{"id":"https://openalex.org/W2129328412","doi":"https://doi.org/10.1109/iros.2007.4399331","title":"Auditory and visual integration based localization and tracking of humans in daily-life environments","display_name":"Auditory and visual integration based localization and tracking of humans in daily-life environments","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2129328412","doi":"https://doi.org/10.1109/iros.2007.4399331","mag":"2129328412"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2007.4399331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054240780","display_name":"Hyun-Don Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hyun-Don Kim","raw_affiliation_strings":["Speech Media Processing Group, Kyoto University, Kyoto, Japan","Kyoto University, Kyoto"],"affiliations":[{"raw_affiliation_string":"Speech Media Processing Group, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["Speech Media Processing Group, Kyoto University, Kyoto, Japan","Kyoto University, Kyoto"],"affiliations":[{"raw_affiliation_string":"Speech Media Processing Group, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Speech Media Processing Group, Kyoto University, Kyoto, Japan","Kyoto University, Kyoto"],"affiliations":[{"raw_affiliation_string":"Speech Media Processing Group, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Speech Media Processing Group, Kyoto University, Kyoto, Japan","Kyoto University, Kyoto"],"affiliations":[{"raw_affiliation_string":"Speech Media Processing Group, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054240780"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":1.9455,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86890086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2021","last_page":"2027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7697303295135498},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7202891111373901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7056556940078735},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6703752279281616},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5459541082382202},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.45803263783454895},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.41581499576568604},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.2206975221633911}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7697303295135498},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7202891111373901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7056556940078735},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6703752279281616},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5459541082382202},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.45803263783454895},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.41581499576568604},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.2206975221633911},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2007.4399331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.5614","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.5614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/~okuno/paper/IROS2007-Kim.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1869758581","https://openalex.org/W1912147533","https://openalex.org/W1985690171","https://openalex.org/W2101329857","https://openalex.org/W2116546045","https://openalex.org/W2147673046","https://openalex.org/W2153458938","https://openalex.org/W2154808488","https://openalex.org/W2165943878","https://openalex.org/W6639229959","https://openalex.org/W6675228299","https://openalex.org/W6684277850"],"related_works":["https://openalex.org/W2084086966","https://openalex.org/W2023861399","https://openalex.org/W2730915376","https://openalex.org/W8302103","https://openalex.org/W2626306547","https://openalex.org/W2021396365","https://openalex.org/W2394134009","https://openalex.org/W2119515433","https://openalex.org/W3171631314","https://openalex.org/W2158788032"],"abstract_inverted_index":{"The":[0],"purpose":[1],"of":[2,139],"this":[3],"research":[4],"is":[5,32],"to":[6,12,80,84,124,159,166],"develop":[7],"techniques":[8],"that":[9,35,57,98,189],"enable":[10,81],"robots":[11,36],"choose":[13],"and":[14,29,55,67,127,162,165,180],"track":[15],"a":[16,39,48,82,96,118,155,168],"desired":[17,40],"person":[18],"for":[19,148],"interaction":[20],"in":[21,120,172,194],"daily-life":[22,196],"environments.":[23,197],"Therefore,":[24],"localizing":[25],"multiple":[26,87],"moving":[27,88],"sounds":[28],"human":[30,150],"faces":[31,103,140],"necessary":[33],"so":[34],"can":[37,59,99,133],"locate":[38],"person.":[41],"For":[42,91],"sound":[43,61,89],"source":[44],"localization,":[45,93],"we":[46,94,153],"used":[47],"cross-power":[49],"spectrum":[50],"phase":[51],"analysis":[52],"(CSP)":[53],"method":[54,97,158],"showed":[56],"CSP":[58],"localize":[60],"sources":[62],"only":[63],"using":[64,104,111],"two":[65],"microphones":[66],"does":[68],"not":[69],"need":[70],"impulse":[71],"response":[72],"data.":[73],"An":[74],"expectation-maximization":[75],"(EM)":[76],"algorithm":[77],"was":[78],"shown":[79],"robot":[83,132],"cope":[85],"with":[86,117,185],"sources.":[90],"face":[92],"developed":[95,154,177],"reliably":[100],"detect":[101],"several":[102],"the":[105,112,131,176,195],"skin":[106,129,136],"color":[107,121,137],"classification":[108],"obtained":[109],"by":[110,142],"EM":[113],"algorithm.":[114],"To":[115],"deal":[116],"change":[119],"state":[122],"according":[123],"illumination":[125],"condition":[126],"various":[128,186],"colors,":[130],"obtain":[134],"new":[135],"features":[138],"detected":[141],"OpenCV,":[143],"an":[144],"open":[145],"vision":[146],"library,":[147],"detecting":[149],"faces.":[151],"Finally,":[152],"probability":[156],"based":[157],"integrate":[160],"auditory":[161],"visual":[163],"information":[164],"produce":[167],"reliable":[169],"tracking":[170],"path":[171],"real":[173],"time.":[174],"Furthermore,":[175],"system":[178],"chose":[179],"tracked":[181],"people":[182],"while":[183],"dealing":[184],"background":[187],"noises":[188],"are":[190],"considered":[191],"loud,":[192],"even":[193]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
