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

Noise-resistant moving target detection algorithm based on low rank matrix

A moving target, low-rank matrix technology, applied in computing, image analysis, computer components and other directions, can solve problems such as impact

Active Publication Date: 2015-05-06
NAT UNIV OF DEFENSE TECH
View PDF3 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] as attached image 3 As shown, the first row is the test image frame. From left to right, the noise of the test image frame gradually increases from zero. Observe that the comparison methods KDE (third row), SOBS (fourth row), and ViBe (fifth row) have no noise In the case of (the first column), the detection result is accurate, and the moving target can be better identified. When the noise increases, the existing methods of non-parametric model (KDE), adaptive background model (SOBS), visual background extractor ( ViBe) all have different degrees of failure, which are obviously affected by noise

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
  • Noise-resistant moving target detection algorithm based on low rank matrix
  • Noise-resistant moving target detection algorithm based on low rank matrix
  • Noise-resistant moving target detection algorithm based on low rank matrix

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Below, the present invention will be further described in conjunction with the accompanying drawings and specific embodiments.

[0041] Such as figure 1 Shown is the overall flow chart of the proposed method of the present invention.

[0042] First, add different degrees and different types of noise to the 360×240 video captured by the surveillance camera, with a total of 300 frames, to simulate the noise in different environments, so that multiple different test image sets can be obtained. as attached image 3 As shown in the first row, in the same monitoring scene, different levels of noise are added. attached figure 2A schematic diagram of the method proposed in the present invention is shown in . After the obtained continuous video frames are decomposed into a low-rank matrix, the low-rank part and the sparse error part are obtained, that is, the required background and foreground.

[0043] Secondly, set the parameters in the iterative process, the size of the ...

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 relates to the field of digital image processing, in particular to an algorithm for utilizing similarity of a continuous video frame to conduct matrix decomposition under low rank restraint to obtain a noise robustness foreground detection result under the condition that an image sequence is polluted by noise signals. By means of the similarity of the continuous image frame in the video, the low rank features of the video matrix are obtained. A convex optimizing method is utilized to excavate the low rank features in the video matrix, and the low rank structure and the sparse error structure of the original video matrix are acquired gradually through iteration optimization. The low rank structure corresponds to a background model in the moving target detection problem, and the sparse error portion corresponds to the moving foreground in the moving target detection problem.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to matrix decomposition under low-rank constraints by using the similarity of continuous video frames under the condition that the image sequence is polluted by noise signals, so as to obtain foreground detection results robust to noise. Background technique [0002] In the past ten years, with the popularization of digital technology and the improvement of computer performance, intelligent video analysis, as an important part of computer applications, has received close attention and research from scholars at home and abroad. Yilmaz pointed out that intelligent video analysis is divided into three key steps: moving object detection, object tracking and behavior recognition. As the first step of intelligent video, moving target detection refers to a method for accurately and completely extracting moving targets from a given image sequence or surveillance video. The extracted ...

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): G06T7/20
CPCG06V20/42G06V2201/07
Inventor 熊志辉肖华欣刘煜王炜张茂军
Owner NAT UNIV OF DEFENSE TECH
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