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

A Correlation Matching Tracking Method for Moving Targets in Complex Backgrounds

A technology of correlation matching and moving targets, applied in the field of photoelectric tracking of moving targets

Active Publication Date: 2016-08-31
中国航天科工集团第二研究院二〇七所
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a method for correlation matching and tracking of moving targets in complex backgrounds, by adopting targeted processing methods in different stages of correlation matching and tracking to solve the problem of target occlusion, target posture and size changes in the real environment , light changes, etc., how to achieve effective tracking

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
  • A Correlation Matching Tracking Method for Moving Targets in Complex Backgrounds
  • A Correlation Matching Tracking Method for Moving Targets in Complex Backgrounds
  • A Correlation Matching Tracking Method for Moving Targets in Complex Backgrounds

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The technical solution of the present invention will be further described in detail below.

[0026] The technical scheme of the present invention adopts the target template size change criterion to solve the template size change problem; uses the target template update criterion to solve the problem of long-term stable tracking, and improves the template update stability by designing an improved template update criterion, which will not cause the target to be blocked. It leads to template mutation and affects image matching, which leads to target tracking failure.

[0027] In this embodiment, the image signal processor hardware platform is constructed by TMS320C6416DSP produced by TI Company. The software code of the correlation matching tracking method proposed by the present invention is realized by mixed programming of TMS320C6416DSP special C language and special assembly language, and is solidified on the image signal processor hardware after compilation, and the D...

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 a photoelectric tracking technology of a moving target, and particularly relates to a correlation matching tracking method of the moving target in a complex background. The correlation matching tracking method is divided into a target template size change rule and a target template updating rule, wherein (1) the target template size change rule comprises the following steps: according to an original template of a previous frame, proportionally calculating a zooming-in template and a zooming-out template; calculating matching degrees in allusion to the three templates respectively, and accordingly determining the template; and (2) target template updating rule comprises the following steps: firstly, selecting regions with the same size as that of a current template within a current tracking window by starting from the left upper corner, with 1 pixel as a step length, matching with the current template one by one, and calculating each matching degree cn according to a matching degree formula in the step (1), selecting a region corresponding to the maximum matching degree as an optimal matching region; and secondly, setting a first frame, taking a target region as the current template, calculating each frame to obtain an updated template, and controlling the positioning target of each frame through the above two steps.

Description

technical field [0001] The invention belongs to the photoelectric tracking technology of a moving target, and in particular relates to a method for correlation matching and tracking of a moving target under a complex background. Background technique [0002] The tracking based on the template matching method is a method of pixel-by-pixel comparison. Its basic idea is to use the known object as a template to translate on the collected image, and calculate the correlation value between the object and the sub-image, and the one with the largest correlation value is considered to be The object to be tracked. In the traditional correlation matching method, the size and shape of the template are regarded as constant, but in fact the two are always changing. When the target approaches or moves away from the camera, or the camera field of view changes, the target will become larger or smaller, and the size of the template remains the same, which may cause two problems: one is that ...

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 Patents(China)
IPC IPC(8): G06T7/20H04N7/18
Inventor 冯雪崔述金王楠石春雷
Owner 中国航天科工集团第二研究院二〇七所
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