Video monitoring multi-target tracking method for fusion feature matching and data association

A multi-target tracking and video monitoring technology, applied in image data processing, instruments, computing, etc., can solve problems such as tracking loss, misassociation, and failure to take into account

Active Publication Date: 2014-12-17
NANJING NANYOU INST OF INFORMATION TECHNOVATION CO LTD
View PDF5 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for environments with high target density or clutter density, using the nearest neighbor algorithm for data association can easily lead to misassociation, resulting in tracking loss or track merging; second, the patent obtains the foreground map through background difference, which will efficientl...

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
  • Video monitoring multi-target tracking method for fusion feature matching and data association
  • Video monitoring multi-target tracking method for fusion feature matching and data association

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0065] Such as figure 1 As shown, the present invention designs a video monitoring multi-target tracking method that combines feature matching and data association. Timing operates according to the following steps for each frame of video surveillance screen received:

[0066] Step A. Use the background modeling method to carry out background modeling for the current video surveillance frame, detect and obtain the target in the current video surveillance frame through the background difference method, and detect and obtain the measurement data of each target. The measurement data of the target is The position of the pixel point area occupied by the target in the frame of the video surveillance picture and the size of the pixel point area occupied by the target specifically include the following steps:

[0067] Step A01....

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 video monitoring multi-target tracking method for fusion feature matching and data association, and is improved by aiming at a traditional video monitoring target tracking method. On the basis of predicting by adopting a Kalman filter, joint probability data association and the matching checking of RGB (Red Green Blue) color histogram features and Surf features are introduced, various motion states of a target can be tracked, and target tracking accuracy is guaranteed.

Description

technical field [0001] The invention relates to a multi-target tracking method for video surveillance which combines feature matching and data association. Background technique [0002] Multi-target tracking is a current research hotspot in the field of computer vision. Multi-target tracking refers to the use of computers to determine the position, size, and completeness of each independent moving target of interest in a video sequence. motion track. In recent years, with the rapid growth of computer data processing capabilities and the development of image analysis technology, the real-time tracking technology of objects has come to the fore. It has very important practical value. [0003] The current methods of target tracking in image sequences can be roughly divided into the following three types: [0004] (1) Methods based on motion analysis, typical of which are difference method, optical flow method, etc., which are suitable for situations where background changes ...

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): G06T7/20G06T7/00
Inventor 李晓飞车少帅刘浏吴鹏飞赵光明
Owner NANJING NANYOU INST OF INFORMATION TECHNOVATION CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap