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

Target tracking method based on deep transfer learning

A technology of transfer learning and target tracking, applied in image data processing, instrumentation, computing, etc., can solve problems such as accurate tracking and dependence of difficult targets

Active Publication Date: 2019-03-29
SHANGRAO NORMAL UNIV
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the shortcoming of this type of tracking method is that it relies heavily on a large number of training samples to fit the apparent data distribution of the target.
[0006] Therefore, the existing target tracking methods are difficult to achieve accurate tracking of the target

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 deep transfer learning
  • Target tracking method based on deep transfer learning
  • Target tracking method based on deep transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.

[0091] It should be noted that like numerals and let...

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 provides a target tracking method based on depth transfer learning, which relates to the technical field of data processing. The method includes two phases: off-line training and on-linetracking. In the offline training phase, based on the auxiliary image data, the transcendental structural feature information of the general target is obtained by using the depth convolution neural network. Then transfer learning is used to transfer the acquired prior structural feature information to the online tracking process. In the online tracking phase, a target tracking model based on depth transfer learning is established by combining the prior structural features, Haar features and image gray features obtained from off-line learning, and adopting the structure sparse representation and the dictionary template technology based on multi-subspace to obtain the final target tracking results. This method makes full use of the priori structural feature information of video image data and fuses the feature information acquired in the online tracking stage, which can reduce the drift problem of tracking and improve the robustness of target tracking.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular, to a target tracking method based on deep transfer learning. Background technique [0002] With the increase of high-performance computers and high-quality camera terminals, as well as the growth of demand for intelligent video analysis, visual target tracking technology has attracted more and more attention, and has been used in many fields of military and civilian (intelligent security systems, intelligent transportation systems, etc.) , precision guidance system, medical diagnosis, aerospace) and so on have extremely broad application prospects. [0003] The main process of visual target tracking is to process the video or image sequence, after performing feature extraction, target positioning, tracking detection and classification recognition on the target of interest, and finally obtain the position or motion parameters of the target. This information can be u...

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): G06T7/246
CPCG06T2207/10016G06T2207/20081G06T7/251
Inventor 刘金华吴姗任桂平徐信叶徐牡莲李永明
Owner SHANGRAO NORMAL UNIV
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