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

Visual tracking failure detection system based on neural network and training method thereof

A neural network and visual tracking technology applied in the field of visual tracking to achieve good classification accuracy

Pending Publication Date: 2020-06-30
ACADEMY OF MILITARY MEDICAL SCI
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the limitation that the existing tracking algorithm lacks a general tracking failure detection method, the present invention proposes a tracking failure detection system based on a deep neural network, and designs a sample generation method for deep neural network training

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
  • Visual tracking failure detection system based on neural network and training method thereof
  • Visual tracking failure detection system based on neural network and training method thereof
  • Visual tracking failure detection system based on neural network and training method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] Using the OTB-100 dataset ] Perform sample generation, generate 58,723 normal tracking samples (50,000 are randomly selected for training), and 48,235 tracking failure samples. Take 80% of the total samples as the training data set and 20% as the verification data set. For the same data set, 60 videos are randomly taken out, the label data of the first frame is changed (the size of the label target is changed), samples for testing are generated, and 34,321 samples with normal tracking are generated (30,000 samples are randomly extracted for testing), and the tracking fails There are 27748 samples.

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 visual tracking failure detection system based on a neural network and a training method thereof, and belongs to the technical field of visual tracking. The method comprisesthe steps: establishing the visual tracking failure detection system based on the neural network, wherein the system is formed by connecting a related filtering module and a tracking anomaly sensing module in series; according to the visual tracking failure detection system, judging whether target tracking fails or not according to a result graph generated by a related filter by utilizing the strong visual perception capability of a deep neural network; and enabling the correlation filtering module to perform model parameter updating according to a result of the tracking exception sensing module. In view of the fact that the neural network method has good classification precision but needs a large number of samples for training, the training needs a large number of samples including positive samples and negative samples, a corresponding large-scale training sample generation method is designed, and the method is mainly used for training of a deep neural network model. And testing is carried out on the public data set. The method can support training of the deep neural network.

Description

technical field [0001] The invention belongs to the technical field of visual tracking, in particular to a neural network-based visual tracking failure detection system and a training method thereof. Background technique [0002] Visual target tracking is a kind of algorithm that tracks specific targets in the image data stream. The input is continuous image data and the target template to be tracked, and the output is the position of the tracked target. Changes in the shape of the target and interference from the external environment may cause the tracking algorithm to fail, that is, the target position cannot be accurately located. It is of great significance to find out the failure of the tracking algorithm in time, and adjust or reset the tracking algorithm in time to improve the stability of the target tracking system. [0003] The detection tracking algorithm uses a fast detector to match the target image (image to be detected) to the target position, and determines t...

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): G06T7/246G06T7/73
CPCG06T7/246G06T7/73G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/20024
Inventor 李椋雷煜王以政吴婷陈明松
Owner ACADEMY OF MILITARY MEDICAL SCI
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