Tracking method and tracking device for image feature points

Abstract

The invention relates to an image feature point tracking method and a device. The method comprises the following steps: determining a polar line projected by a target feature point in a second image;acquiring a first gray value of a start tracking point located on the polar line; acquiring a second gray value and a gray gradient value of the target feature point; in accordance with a first gray value, the second gray value and the gray gradient value tracking the position of the target feature point in the second image in the direction of the polar line, combined with the gray value of targetfeature points, the gray level gradient value and the gray level value of the initial tracking point tracking the target feature points in the polar direction, which can increase the number of feature points successfully tracked, improve the robustness and stability of tracking target feature points, and reduce the tracking range of feature points to the polar direction, which simplifies the feature point tracking model, shortens the tracking time, improves the tracking efficiency and provides more effective data support for the subsequent image information processing such as machine vision.

Description

Technical field [0001] The present invention relates to the technical field of image processing, in particular to a method for tracking image feature points, a device for tracking image feature points, computer equipment and computer-readable storage media. Background technique [0002] In computer vision systems, it is often necessary to process images, especially to identify and track objects in the images. One of the commonly used implementation methods is to extract some stable and robust pixels in each image as the characteristic pixels of the image, and then use target tracking algorithms such as optical flow to measure these characteristic pixels between different images. Perform match tracking. [0003] However, when traditional target tracking algorithms track image feature pixels, it is easy to cause the feature pixels to have a low matching degree in the target image, which reduces the robustness of tracking image feature pixels. The point tracking time is too long, wh...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to provide a tracking method for image feature points, a tracking device for image feature points, computer equipment, and a computer-readable storage medium for the problem of low robustness of tracking image feature pixels in traditional technologies.

Images