Target tracking method based on feature point matching

A technology of feature point matching and target tracking, which is applied in the field of signal tracking and can solve problems such as the inability to stably track non-rigid targets

Active Publication Date: 2015-07-15
BEIHANG UNIV
View PDF2 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of this, the embodiment of the present invention expects to provide a target tracking method based on feature point matching, which can at least solve technical problems such as the inability to stably track non-rigid targets in the prior art

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
  • Target tracking method based on feature point matching
  • Target tracking method based on feature point matching
  • Target tracking method based on feature point matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] This embodiment provides a target tracking method based on feature point matching, such as figure 1 As shown, the method described in this embodiment includes:

[0048] Step S101: decomposing the video into image frames to obtain an image frame sequence;

[0049] The external shape characteristics of non-rigid objects change with time. Therefore, it is necessary to decompose the video of non-rigid objects into image frames to obtain image frame sequences. The shape of the target (non-rigid body or other high-speed rotating object) in each image frame in the image frame sequence is different, but the difference between adjacent image frames is not large.

[0050] Step S102: Obtain feature point information of the target in the first image frame of the image frame sequence;

[0051] In order to track the target, it is first necessary to determine the target in the image frame. The usual way to determine the target is to mark the target's feature points and use it as th...

Embodiment 2

[0095] The present invention is described below through a specific scene.

[0096] It is relatively simple to decompose a video into a sequence of image frames, and this embodiment does not give too much description.

[0097]In this embodiment, whether it is tracking or detection, it starts from the feature points detected globally in the first image frame. We have corresponding numbers for all detected feature points in the first image frame, and track them in subsequent frames. The feature points on and the feature points on the detection matching also correspond to this number, assuming that some feature points of the k+1th image frame are obtained from the kth image frame through optical flow tracking, and these feature points have their own number (corresponding to the first frame), when calculating the angle, scale and position of the k+1 frame image frame target, find the feature point corresponding to the number in the first frame, and calculate the angle, scale and po...

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 discloses a target tracking method based on feature point matching. The method comprises the steps that a video is decomposed according to image frames to obtain an image frame sequence; feature point information of a target in a first image frame of the image frame sequence is acquired; shape information and location information of the target in the remnant image frames of the image frame sequence are determined according to the feature point information.

Description

technical field [0001] The invention belongs to the technical field of signal tracking, and in particular relates to a target tracking method based on feature point matching. Background technique [0002] Object tracking technology is one of the core topics in the field of computer vision, which has very important significance and extensive practical value. It integrates advanced technologies and research results in related fields such as image processing, pattern recognition, artificial intelligence, automatic control, and computer applications. In recent years, with the rapid development of target tracking technology, the requirements for algorithm stability and applicability are also increasing. The scenarios processed by algorithms are becoming more and more complex, and the targets are becoming more and more extensive. Traditional algorithms can no longer meet people's requirements. For non-rigid bodies and high-frequency rotating objects, the characteristics of unsta...

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 Applications(China)
IPC IPC(8): G06K9/00
Inventor 赵龙多靖贇刘振
Owner BEIHANG UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap