Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Characteristic point optimization method for three-dimensional reconstruction of video scene

A technology of video scene and 3D reconstruction, applied in 3D modeling, image data processing, instruments, etc., can solve the problems of poor accuracy and achieve the effect of improving accuracy

Inactive Publication Date: 2012-06-27
日照新睿招商发展有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the poor accuracy of the existing KLT feature point tracking method for 3D reconstruction of video scenes, the present invention provides a feature point optimization method for effectively improving the accuracy of 3D reconstruction of video scenes

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
  • Characteristic point optimization method for three-dimensional reconstruction of video scene
  • Characteristic point optimization method for three-dimensional reconstruction of video scene
  • Characteristic point optimization method for three-dimensional reconstruction of video scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described below in conjunction with the accompanying drawings.

[0038] refer to Figure 1 to Figure 3 , a feature point selection method during three-dimensional reconstruction of a video scene, comprising the following steps:

[0039] 1) Image sequence I(X, t ), where X represents the position of the i-th feature point, and the coordinates of X are ( , ), t Represents the ordinal number of the frame, and uses the KLT tracker to track the feature points. The time interval between two frames of data in the image sequence is set to be limited and small, the feature points only change in position, and the brightness remains unchanged, as follows:

[0040] (1)

[0041] in, represents the brightness of the feature point, X represents the position of the feature point, δ(X) represents the transformation function, Indicates the time interval:

[0042] δ( x ) The approximation is represented...

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 characteristic point optimization method for the three-dimensional reconstruction of a video scene, comprising the following steps: 1) in an image sequence I (X, t) of the video scene, X represents the position of the ith characteristic point, t represents the ordinal number of frames, and a Karhunen Loeve transform (KLT) tracker is used for tracking characteristic points; and 2) the direction of each tracked characteristic point between adjacent frames is calculated, a sine value is used for representing the vector direction theta, a mean value of the theta is calculated to determine the center c, and a threshold value a is set to eliminate vector directions with larger change; the absolute value of theta-c represents the absolute distance; when the absolute value of theta-c is less than or equal to a, a tracked data result of the KLT tracker is not changed; and when the absolute value of theta-c is larger than a, the tracking points are eliminated, therefore, the optimized characteristic points are obtained. The invention provides the characteristic point optimization method for the three-dimensional reconstruction of the video scene, which effectivelyimproves the accuracy.

Description

technical field [0001] The invention relates to the technical fields of image processing, computer vision, calculation method, mathematics, numerical method, video processing, three-dimensional reconstruction, etc., in particular to a method for determining feature points during three-dimensional reconstruction of video. Background technique [0002] In recent years, the problem of recovering structure from motion has been a very important problem in the field of computer vision, and many researchers have been engaged in solving this problem. 3D reconstruction from video is a very important problem. In recent years, 3D reconstruction has become more and more widely used, for example, aerospace vehicles, robot navigation, reconstruction of 3D models of sculptures and historical monuments, 3D animation and visual inspection, etc. The goal of this problem can be briefly described as follows. A video is obtained from a single camera for a scene of interest, and then we need to ...

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): G06T17/00
Inventor 陈胜勇王月辉汪晓妍
Owner 日照新睿招商发展有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com