Detecting humans using luminance saliency in thermal images

This Letter introduces an efficient human detection method in thermal images, using a center-symmetric local binary pattern (CS-LBP) with a luminance saliency map and a random forest (RF) classifier scheme. After detecting a candidate human region, we crop only the head and shoulder region, which ha...

Full description

Saved in:
Bibliographic Details
Published in:Optics letters 2012-10, Vol.37 (20), p.4350-4352
Main Authors: Ko, ByoungChul, Kim, DeokYeon, Nam, JaeYeal
Format: Article
Language:English
Subjects:
Classifiers
Decision Trees
Human
Humans
Legs
Light
Luminance
Optical Phenomena
Radio frequencies
Thermography - methods
Trunks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c324t-fd888d94928f413877efba2dac97f3694e7494ceba7eb61132a2fd16875a66093
cites cdi_FETCH-LOGICAL-c324t-fd888d94928f413877efba2dac97f3694e7494ceba7eb61132a2fd16875a66093
container_end_page 4352
container_issue 20
container_start_page 4350
container_title Optics letters
container_volume 37
creator Ko, ByoungChul
Kim, DeokYeon
Nam, JaeYeal
description This Letter introduces an efficient human detection method in thermal images, using a center-symmetric local binary pattern (CS-LBP) with a luminance saliency map and a random forest (RF) classifier scheme. After detecting a candidate human region, we crop only the head and shoulder region, which has a higher thermal spectrum than the legs or trunk. The CS-LBP feature is then extracted from the luminance saliency map of a hotspot and applied to the RF classifier, which is an ensemble of randomized decision trees. We demonstrate that our detection method is more robust than conventional feature descriptors and classifiers in thermal images.
doi_str_mv 10.1364/OL.37.004350
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1283720327</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1283720327</sourcerecordid><originalsourceid>FETCH-LOGICAL-c324t-fd888d94928f413877efba2dac97f3694e7494ceba7eb61132a2fd16875a66093</originalsourceid><addsrcrecordid>eNqFkDtPwzAURi0EoqWwMaOMDKTYvo4fYkLlKUXqArPlODdtUOKWOBn670nVwsp0daWjI32HkGtG5wykuF_mc1BzSgVk9IRMWQYmFcqIUzKlTMjUZIZPyEWMX5RSqQDOyYQDVSAyMyUPT9ij7-uwStZD60JMhrh_mqGtgwsek-iaGoPfJXVI-jV2rWuSunUrjJfkrHJNxKvjnZHPl-ePxVuaL1_fF4956oGLPq1KrXVphOG6Egy0UlgVjpfOG1WBNAKVMMJj4RQWkjHgjlclk1plTkpqYEZuD95tt_keMPa2raPHpnEBN0O0jGtQnAJX_6N7PRuXixG9O6C-28TYYWW33bir21lG7b6sXeYWlD2UHfGbo3koWiz_4N-U8AMNY3IE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1113214594</pqid></control><display><type>article</type><title>Detecting humans using luminance saliency in thermal images</title><source>Jisc-Optica Publishing Group Read &amp; Publish Agreement 2022-2024 – E Combination 1</source><creator>Ko, ByoungChul ; Kim, DeokYeon ; Nam, JaeYeal</creator><creatorcontrib>Ko, ByoungChul ; Kim, DeokYeon ; Nam, JaeYeal</creatorcontrib><description>This Letter introduces an efficient human detection method in thermal images, using a center-symmetric local binary pattern (CS-LBP) with a luminance saliency map and a random forest (RF) classifier scheme. After detecting a candidate human region, we crop only the head and shoulder region, which has a higher thermal spectrum than the legs or trunk. The CS-LBP feature is then extracted from the luminance saliency map of a hotspot and applied to the RF classifier, which is an ensemble of randomized decision trees. We demonstrate that our detection method is more robust than conventional feature descriptors and classifiers in thermal images.</description><identifier>ISSN: 0146-9592</identifier><identifier>EISSN: 1539-4794</identifier><identifier>DOI: 10.1364/OL.37.004350</identifier><identifier>PMID: 23073459</identifier><language>eng</language><publisher>United States</publisher><subject>Classifiers ; Decision Trees ; Human ; Humans ; Legs ; Light ; Luminance ; Optical Phenomena ; Radio frequencies ; Thermography - methods ; Trunks</subject><ispartof>Optics letters, 2012-10, Vol.37 (20), p.4350-4352</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c324t-fd888d94928f413877efba2dac97f3694e7494ceba7eb61132a2fd16875a66093</citedby><cites>FETCH-LOGICAL-c324t-fd888d94928f413877efba2dac97f3694e7494ceba7eb61132a2fd16875a66093</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/23073459$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Ko, ByoungChul</creatorcontrib><creatorcontrib>Kim, DeokYeon</creatorcontrib><creatorcontrib>Nam, JaeYeal</creatorcontrib><title>Detecting humans using luminance saliency in thermal images</title><title>Optics letters</title><addtitle>Opt Lett</addtitle><description>This Letter introduces an efficient human detection method in thermal images, using a center-symmetric local binary pattern (CS-LBP) with a luminance saliency map and a random forest (RF) classifier scheme. After detecting a candidate human region, we crop only the head and shoulder region, which has a higher thermal spectrum than the legs or trunk. The CS-LBP feature is then extracted from the luminance saliency map of a hotspot and applied to the RF classifier, which is an ensemble of randomized decision trees. We demonstrate that our detection method is more robust than conventional feature descriptors and classifiers in thermal images.