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

A multi-target positioning and tracking video monitoring method

A multi-target positioning and video monitoring technology, applied in image analysis, image enhancement, instruments, etc., can solve the problem that video images cannot have foreground objects, and achieve the effect of removing interference and reducing requirements

Active Publication Date: 2018-10-19
杨百川
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The easiest way is to take the average value of the video image sequence, but this has many disadvantages. First, a large number of video images need to be input before calculating the background image. Second, the average video image cannot have foreground objects.
There is no relevant literature report

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 multi-target positioning and tracking video monitoring method
  • A multi-target positioning and tracking video monitoring method
  • A multi-target positioning and tracking video monitoring method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Such as figure 1 Shown, the present invention realizes as follows:

[0033] (1) Apply the Gaussian mixture model to the first 50 frames of the video for background modeling, effectively remove the interference of small changes in the foreground objects in the background to the extraction of moving targets, and reduce the requirements for the video sequence of target extraction.

[0034] (2) The next frame image in the video is subtracted from the background image obtained by Gaussian mixture model background modeling to obtain the foreground image.

[0035] (3) When the moving object has a large similarity with the background tone, the foreground object in the obtained foreground image is incomplete, so the expansion operation is performed in the foreground image to merge all the background points that are in contact with the tracking target into the region of interest In , expand the boundary outward, fill the hole in the binarized tracking target, and fill the incomp...

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

A multi-target positioning and tracking video monitoring method is suitable for moving target positioning and tracking video monitoring methods where the camera's field of view is fixed and there are small dynamic changes in objects in the background. Before the system works, the background is first trained through the Gaussian mixture model, and then the background subtraction method is used to obtain the foreground image in the next frame of the video, and then the accurate foreground object area, that is, the position of the moving target is obtained based on the expansion operation and median filtering; it is detected whether the moving target is exists. If the moving target exists, determine the target position according to the connected domain search. If there is no moving target, go to the next frame of the video; perform tone space conversion on the target position area image and combine the NTSC space tone map I and the HSV space tone map H. The hue histogram is obtained by weighting, and the back projection of the image is further obtained, and then the Meanshift algorithm is used to accurately locate the target position. Repeat the above calculation for the next frame of the video. The invention can be used for moving target trajectory analysis, vehicle speeding and violation detection, and human flow detection.

Description

technical field [0001] The invention designs a multi-target positioning and tracking video monitoring method, which is suitable for the video monitoring of moving target positioning and tracking in which the field of view of the camera is fixed and the background has slight dynamic changes of objects. Background technique [0002] The Meanshift algorithm is one of the more effective target tracking algorithms at present. This algorithm uses the method of gradient optimization to realize the positioning and tracking of the tracking target, and has good adaptability to the deformation, scaling, rotation and other changes of the tracking target. The operation speed is also relatively fast. The Meanshift algorithm has a better tracking effect in the case of a single-tone tracking target and a low similarity between the background image and the tracking target color, but when there are foreground objects with similar colors in the surrounding environment, since the Meanshift algo...

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): G06T7/285G06T5/00G06T5/30G06T5/40G06T5/50
CPCG06T5/30G06T5/40G06T5/50G06T2207/30232G06T2207/20224G06T2207/20032G06T2207/10016G06T5/70
Inventor 杨百川盛蔚任建新
Owner 杨百川
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