Sub-pixel Object Tracking Method Based on Feature Matching

A sub-pixel level, feature matching technology, applied in the field of target tracking and image processing, can solve the problems of tracking loss and drift, and achieve the effect of fast tracking, reducing the amount of calculation, and improving the tracking accuracy.

Active Publication Date: 2021-04-06
INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this kind of method usually tracks the whole target. If it tracks a point in the target, it will often drift or even lose track.

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
  • Sub-pixel Object Tracking Method Based on Feature Matching
  • Sub-pixel Object Tracking Method Based on Feature Matching
  • Sub-pixel Object Tracking Method Based on Feature Matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035]In order to make the objects, technical solutions, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0036]figure 1 For the feature-matched sub-pixel level target tracking method provided by the present invention, according tofigure 1 As shown, the tracking method includes:

[0037]S101: Select the tracking point of the first frame image in the image of continuous transmission as a reference tracking point;

[0038]S102: The feature vector of the first frame image and the nth frame image are respectively obtained, and the feature vector of the first frame image is obtained, and the characteristic vector of the nth frame image is obtained, where N is greater than 1 natural number;

[0039]S103: Match the feature vector of the first frame image with the feature vector of the nth frame image to obtain a feature point pair;

[0040]S104: Estimate the feature point to estimate the conversion matr...

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

A sub-pixel-level target tracking method based on feature matching, including: selecting the tracking point of the first frame image as a reference tracking point in the continuously transmitted images; respectively processing the first frame image and the Nth frame image to obtain the first frame image The feature vector of a frame image and the feature vector of the Nth frame image, N is a natural number greater than 1; the first frame image is matched with the feature vector of the Nth frame image to obtain a pair of feature points; the pair of feature points is estimated to obtain Transformation matrix, perform dot multiplication between the transformation matrix and the reference tracking point to obtain a new tracking point, and complete the update of the tracking point. The sub-pixel-level target tracking method based on feature matching proposed by the present invention can track a point in the target with high precision, and is robust when there are obvious changes in the image tracking point area; at the same time, the method is simple to calculate and can be parallelized High precision is beneficial for accelerated calculations, and can be widely used in high-speed and high-precision real-time tracking photoelectric countermeasure systems.

Description

Technical field[0001]The present invention relates to the field of image processing, and the objectual tracking technology, and more particularly to a feature-based high-precision target tracking method.Background technique[0002]Target Tracking has been a popular research direction of academic research and practical application in the past few decades. At present, it is basically divided into gray and based on characteristic tracking methods. Based on the gray tracking algorithm is mainly divided into two types of template matching and clustering. These two types of target tracking methods are simple, and it is also suitable for real-time tracking, but often matches the error, and the robustness is poor. In the target method based on the characteristics, there is a problem that the online learning target tracking method is prone to drift, easy to degenerate, and is not good in real time. The target tracking method based on deep learning is the hotspots in this stage, high tracking a...

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): G06T7/246
CPCG06T2207/10016G06T2207/20164G06T7/246
Inventor 窦润江刘力源刘剑吴南健
Owner INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI
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