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

Intelligent segmentation method of video image target

A video image and object technology, applied in the field of intelligent segmentation of video image objects, can solve problems such as many moving objects, complex background components, and difficult video object segmentation algorithms

Pending Publication Date: 2020-05-15
福建省星云大数据应用服务有限公司
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Video object segmentation based on time and space is relatively simple to implement and has good real-time performance. However, due to the obvious changes in illumination, many moving objects, and complex background components in the actual scene, it brings difficulties to the video object segmentation algorithm.

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
  • Intelligent segmentation method of video image target
  • Intelligent segmentation method of video image target
  • Intelligent segmentation method of video image target

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0096] An intelligent segmentation method of a video image target, which adopts the method of alternately carrying out the background model establishment stage and the foreground detection stage, such as figure 1 As shown, a new color space distance measure and a new periodic dynamic background processing method are used in the YUV color space, and the maximum continuous unmatched time length parameter is used to effectively distinguish the foreground and the background in the modeling stage. This method Specifically include the following steps:

[0097] Step 1: Set the frame rate of the surveillance video as fFPS, and the frame number as n, T 1 and T 2 are the periods of the background model building phase and the foreground detection phase, respectively, when 1≤n≤T 1 When f is the stage of establishing the background model; when T 1 f≤n≤(T 1 +T 2 )f, it is the foreground detection stage.

[0098] Step 2: Convert pixel x n =The pixel value of (R, G, B) is converted fro...

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 an intelligent segmentation method for a video image target, and the method employs a YUV color space and a specific distance measurement to overcome the impact from illumination, maintains a plurality of clustering centers to process a dynamic background, and employs a maximum continuous unmatched time length parameter to exclude foreground pixels out of a background model. According to the method, structured background motion can be obtained for a long time in a limited storage space, and a compact model can be established for a dynamic background; the influence of illumination on background modeling and foreground detection can be overcome; periodically switching between a modeling stage and a detection stage is carried out to meet the application requirement oflong-time uninterrupted operation of video monitoring. The method has better segmentation accuracy and higher processing speed, and is more suitable for video object segmentation of scenes such as passenger flow statistics, traffic flow video monitoring, industrial automatic monitoring and safety protection.

Description

technical field [0001] The invention belongs to the technical field of intelligent video monitoring and analysis, and in particular relates to an intelligent segmentation method of a video image target. Background technique [0002] Digital video sequence images provide richer information than static images. By analyzing multiple frames of images, information that cannot be obtained from a single image is obtained. With the development of computer vision technology, video analysis technology is more and more widely used. Video object segmentation is one of the key technologies in video analysis system, mainly used in object-based video coding, content-based video retrieval, intelligent monitoring, interactive video entertainment and more. The current video object segmentation methods are as follows: [0003] Motion Estimation Video Object Segmentation: It refers to using methods such as optical flow field to estimate motion parameters first, find pixel connected domains t...

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): G06K9/00H04N7/18
CPCH04N7/18G06V20/49G06V20/41
Inventor 林欣郁邹建红张毅高元荣陈米思肖晓柏朱含杉陈华辉陈思添谢月萍
Owner 福建省星云大数据应用服务有限公司
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