</description><subject>Classifiers</subject><subject>Decision Trees</subject><subject>Human</subject><subject>Humans</subject><subject>Legs</subject><subject>Light</subject><subject>Luminance</subject><subject>Optical Phenomena</subject><subject>Radio frequencies</subject><subject>Thermography - methods</subject><subject>Trunks</subject><issn>0146-9592</issn><issn>1539-4794</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2012</creationdate><recordtype>article</recordtype><recordid>eNqFkDtPwzAURi0EoqWwMaOMDKTYvo4fYkLlKUXqArPlODdtUOKWOBn670nVwsp0daWjI32HkGtG5wykuF_mc1BzSgVk9IRMWQYmFcqIUzKlTMjUZIZPyEWMX5RSqQDOyYQDVSAyMyUPT9ij7-uwStZD60JMhrh_mqGtgwsek-iaGoPfJXVI-jV2rWuSunUrjJfkrHJNxKvjnZHPl-ePxVuaL1_fF4956oGLPq1KrXVphOG6Egy0UlgVjpfOG1WBNAKVMMJj4RQWkjHgjlclk1plTkpqYEZuD95tt_keMPa2raPHpnEBN0O0jGtQnAJX_6N7PRuXixG9O6C-28TYYWW33bir21lG7b6sXeYWlD2UHfGbo3koWiz_4N-U8AMNY3IE</recordid><startdate>20121015</startdate><enddate>20121015</enddate><creator>Ko, ByoungChul</creator><creator>Kim, DeokYeon</creator><creator>Nam, JaeYeal</creator><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>20121015</creationdate><title>Detecting humans using luminance saliency in thermal images</title><author>Ko, ByoungChul ; Kim, DeokYeon ; Nam, JaeYeal</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c324t-fd888d94928f413877efba2dac97f3694e7494ceba7eb61132a2fd16875a66093</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Classifiers</topic><topic>Decision Trees</topic><topic>Human</topic><topic>Humans</topic><topic>Legs</topic><topic>Light</topic><topic>Luminance</topic><topic>Optical Phenomena</topic><topic>Radio frequencies</topic><topic>Thermography - methods</topic><topic>Trunks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ko, ByoungChul</creatorcontrib><creatorcontrib>Kim, DeokYeon</creatorcontrib><creatorcontrib>Nam, JaeYeal</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Optics letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ko, ByoungChul</au><au>Kim, DeokYeon</au><au>Nam, JaeYeal</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Detecting humans using luminance saliency in thermal images</atitle><jtitle>Optics letters</jtitle><addtitle>Opt Lett</addtitle><date>2012-10-15</date><risdate>2012</risdate><volume>37</volume><issue>20</issue><spage>4350</spage><epage>4352</epage><pages>4350-4352</pages><issn>0146-9592</issn><eissn>1539-4794</eissn><abstract>This Letter introduces an efficient human detection method in thermal images, using a center-symmetric local binary pattern (CS-LBP) with a luminance saliency map and a random forest (RF) classifier scheme. After detecting a candidate human region, we crop only the head and shoulder region, which has a higher thermal spectrum than the legs or trunk. The CS-LBP feature is then extracted from the luminance saliency map of a hotspot and applied to the RF classifier, which is an ensemble of randomized decision trees. We demonstrate that our detection method is more robust than conventional feature descriptors and classifiers in thermal images.</abstract><cop>United States</cop><pmid>23073459</pmid><doi>10.1364/OL.37.004350</doi><tpages>3</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0146-9592
ispartof Optics letters, 2012-10, Vol.37 (20), p.4350-4352
issn 0146-9592
1539-4794
language eng
recordid cdi_proquest_miscellaneous_1283720327
source Jisc-Optica Publishing Group Read & Publish Agreement 2022-2024 – E Combination 1
subjects Classifiers
Decision Trees
Human
Humans
Legs
Light
Luminance
Optical Phenomena
Radio frequencies
Thermography - methods
Trunks
title Detecting humans using luminance saliency in thermal images
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T16%3A00%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Detecting%20humans%20using%20luminance%20saliency%20in%20thermal%20images&rft.jtitle=Optics%20letters&rft.au=Ko,%20ByoungChul&rft.date=2012-10-15&rft.volume=37&rft.issue=20&rft.spage=4350&rft.epage=4352&rft.pages=4350-4352&rft.issn=0146-9592&rft.eissn=1539-4794&rft_id=info:doi/10.1364/OL.37.004350&rft_dat=%3Cproquest_cross%3E1283720327%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c324t-fd888d94928f413877efba2dac97f3694e7494ceba7eb61132a2fd16875a66093%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1113214594&rft_id=info:pmid/23073459&rfr_iscdi=true