A feature point optimization method and system suitable for plane tracking

An optimization method and feature point technology, applied in the field of plane tracking, can solve problems such as inability to obtain stable tracking effect, difficulty in obtaining homography matrix, and affecting robustness, so as to achieve stable tracking, improve practicability, and reduce offset effect of error

Active Publication Date: 2022-07-12
GAODING XIAMEN TECH CO LTD +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the process of retrieving the tracking target, it is often encountered in the case of shaking, deformation, discoloration, etc. of the object in the plane, and it is difficult to obtain an accurate homography matrix, so that a stable tracking effect cannot be obtained, which affects its robustness

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A feature point optimization method and system suitable for plane tracking
  • A feature point optimization method and system suitable for plane tracking
  • A feature point optimization method and system suitable for plane tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to facilitate the understanding of those skilled in the art, the structure of the present invention will be further described in detail with reference to the accompanying drawings:

[0040] refer to figure 1 , a feature point optimization method suitable for plane tracking, including the following steps:

[0041] S1, the step of obtaining the area to be tracked: obtaining an initial video file, and obtaining the area to be tracked in a designated key frame of the initial video file; wherein the area to be tracked is an area selected by a user.

[0042] figure 2 is the initial frame to be tracked by this method. This method selects the upper half-life area of ​​the girl in the video as the plane to be tracked. In order to eliminate the interference of the background area, we only crop out the images in the area to prepare for subsequent feature extraction, because those areas The feature points of s are sparse or non-existent, and finally we get image 3 The...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a feature point optimization method and a system suitable for plane tracking, comprising the following steps: a step of obtaining an area to be tracked: obtaining an initial video file, and obtaining the area to be tracked in a designated key frame of the initial video file; A screening step: predict that the corner point of the i-1th frame image corresponding to the to-be-tracked area is at the corresponding corner point of the i-th frame, screen out the qualified pair of corner points, and calculate the first corner point according to the pair of corner points. A homography matrix; the second screening step: using the first homography matrix to perform positive operations on the corners of the i-1th frame image corresponding to the to-be-tracked area and inverse operations on the calculation results, and filter qualified Corner point pair; the third screening step: using the second homography matrix to perform a positive operation on the corner points of the i-1th frame image corresponding to the area to be tracked, and filter the first matching point pair to obtain a second matching Right.

Description

technical field [0001] The invention relates to the field of plane tracking, in particular to a feature point optimization method and system suitable for plane tracking. Background technique [0002] Plane-based visual tracking, referred to as plane tracking. When plane tracking is performed in a video, because the target area moves too fast between video frames, the tracking may fail, and the tracking target needs to be retrieved in time. [0003] However, in the process of retrieving the tracking target, the objects in the plane are often jittered, deformed, discolored, etc., and it is difficult to obtain an accurate homography matrix, so that a stable tracking effect cannot be obtained, which affects its robustness. [0004] Aiming at the above problems in the prior art, it is the purpose of the present invention to design a feature point optimization method and system suitable for plane tracking. SUMMARY OF THE INVENTION [0005] In view of the problems existing in t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/246G06T7/215
CPCG06T7/248G06T7/215G06T2207/10016
Inventor 曾锐林汉权林杰兴
Owner GAODING XIAMEN TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products