Statistical and entropy based multi purpose human motion analysis

As visual surveillance systems are gaining wider usage in a variety of fields, they need to be embedded with the capability to interpret scenes automatically, which is known as human motion analysis (HMA). However, existing HMA methods are too domain specific and computationally expensive. This pape...

Full description

Saved in:
Bibliographic Details
Main Authors: Chin-Poo Lee, Kian-Ming Lim, Wei-Lee Woon
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Artificial neural networks
Computer vision
Entropy
Hidden Markov models
Image Processing
Motion Analysis
Motion segmentation
Neural Networks
Tracking
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page V1-738
container_issue
container_start_page V1-734
container_title
container_volume 1
creator Chin-Poo Lee
Kian-Ming Lim
Wei-Lee Woon
description As visual surveillance systems are gaining wider usage in a variety of fields, they need to be embedded with the capability to interpret scenes automatically, which is known as human motion analysis (HMA). However, existing HMA methods are too domain specific and computationally expensive. This paper proposes a general purpose HMA method. It is based on the idea that human beings tend to exhibit random motion patterns during abnormal situations. Hence, angular and linear displacements of limb movements are characterized using basic statistical quantities. In addition, it is enhanced with the entropy of the Fourier spectrum to measure the randomness of the abnormal behavior. Various experiments have been conducted and prove that the proposed method has very high classification accuracy in identifying anomalous behavior.
doi_str_mv 10.1109/ICSPS.2010.5555261
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5555261</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5555261</ieee_id><sourcerecordid>5555261</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-48b4e6dbfd614124f4225dbafee890c2b539b28d79ed8f4faa7372e67748e5c43</originalsourceid><addsrcrecordid>eNpVj8tKxDAYhSMiKGNfQDd5gY5J-rdJlkPxMjCg0NkPSfMHI73RpIu-vQVn49kcPvg4cAh54mzPOdMvx7r5avaCbVxuERW_IZmWioMAqJQuytt_LNQ9yWL8YVtg0wU8kEOTTAoxhdZ01AyO4pDmcVqpNREd7ZcuBTot8zRGpN9LbwbajymMwyabbo0hPpI7b7qI2bV35Pz2eq4_8tPn-7E-nPKgWcpBWcDKWe8qDlyAByFKZ41HVJq1wpaFtkI5qdEpD94YWUiBlZSgsGyh2JHnv9mAiJdpDr2Z18v1d_ELdq1Mqg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Statistical and entropy based multi purpose human motion analysis</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Chin-Poo Lee ; Kian-Ming Lim ; Wei-Lee Woon</creator><creatorcontrib>Chin-Poo Lee ; Kian-Ming Lim ; Wei-Lee Woon</creatorcontrib><description>As visual surveillance systems are gaining wider usage in a variety of fields, they need to be embedded with the capability to interpret scenes automatically, which is known as human motion analysis (HMA). However, existing HMA methods are too domain specific and computationally expensive. This paper proposes a general purpose HMA method. It is based on the idea that human beings tend to exhibit random motion patterns during abnormal situations. Hence, angular and linear displacements of limb movements are characterized using basic statistical quantities. In addition, it is enhanced with the entropy of the Fourier spectrum to measure the randomness of the abnormal behavior. Various experiments have been conducted and prove that the proposed method has very high classification accuracy in identifying anomalous behavior.</description><identifier>ISBN: 9781424468928</identifier><identifier>ISBN: 1424468922</identifier><identifier>EISBN: 9781424468935</identifier><identifier>EISBN: 1424468930</identifier><identifier>DOI: 10.1109/ICSPS.2010.5555261</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Artificial neural networks ; Computer vision ; Entropy ; Hidden Markov models ; Image Processing ; Motion Analysis ; Motion segmentation ; Neural Networks ; Tracking</subject><ispartof>2010 2nd International Conference on Signal Processing Systems, 2010, Vol.1, p.V1-734-V1-738</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5555261$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5555261$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chin-Poo Lee</creatorcontrib><creatorcontrib>Kian-Ming Lim</creatorcontrib><creatorcontrib>Wei-Lee Woon</creatorcontrib><title>Statistical and entropy based multi purpose human motion analysis</title><title>2010 2nd International Conference on Signal Processing Systems</title><addtitle>ICSPS</addtitle><description>As visual surveillance systems are gaining wider usage in a variety of fields, they need to be embedded with the capability to interpret scenes automatically, which is known as human motion analysis (HMA). However, existing HMA methods are too domain specific and computationally expensive. This paper proposes a general purpose HMA method. It is based on the idea that human beings tend to exhibit random motion patterns during abnormal situations. Hence, angular and linear displacements of limb movements are characterized using basic statistical quantities. In addition, it is enhanced with the entropy of the Fourier spectrum to measure the randomness of the abnormal behavior. Various experiments have been conducted and prove that the proposed method has very high classification accuracy in identifying anomalous behavior.