{"id":"https://openalex.org/W4212799506","doi":"https://doi.org/10.5220/0010882700003124","title":"Combining Local and Global Pose Estimation for Precise Tracking of Similar Objects","display_name":"Combining Local and Global Pose Estimation for Precise Tracking of Similar Objects","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4212799506","doi":"https://doi.org/10.5220/0010882700003124"},"language":"en","primary_location":{"id":"doi:10.5220/0010882700003124","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010882700003124","pdf_url":null,"source":{"id":"https://openalex.org/S4363608825","display_name":"Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5220/0010882700003124","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009603026","display_name":"Niklas Gard","orcid":"https://orcid.org/0000-0002-0227-2857"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Niklas Gard","raw_affiliation_strings":["Vision and Imaging Technologies, Fraunhofer HHI, Einsteinufer 37, 10587 Berlin, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vision and Imaging Technologies, Fraunhofer HHI, Einsteinufer 37, 10587 Berlin, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074580099","display_name":"Anna Hilsmann","orcid":"https://orcid.org/0000-0002-2086-0951"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anna Hilsmann","raw_affiliation_strings":["Vision and Imaging Technologies, Fraunhofer HHI, Einsteinufer 37, 10587 Berlin, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vision and Imaging Technologies, Fraunhofer HHI, Einsteinufer 37, 10587 Berlin, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009614926","display_name":"Peter Eisert","orcid":"https://orcid.org/0000-0001-8378-4805"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Eisert","raw_affiliation_strings":["Institute for Computer Science, Humboldt University of Berlin, Unter den Linden 6, 10099 Berlin, Germany, --- Select a Country ---","Vision and Imaging Technologies, Fraunhofer HHI, Einsteinufer 37, 10587 Berlin, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computer Science, Humboldt University of Berlin, Unter den Linden 6, 10099 Berlin, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Vision and Imaging Technologies, Fraunhofer HHI, Einsteinufer 37, 10587 Berlin, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I2800274787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"745","last_page":"756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/pose","display_name":"Pose","score":0.8363445997238159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8076543807983398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7759426832199097},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7475054264068604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6925032734870911},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6789879202842712},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.6032782793045044},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.572537899017334},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.560314416885376},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.502234935760498},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46501877903938293},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43474602699279785},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.43006742000579834},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4191628396511078}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8363445997238159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076543807983398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7759426832199097},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7475054264068604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6925032734870911},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6789879202842712},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.6032782793045044},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.572537899017334},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.560314416885376},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.502234935760498},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46501877903938293},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43474602699279785},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.43006742000579834},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4191628396511078},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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:10.5220/0010882700003124","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010882700003124","pdf_url":null,"source":{"id":"https://openalex.org/S4363608825","display_name":"Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.13278","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.13278","pdf_url":"https://arxiv.org/pdf/2201.13278","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.5220/0010882700003124","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010882700003124","pdf_url":null,"source":{"id":"https://openalex.org/S4363608825","display_name":"Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1526868886","https://openalex.org/W1578285471","https://openalex.org/W1891950620","https://openalex.org/W1991544872","https://openalex.org/W1992706277","https://openalex.org/W2033959528","https://openalex.org/W2051460003","https://openalex.org/W2058009001","https://openalex.org/W2111479032","https://openalex.org/W2130943454","https://openalex.org/W2159751701","https://openalex.org/W2194775991","https://openalex.org/W2472269674","https://openalex.org/W2545656684","https://openalex.org/W2591860053","https://openalex.org/W2598042504","https://openalex.org/W2604236302","https://openalex.org/W2605102758","https://openalex.org/W2890035883","https://openalex.org/W2891547641","https://openalex.org/W2898071329","https://openalex.org/W2904008996","https://openalex.org/W2921365283","https://openalex.org/W2963188159","https://openalex.org/W2963756608","https://openalex.org/W2968638558","https://openalex.org/W2970399728","https://openalex.org/W2981378444","https://openalex.org/W2984042658","https://openalex.org/W2989915422","https://openalex.org/W2998787775","https://openalex.org/W3013928509","https://openalex.org/W3035355652","https://openalex.org/W3045003611","https://openalex.org/W3100052745","https://openalex.org/W3107730598","https://openalex.org/W3108326808","https://openalex.org/W3117567287","https://openalex.org/W3124643953","https://openalex.org/W3127669830","https://openalex.org/W3158252298","https://openalex.org/W3205232447","https://openalex.org/W4289489637","https://openalex.org/W4394666750"],"related_works":["https://openalex.org/W4253893311","https://openalex.org/W3089306886","https://openalex.org/W2113785214","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W4387967917","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4382141741","https://openalex.org/W2951583186"],"abstract_inverted_index":{"In":[0,73],"this":[1],"paper,":[2],"we":[3,145],"present":[4],"a":[5,21,33,82,128,154],"multi-object":[6],"6D":[7],"detection":[8,41],"and":[9,15,28,37,70,118],"tracking":[10,116],"pipeline":[11,117],"for":[12,25],"potentially":[13],"similar":[14,133],"non-textured":[16,132],"objects.":[17],"The":[18],"combination":[19],"of":[20,62,100,122,131,162],"convolutional":[22],"neural":[23],"network":[24,51],"object":[26,91],"classification":[27],"rough":[29],"pose":[30,35,60,76,104],"estimation":[31,61],"with":[32,55,65],"local":[34,83,101],"refinement":[36,85,102],"an":[38],"automatic":[39],"mismatch":[40],"enables":[42],"direct":[43],"application":[44,158],"in":[45,153],"real-time":[46],"AR":[47,156],"scenarios.":[48],"A":[49],"new":[50],"architecture,":[52],"trained":[53],"solely":[54],"synthetic":[56],"images,":[57],"allows":[58],"simultaneous":[59],"multiple":[63],"objects":[64,134],"reduced":[66],"GPU":[67],"memory":[68],"consumption":[69],"enhanced":[71,137],"performance.":[72],"addition,":[74],"the":[75,97,114,120,123,136,141,148,160],"estimates":[77],"are":[78],"further":[79],"improved":[80],"by":[81],"edge-based":[84],"step":[86],"that":[87],"explicitly":[88],"exploits":[89],"known":[90],"geometry":[92],"information.":[93],"For":[94],"continuous":[95],"movements,":[96],"sole":[98],"use":[99],"reduces":[103],"mismatches":[105],"due":[106],"to":[107,140],"geometric":[108],"ambiguities":[109],"or":[110],"occlusions.":[111],"We":[112],"showcase":[113],"entire":[115],"demonstrate":[119,135],"benefits":[121],"combined":[124],"approach.":[125],"Experiments":[126],"on":[127],"challenging":[129],"set":[130],"quality":[138],"compared":[139],"baseline":[142],"method.":[143],"Finally,":[144],"illustrate":[146],"how":[147],"system":[149],"can":[150],"be":[151],"used":[152],"real":[155],"assistance":[157],"within":[159],"field":[161],"construction.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}