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

Target tracking method based on conditional adversarial generative twinning network

A target tracking, twin network technology, applied in biological neural network models, neural learning methods, image data processing and other directions, can solve the problems of tracking failure, motion blur model, poor tracking effect of trackers, etc., to improve robustness, Enhance the dynamic adjustment ability and prevent the effect of overfitting

Pending Publication Date: 2021-05-25
SHENYANG LIGONG UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the technical problem that the model drifts due to motion blur and low resolution when the tracked target is moving rapidly and violently, resulting in poor tracking effect or even tracking failure of the tracker

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 conditional adversarial generative twinning network
  • Target tracking method based on conditional adversarial generative twinning network
  • Target tracking method based on conditional adversarial generative twinning network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0105] A target tracking method based on conditional confrontation generation twin network, characterized in that: the method comprises the following steps:

[0106] (1) Obtain real-time video data for data preprocessing;

[0107] (2) Input the preprocessed data in step (1) into the conditional confrontation generation twin tracking network consisting of the conditional confrontation generation defuzzification network module and the fully convolutional twin tracking network;

[0108] (3) Embed the conditional confrontation generation defuzzification network module completed by the confrontation optimization into the fully convolutional twin tracking network framework after the feedback update, and use the conditional confrontation generation twin tracking network completed online to perform preprocessing on the real-time video data, track the target, and obtain the target position.

[0109] (2) The conditional adversarial generation twin tracking network construction method i...

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 a conditional adversarial generation twinning network. The method comprises the following steps: (1) acquiring real-time video data for data preprocessing; (2) inputting the data preprocessed in the step (1) into a conditional adversarial generation twin tracking network consisting of a conditional adversarial generation deblurring network module and a full-convolution twin tracking network; and (3) embedding the conditional adversarial generation deblurring network module subjected to adversarial optimization into the full-convolution twinning tracking network framework subjected to feedback updating, and performing target tracking on the preprocessed real-time video data by using a conditional adversarial generation twinning tracking network subjected to online combination to obtain a target position. The dynamic adjustment capability of the tracking network is enhanced, the robustness of a tracker is improved, the tracking network is subjected to separation training in a transfer learning mode, the over-fitting phenomenon is prevented, the training time is shortened, and the generalization capability of the tracking network is improved.

Description

technical field [0001] The present invention relates to the technical field of machine vision and target tracking, and more specifically relates to a target tracking method based on conditional confrontation generative twin network. Background technique [0002] Target tracking is one of the important research topics in the field of computer vision. Its main task is to obtain the position information of the target of interest in the video sequence, to realize the analysis and understanding of the behavior of the moving target, and to provide further semantic analysis (action recognition, scene, etc.) recognition, etc.) to provide the basis for completing more advanced tasks. As a middle-level and high-level processing stage in the field of computer vision, target tracking is an important technical means for intelligent analysis of video content. Through high-dimensional feature extraction and spatial coordinate positioning of the target of interest in the video frame sequenc...

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): G06T7/246G06N3/04G06N3/08
CPCG06T7/246G06N3/08G06T2207/10016G06N3/045Y02T10/40
Inventor 宋建辉张甲刘砚菊于洋
Owner SHENYANG LIGONG 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