{"id":"https://openalex.org/W2052324571","doi":"https://doi.org/10.1109/icip.2013.6738548","title":"Video tracking through occlusions by fast audio source localisation","display_name":"Video tracking through occlusions by fast audio source localisation","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2052324571","doi":"https://doi.org/10.1109/icip.2013.6738548","mag":"2052324571"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2013.6738548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2013.6738548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Image Processing","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/A5083533632","display_name":"Eleonora D'Arca","orcid":null},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]},{"id":"https://openalex.org/I4210085930","display_name":"Heriot-Watt University Malaysia","ror":"https://ror.org/0059w0420","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210085930"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","MY"],"is_corresponding":false,"raw_author_name":"Eleonora D'Arca","raw_affiliation_strings":["Joint Research Institute for Signal and Image Processing, Heriot-Watt University &amp; University of Edinburgh, UK","Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ. & Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Research Institute for Signal and Image Processing, Heriot-Watt University &amp; University of Edinburgh, UK","institution_ids":["https://openalex.org/I4210085930","https://openalex.org/I32062511"]},{"raw_affiliation_string":"Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ. & Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084447379","display_name":"Ashley M. Hughes","orcid":"https://orcid.org/0000-0002-1431-3396"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]},{"id":"https://openalex.org/I4210085930","display_name":"Heriot-Watt University Malaysia","ror":"https://ror.org/0059w0420","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210085930"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","MY"],"is_corresponding":false,"raw_author_name":"Ashley Hughes","raw_affiliation_strings":["Joint Research Institute for Signal and Image Processing, Heriot-Watt University &amp; University of Edinburgh, UK","Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ. & Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Research Institute for Signal and Image Processing, Heriot-Watt University &amp; University of Edinburgh, UK","institution_ids":["https://openalex.org/I4210085930","https://openalex.org/I32062511"]},{"raw_affiliation_string":"Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ. & Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102909686","display_name":"Neil M. Robertson","orcid":"https://orcid.org/0000-0003-2461-8799"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]},{"id":"https://openalex.org/I4210085930","display_name":"Heriot-Watt University Malaysia","ror":"https://ror.org/0059w0420","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210085930"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","MY"],"is_corresponding":false,"raw_author_name":"Neil M. Robertson","raw_affiliation_strings":["Joint Research Institute for Signal and Image Processing, Heriot-Watt University &amp; University of Edinburgh, UK","Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ. & Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Research Institute for Signal and Image Processing, Heriot-Watt University &amp; University of Edinburgh, UK","institution_ids":["https://openalex.org/I4210085930","https://openalex.org/I32062511"]},{"raw_affiliation_string":"Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ. & Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016434897","display_name":"James R. Hopgood","orcid":"https://orcid.org/0000-0002-3029-2425"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]},{"id":"https://openalex.org/I4210085930","display_name":"Heriot-Watt University Malaysia","ror":"https://ror.org/0059w0420","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210085930"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","MY"],"is_corresponding":false,"raw_author_name":"James Hopgood","raw_affiliation_strings":["Joint Research Institute for Signal and Image Processing, Heriot-Watt University &amp; University of Edinburgh, UK","Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ. & Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Research Institute for Signal and Image Processing, Heriot-Watt University &amp; University of