bullet Sensors & Transducers Journal

    (ISSN 1726-5479)

205.767

2008 e-Impact Factor

25 Top Downloaded Articles

Best Selling Articles 2012

Journal Subscription 2014

Editorial Calendar

Submit an Article

Editorial Board

Current Issue

S&T journal's cover

Sensors & Transducers Journal 2011

Sensors & Transducers Journal 2010

Sensors & Transducers Journal 2009

Sensors & Transducers Journal 2008

Sensors & Transducers Journal 2007

2000-2002 S&T e-Digest Contents

2003 S&T e-Digest Contents

2004 S&T e-Digest Contents

2005 S&T e-Digest Contents

2006 S&T e-Digest Contents

 

Best Articles 2011

 

 

 

Vol. 161, Issue 12, December 2013, pp. 98-106

 

Bullet

 

Research on the Human Motion Analysis and Key Technology Based on Intelligent Video Surveillance
 
Weihong WANG, Xiaojun WANG

Physical Education, Si Chuan University, Cheng du 610064, China
E-mail: weihongwangstst@126.com

 

Received: 11 October 2   /Accepted: 22 November 2013   /Published: 30 December 2013

Digital Sensors and Sensor Sysstems

 

Abstract: A key technology of intelligent video surveillance was demonstrated in this paper. The first human motion detection in video sequences, and then carry on the track, the research on the recognition of human behavior, the abnormal behavior detection. Firstly, the first video image denoising with Gauss low-pass filter, then using the background subtraction method and frame difference method for target detection, and then use morphological image processing, regional connectivity analysis and a series of processing methods, to eliminate the small holes and noise, the moving object is extracted from the video sequence background subtraction method, and compare the advantages and disadvantages and frame difference method. Finally, the analysis and discussion of human behavior recognition method were demonstrated. Methods using the template matching method based on characteristic value for human identification, selection of structure moment features with translation, rotation, scaling invariance of the values, the method overcomes the defects of the traditional template matching method, comparing the similarity of feature extraction value, in order to distinguish between normal and abnormal behavior, to achieve the recognition of human behavior.

 

Keywords: Non-negative matrix factorization, Pattern recognition, Algorithm, Database.

 

 

Buy this article online (it will be send to you in the pdf format by e-mail) or subscribe Sensors & Transducers journal

(12 issues per year plus special issues; 40 % discount for payment IFSA Members):

 

 

Buy this article for
14.95 $ US:

 

 
 

 

 

Download <here> the Library Journal Recommendation Form

 

 

Read more about Wireless Sensor Networks

 

 

 

 

 


1999 - 2013 Copyright , International Frequency Sensor Association (IFSA). All Rights Reserved.


Home - News - Links - Archives - Tools - Voltage-to-Frequency Converters - Standardization - Patents - Marketplace - Projects - Wish List - e-Shop - Sensor Jobs - Membership - Videos - Publishing - Site Map - Subscribe - Search

 Members Area -Sensors Portal -Training Courses - S&T Digest - For advertisers - Bookstore - Forums - Polls - Submit Press Release - Submit White Paper - Testimonies - Twitter - Facebook - LinkedIn