Combined judging strategy-based visual target tracking method

A target tracking and strategy technology, applied in the field of visual target tracking, can solve the problems that the tracker cannot make fast adjustments, the target texture changes, and destroy the integrity of the target outline, etc., to improve the tracking failure problem, reduce pixel errors, and improve The effect of tracking accuracy

Active Publication Date: 2018-05-08
BEIHANG UNIV
View PDF5 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The most important change of target motion information is the sudden change of motion speed, which makes the tracker unable to make quick adjustments; the change of target size, deformation, etc. will lead

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
  • Combined judging strategy-based visual target tracking method
  • Combined judging strategy-based visual target tracking method
  • Combined judging strategy-based visual target tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] What the present invention adopts is a tracking algorithm based on the combined judgment of multiple trackers, each tracker can effectively deal with the interference of an environmental factor, and the result of each tracker can be adaptively changed in real time by establishing a judgment mechanism weights, so as to achieve the result fusion of the tracker. Its main tracking framework is based on the filter algorithm based on kernel correlation, on top of which, several auxiliary tracking combination judgments are added for the above mentioned environmental factors.

[0082] Such as figure 1 As shown, the present invention is realized as:

[0083] (1) After initializing the target position in the initial frame, use the circulatory matrix to perform dense cyclic sampling of the target area to obtain η*n*m positive and negative samples, where η is a value between 8 and 10;

[0084] (2) For the positive and negative samples obtained in step (1), a unified set is formed...

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 relates to a combined judging strategy-based visual target tracking method. The method comprises the following steps of: (1) aiming at a target size change problem, establishing a self-adaptive scale so as to automatically adjust the size of a tracking frame; (2) aiming at a problem that a position of a target cannot be continuously determined after the target is sheltered, predicting a current observed quantity by adoption of Kalman filtering, and after the target reappears, continuously tracking the target by using a KCF algorithm; and (3) aiming at a problem of tracking failure caused by rapid movement of the target. According to the method, a movement speed of the target is calculated through detecting a position movement distance of the target in adjacent frames, and a detection area size extension coefficient is self-adaptively adjusted, so that relatively high precision can be obtained under different environments, the robustness of the whole tracking system is effectively improved, a relatively high calculation speed is kept, and a high engineering practical value is provided.

Description

technical field [0001] The invention relates to a visual target tracking method based on a combined judgment strategy. Background technique [0002] Moving object tracking is a method for processing, sampling and detection of video signals, which detects and marks specific areas contained in images through certain specific features. In recent years, many scholars have proposed many excellent tracking algorithms. The commonly used tracking algorithms mainly have the following three ideas: method based on feature matching, method based on region correlation and method based on model. [0003] Among them, the feature-based method does not need to care about the appearance of the target and the type of the target. After the extracted features are determined, the feature vector or feature map is constructed, and the comparison between adjacent frames is carried out around the target position of the previous frame. feature match. For example, the algorithm based on the joint mod...

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): G06T7/277G06T7/262G06K9/62
CPCG06T7/262G06T7/277G06T2207/10016G06T2207/20056G06F18/241
Inventor 张弘饶波李伟鹏
Owner BEIHANG UNIV
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