Edinburgh, UK","institution_ids":["https://openalex.org/I4210085930","https://openalex.org/I32062511"]},{"raw_affiliation_string":"Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ. & Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9662,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75473441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2660","last_page":"2664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8319467306137085},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7385602593421936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6780188679695129},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.6169937252998352},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5484715700149536},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4192466735839844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38788890838623047},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3418794274330139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319467306137085},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7385602593421936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6780188679695129},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6169937252998352},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5484715700149536},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4192466735839844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38788890838623047},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3418794274330139},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip.2013.6738548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2013.6738548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Image Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/f06fbc16-8020-4f5b-8a74-20e5272f1f81","is_oa":false,"landing_page_url":"https://pure.qub.ac.uk/en/publications/f06fbc16-8020-4f5b-8a74-20e5272f1f81","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"D'Arca, E, Hughes, A, Robertson, N & Hopgood, J R 2013, 'Video tracking through occlusions by fast audio source localisation', pp. 2660--2664.","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8726282573","display_name":null,"funder_award_id":"EP/K014277/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1591726647","https://openalex.org/W1975143133","https://openalex.org/W1982547756","https://openalex.org/W2002827932","https://openalex.org/W2015293542","https://openalex.org/W2046317813","https://openalex.org/W2065274193","https://openalex.org/W2105582566","https://openalex.org/W2124781496","https://openalex.org/W2127025755","https://openalex.org/W2129866629","https://openalex.org/W2130357996","https://openalex.org/W2138414774","https://openalex.org/W2140647972","https://openalex.org/W2142612029","https://openalex.org/W2145097187","https://openalex.org/W2163141813","https://openalex.org/W2164865661","https://openalex.org/W2407461433","https://openalex.org/W2540622796","https://openalex.org/W2915347754","https://openalex.org/W6635336337","https://openalex.org/W6681054008","https://openalex.org/W6713775275"],"related_works":["https://openalex.org/W2084086966","https://openalex.org/W4285271403","https://openalex.org/W2542007731","https://openalex.org/W2968379562","https://openalex.org/W2091015105","https://openalex.org/W4388689193","https://openalex.org/W2110899030","https://openalex.org/W29633852","https://openalex.org/W2985362983","https://openalex.org/W4327670844"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,20,60,75,92,113,122],"novel":[6,21],"audio-visual":[7],"speaker":[8,31,154],"detection":[9,184],"and":[10,58,71,83,96,119,139,166,176],"localisation":[11],"algorithm.":[12],"Audio":[13],"source":[14],"position":[15],"estimates":[16,51],"are":[17],"computed":[18],"by":[19,39,164,186],"stochastic":[22],"region":[23,44],"contraction":[24,45],"(SRC)":[25],"audio":[26,34,70],"search":[27,35],"algorithm":[28,36],"for":[29],"accurate":[30],"localisation.":[32],"This":[33],"is":[37,89],"aided":[38],"available":[40],"video":[41,72,94,107,134],"information":[42],"(stochastic":[43],"with":[46],"height":[47],"estimation":[48],"(SRC-HE))":[49],"which":[50,79],"head":[52],"heights":[53],"over":[54,65,188],"the":[55,85,101,104,157,161],"whole":[56],"scene":[57],"gives":[59],"speed":[61],"improvement":[62],"of":[63,91,106,170],"56%":[64],"SRC.":[66,189],"We":[67,99,132],"finally":[68],"combine":[69],"data":[73],"in":[74,125,145,168],"Kalman":[76],"filter":[77],"(KF)":[78],"fuses":[80],"person-position":[81],"likelihoods":[82],"tracks":[84],"speaker.":[86],"Our":[87],"system":[88],"composed":[90],"single":[93],"camera":[95],"16":[97],"microphones.":[98],"validate":[100],"approach":[102],"on":[103,160],"problem":[105],"occlusion":[108,135],"i.e.":[109],"two":[110],"people":[111],"having":[112],"conversation":[114],"have":[115],"to":[116],"be":[117,137,142],"detected":[118],"localised":[120],"at":[121],"distance":[123],"(as":[124],"surveillance":[126],"scenarios":[127],"vs.":[128],"enclosed":[129],"meeting":[130],"rooms).":[131],"show":[133],"can":[136,141],"resolved":[138],"speakers":[140],"correctly":[143],"detected/localised":[144],"real":[146],"data.":[147],"Moreover,":[148],"SRC-HE":[149],"based":[150,159],"joint":[151],"audio-video":[152],"(AV)":[153],"tracking":[155,173,179],"outperforms":[156],"one":[158],"original":[162],"SRC":[163],"16%":[165],"4%":[167],"terms":[169],"multi":[171,177],"object":[172,178],"precision":[174],"(MOTP)":[175],"accuracy":[180],"(MOTA).":[181],"Speaker":[182],"change":[183],"improves":[185],"11%":[187]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
