{"id":"https://openalex.org/W99487261","doi":null,"title":"Object Localization by Joint Audio-Video Signal Processing.","display_name":"Object Localization by Joint Audio-Video Signal Processing.","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W99487261","mag":"99487261"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.142.132","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lnt.de/LMS/publications/web/lnt2000_035.ps.gz","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5100458580","display_name":"Guangyu Wang","orcid":"https://orcid.org/0009-0000-5674-2642","observed_orcids":["https://orcid.org/0009-0000-5674-2642"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangyu Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0000-5674-2642","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051526773","display_name":"Rudolf Rabenstein","orcid":"https://orcid.org/0000-0002-4348-1225","observed_orcids":["https://orcid.org/0000-0002-4348-1225"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rudolf Rabenstein","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4348-1225","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008239821","display_name":"Norbert K. Strobel","orcid":"https://orcid.org/0000-0001-7319-799X","observed_orcids":["https://orcid.org/0000-0001-7319-799X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Norbert Strobel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031403634","display_name":"Sascha Spors","orcid":"https://orcid.org/0000-0001-7225-9992","observed_orcids":["https://orcid.org/0000-0001-7225-9992"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sascha Spors","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7225-9992","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8332,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76470342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.7505000233650208,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.7505000233650208,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10860","display_name":"Speech and Audio Processing","score":0.21439999341964722,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.011500000022351742,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/object-localization","display_name":"object localization","score":0.9860000014305115},{"id":"https://openalex.org/keywords/audio-video-fusion","display_name":"audio-video fusion","score":0.722000002861023},{"id":"https://openalex.org/keywords/sound-localization","display_name":"sound localization","score":0.75},{"id":"https://openalex.org/keywords/object-tracking","display_name":"object tracking","score":0.6679999828338623},{"id":"https://openalex.org/keywords/decentralized-kalman-filter","display_name":"decentralized Kalman filter","score":0.9599999785423279},{"id":"https://openalex.org/keywords/data-fusion","display_name":"data fusion","score":0.6830000281333923},{"id":"https://openalex.org/keywords/state-estimation","display_name":"state estimation","score":0.8790000081062317},{"id":"https://openalex.org/keywords/multimodal-sensor-fusion","display_name":"multimodal sensor fusion","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7356340289115906},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.6847432851791382},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6755470037460327},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5348327159881592},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49930477142333984},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49217382073402405},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.48236697912216187},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4397920072078705},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4161493182182312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3906494975090027},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.39002084732055664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3486219644546509},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.2722471058368683},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2615625858306885},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.25968682765960693},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08370980620384216},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.142.132","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lnt.de/LMS/publications/web/lnt2000_035.ps.gz","raw_type":"text"},{"id":"mag:99487261","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/vmv/vmv2000.html#WangRSS00","pdf_url":null,"source":{"id":"https://openalex.org/S4306421152","display_name":"Vision Modeling and Visualization","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Vision Modeling and Visualization","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7098359087","https://openalex.org/W2011594914","https://openalex.org/W1661382514","https://openalex.org/W1589387574","https://openalex.org/W2149698446","https://openalex.org/W2129866629","https://openalex.org/W2147704751","https://openalex.org/W2988057920","https://openalex.org/W2219986622","https://openalex.org/W7097856784"],"abstract_inverted_index":{"Abstract":[0],"There":[1],"are":[2,99],"many":[3,173],"different":[4],"approaches":[5],"either":[6],"for":[7,14,38,48,107,178],"the":[8,49,70,80,83,95,111,115,123,171],"localization":[9,72,129,143,180],"of":[10,16,51,82,159,165],"sound":[11],"sources":[12],"or":[13,35,136],"tracking":[15],"visible":[17],"objects":[18],"in":[19,102,154],"image":[20],"sequences.":[21],"However,":[22],"most":[23],"applications":[24],"use":[25],"only":[26,33],"one":[27],"modality,":[28],"that":[29,122],"is,":[30],"they":[31],"process":[32],"audio":[34,89,135,146,183],"video":[36,91,137,148,162],"information":[37,92,138,149],"object":[39,52,71,84,179],"localization.":[40],"In":[41,170],"this":[42],"paper":[43],"we":[44,113],"introduce":[45],"a":[46,63,103],"method":[47],"estimation":[50,117,125],"positions":[53],"based":[54,87,144,181],"on":[55,88,145,182],"joint":[56,116,124],"audio-video":[57],"information.":[58],"The":[59],"key":[60],"technique":[61],"is":[62,74,85,150],"modified":[64],"decentralized":[65,104],"Kalman":[66,105],"filter":[67,106],"(MDKF),":[68],"where":[69],"problem":[73],"viewed":[75],"as":[76],"state":[77],"estimation.":[78],"First,":[79],"position":[81],"estimated":[86,97],"and":[90,147,168],"separately.":[93],"Then,":[94],"locally":[96],"results":[98,130],"further":[100],"processed":[101],"data":[108],"fusion.":[109],"At":[110],"output":[112],"obtain":[114],"results.":[118],"Experiments":[119],"have":[120,175],"shown":[121],"provides":[126],"more":[127],"correct":[128],"than":[131],"obtained":[132],"by":[133],"using":[134],"only.":[139],"1":[140],"Introduction":[141],"Object":[142],"an":[151],"important":[152],"topic":[153],"various":[155],"applications,":[156],"e.g.":[157],"analysis":[158,164],"dynamic":[160],"scenes,":[161],"conferences,":[163],"traffic":[166],"situations,":[167],"others.":[169],"past,":[172],"methods":[174],"been":[176],"reported":[177]},"counts_by_year":[],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2016-06-24T00:00:00"}