Video image target tracking processing method and system

A technology for video image and target tracking, applied in the field of video image target tracking processing methods and systems, capable of solving problems such as lost tracking targets, video target tracking error errors, and decreased tracking accuracy, achieving small calculations, accurate tracking processing, and adaptive powerful effect

Active Publication Date: 2016-08-24
CRSC COMM & INFORMATION GRP CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, in the actual video target tracking, due to the unavoidable influence of factors such as background color interference, fast movement of the target, and illumination changes, the existing video target tracking processing methods do not solve the problem caused by spatially similar color interference. Video target tracking errors or even errors, resulting in decreased tracking accuracy, or even loss of tracking targets

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 image target tracking processing method and system
  • Video image target tracking processing method and system
  • Video image target tracking processing method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] see figure 1 , figure 2 , as an implementable mode, a video image target tracking processing method according to an embodiment of the present invention includes the following steps:

[0032] Step S100, modeling the background of the current video image, using the background subtraction method to perform foreground object detection on the foreground in the current video image, obtaining the foreground blobs in the current video image, determining the tracked object, and extracting the tracked object The color histogram of the location of the foreground blob;

[0033] Preferably, as an implementable manner, the step S100 includes the following steps:

[0034] Step S110, read the T frame image in the current video image and use the mixed Gaussian model to model the background to distinguish the foreground and background of the image;

[0035] Wherein, T is an integer.

[0036] As an implementable manner, in the step S110, the background is modeled using a mixed Gaussi...

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 provides a video image target tracking processing method and system. The method comprises the steps of: modeling the background of the current video image, performing foreground target detection on the foreground in the current video image, obtaining the foreground blob in the current video image, determining the tracked target, and extracting the location of the tracked target. The color histogram of the location of the foreground clump; when the tracked target is confirmed, use the scale information and historical position information of the tracked target's foreground clump in the current video image to initialize the Kalman predictor corresponding to the tracked target Train, and update the color histogram of the target in the video image; track the tracked target in the subsequent continuous video of the current video image according to the number of tracking targets detected in the current video image. It is simple and efficient, has strong adaptability, and can accurately track and process video targets.

Description

technical field [0001] The invention relates to the technical field of image and video behavior analysis and processing, in particular to a method and system for tracking and processing video image objects. Background technique [0002] Video behavior analysis is a technology to extract the behavior of the target of interest in the video through certain image processing from the video sequence. [0003] With the needs of anti-terrorism, public safety and safe cities in the world, the security field has become a broad application stage for video behavior analysis. However, the current level of intelligence in video surveillance facilities is low, and most of them only record video data for subsequent inquiries. , the current video behavior analysis such as stay detection, running detection, etc. cannot meet the actual needs. [0004] In order to better meet the needs of practical applications, people have proposed a variety of video behavior analysis methods, such as particl...

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): G06T7/20
Inventor 安国成肖坦李洪研张涛罗志强
Owner CRSC COMM & INFORMATION GRP 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