TLD-based variable-scale target tracking method suitable for UAVs

A target tracking and target technology, applied in the field of computer vision and image processing, to achieve the effect of ensuring stability and high operating efficiency

Active Publication Date: 2017-06-23
中国航天电子技术研究院
View PDF6 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Based on the above problems, the present invention provides a target tracking method suitable for unmanned aerial vehicles based on the TLD framework, based on the characteristics and difficulties of unmanned aerial vehicle reconnaissan

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
  • TLD-based variable-scale target tracking method suitable for UAVs
  • TLD-based variable-scale target tracking method suitable for UAVs
  • TLD-based variable-scale target tracking method suitable for UAVs

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] A kind of target tracking method applicable to unmanned aerial vehicle based on TLD, described target tracking method is based on TLD algorithm, and described TLD algorithm comprises tracker, detector and learner; Described target tracking method comprises the following steps:

[0063] (1) Initialize tracker, detector and learner;

[0064] (2) The tracker generates a series of points to be tracked in the image, and first performs a pyramid optical flow tracking;

[0065] After the target tracking point is generated, the current frame is used as the initial frame, and the reverse tracking is performed;

[0066] Take the mean value of the position deviation between the position of all tracking points and the original tracking point as middleError, if the deviation between the position of the tracking point and the original tracking point>middleError, it is considered that the tracking is inaccurate, and the tracking points with accurate tracking are combined together, and...

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 belongs to the field of image processing and computer vision and particularly to a TLD-based variable-scale target tracking method suitable for UAVs. The method uses a design thought of a tracking-learning-detection (TLD) frame, uses a median optical flow tracker as a tracker, a normalized correlation detector as a detector, and an improved kNN detector as a learning device. Based on the characteristics and difficulties of a UAV detection video sequence, the TLD-based variable-scale target tracking method suitable for UAVs takes account of algorithm performance and adaptability, integrates the advantages of a median optical flow method and a correlation tracking algorithm, and solves the target robust tracking problem of the target tracking of a UAV video processing system when a target is given indefinitely, less pixels of the target to be tracked, unobvious texture, obvious target appearance attitude angle and scale changes, and tracking process real-time performance.

Description

technical field [0001] The invention mainly belongs to the fields of image processing and computer vision, and in particular relates to a TLD-based variable-scale target tracking method suitable for unmanned aerial vehicles. Background technique [0002] Target tracking technology is widely used in military UAV combat reconnaissance and precision strike fields, and also provides technical support for target positioning, damage assessment and other intelligence processing functions. The target tracking algorithm with strong accuracy and high robustness can effectively reduce the burden on ground operators and improve the rapid response combat capability and system detection capability. [0003] At present, in engineering applications, the correlation tracking algorithm is the most used. This algorithm is easy to implement in hardware, simple and effective, and has a considerable processing speed. However, the algorithm is not robust and cannot judge and capture target scale c...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/13G06F18/217G06F18/24
Inventor 黄坤吴国强徐翔尹中义许克鹏曲悠扬
Owner 中国航天电子技术研究院
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