problems in the prior art, that is, in order to solve the problem that the existing target tracking method ignores the depth information of the target scene, resulting in low tracking accuracy, the first aspect of the present invention proposes a target based on appearance features and depth features. The method of tracking, which includes:

Images