Method and device for tracking image feature points, computer equipment and storage medium

Abstract

The invention relates to the technical field of computer vision, and provides a method and device for tracking image feature points, computer equipment and a storage medium. According to the invention, the robustness of tracking the image feature points can be improved. The method comprises the following steps: obtaining two adjacent frames of images, determining to-be-tracked image feature pointson the previous frame of image and a plurality of candidate tracking points in a tracking area of the next frame of image, acquiring feature data of feature points of the image to be tracked from a first feature map corresponding to the front frame image; and obtaining feature data of a plurality of candidate tracking points from the second feature map corresponding to the rear frame image, and obtaining a tracking result of the feature point of the image to be tracked on two adjacent frames of images based on feature comparison between the feature data of the feature point of the image to betracked and the feature data of the plurality of candidate tracking points.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular to a method, device, computer equipment and storage medium for tracking image feature points. Background technique [0002] In the field of computer vision technology, image feature point detection and matching have a wide range of applications, such as image registration, image retrieval, 3D reconstruction and visual SLAM (Simultaneous Localization and Mapping, simultaneous positioning and mapping), etc. Among them, the feature points of the image generally refer to the pixel points with obvious texture features in the image and easy to match and track in the continuous image sequence; the visual SLAM system is a kind of camera that can locate the moving position of the camera during the movement of the camera. A system that builds a map of the scene passed by the trajectory of the motion. [0003] The processing of image feature points generally includes two asp...

AI Technical Summary

Problems solved by technology

[0004] However, the solutions for tracking image feature points provided by traditional technologies are mainly based on the analysis of manually designed features, usually only low-level features are used, and they are sensitive to image noise, light changes and other adverse factors. The technical problem of low robustness of feature point tracking. At the same time, this technology requires a large computational burden on computer equipment, which is difficult to meet the application requirements of real-time low power consumption.

Images