</description><subject>Accuracy</subject><subject>Artificial neural networks</subject><subject>Computer vision</subject><subject>Entropy</subject><subject>Hidden Markov models</subject><subject>Image Processing</subject><subject>Motion Analysis</subject><subject>Motion segmentation</subject><subject>Neural Networks</subject><subject>Tracking</subject><isbn>9781424468928</isbn><isbn>1424468922</isbn><isbn>9781424468935</isbn><isbn>1424468930</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpVj8tKxDAYhSMiKGNfQDd5gY5J-rdJlkPxMjCg0NkPSfMHI73RpIu-vQVn49kcPvg4cAh54mzPOdMvx7r5avaCbVxuERW_IZmWioMAqJQuytt_LNQ9yWL8YVtg0wU8kEOTTAoxhdZ01AyO4pDmcVqpNREd7ZcuBTot8zRGpN9LbwbajymMwyabbo0hPpI7b7qI2bV35Pz2eq4_8tPn-7E-nPKgWcpBWcDKWe8qDlyAByFKZ41HVJq1wpaFtkI5qdEpD94YWUiBlZSgsGyh2JHnv9mAiJdpDr2Z18v1d_ELdq1Mqg</recordid><startdate>201007</startdate><enddate>201007</enddate><creator>Chin-Poo Lee</creator><creator>Kian-Ming Lim</creator><creator>Wei-Lee Woon</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201007</creationdate><title>Statistical and entropy based multi purpose human motion analysis</title><author>Chin-Poo Lee ; Kian-Ming Lim ; Wei-Lee Woon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-48b4e6dbfd614124f4225dbafee890c2b539b28d79ed8f4faa7372e67748e5c43</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Accuracy</topic><topic>Artificial neural networks</topic><topic>Computer vision</topic><topic>Entropy</topic><topic>Hidden Markov models</topic><topic>Image Processing</topic><topic>Motion Analysis</topic><topic>Motion segmentation</topic><topic>Neural Networks</topic><topic>Tracking</topic><toplevel>online_resources</toplevel><creatorcontrib>Chin-Poo Lee</creatorcontrib><creatorcontrib>Kian-Ming Lim</creatorcontrib><creatorcontrib>Wei-Lee Woon</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chin-Poo Lee</au><au>Kian-Ming Lim</au><au>Wei-Lee Woon</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Statistical and entropy based multi purpose human motion analysis</atitle><btitle>2010 2nd International Conference on Signal Processing Systems</btitle><stitle>ICSPS</stitle><date>2010-07</date><risdate>2010</risdate><volume>1</volume><spage>V1-734</spage><epage>V1-738</epage><pages>V1-734-V1-738</pages><isbn>9781424468928</isbn><isbn>1424468922</isbn><eisbn>9781424468935</eisbn><eisbn>1424468930</eisbn><abstract>As visual surveillance systems are gaining wider usage in a variety of fields, they need to be embedded with the capability to interpret scenes automatically, which is known as human motion analysis (HMA). However, existing HMA methods are too domain specific and computationally expensive. This paper proposes a general purpose HMA method. It is based on the idea that human beings tend to exhibit random motion patterns during abnormal situations. Hence, angular and linear displacements of limb movements are characterized using basic statistical quantities. In addition, it is enhanced with the entropy of the Fourier spectrum to measure the randomness of the abnormal behavior. Various experiments have been conducted and prove that the proposed method has very high classification accuracy in identifying anomalous behavior.</abstract><pub>IEEE</pub><doi>10.1109/ICSPS.2010.5555261</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9781424468928
ispartof 2010 2nd International Conference on Signal Processing Systems, 2010, Vol.1, p.V1-734-V1-738
issn
language eng
recordid cdi_ieee_primary_5555261
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Accuracy
Artificial neural networks
Computer vision
Entropy
Hidden Markov models
Image Processing
Motion Analysis
Motion segmentation
Neural Networks
Tracking
title Statistical and entropy based multi purpose human motion analysis
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T00%3A41%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Statistical%20and%20entropy%20based%20multi%20purpose%20human%20motion%20analysis&rft.btitle=2010%202nd%20International%20Conference%20on%20Signal%20Processing%20Systems&rft.au=Chin-Poo%20Lee&rft.date=2010-07&rft.volume=1&rft.spage=V1-734&rft.epage=V1-738&rft.pages=V1-734-V1-738&rft.isbn=9781424468928&rft.isbn_list=1424468922&rft_id=info:doi/10.1109/ICSPS.2010.5555261&rft.eisbn=9781424468935&rft.eisbn_list=1424468930&rft_dat=%3Cieee_6IE%3E5555261%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-48b4e6dbfd614124f4225dbafee890c2b539b28d79ed8f4faa7372e67748e5c43%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5555261&rfr_iscdi=true