{"id":"https://openalex.org/W4392402424","doi":"https://doi.org/10.5220/0012570700003660","title":"Variational Autoencoders for Pedestrian Synthetic Data Augmentation of Existing Datasets: A Preliminary Investigation","display_name":"Variational Autoencoders for Pedestrian Synthetic Data Augmentation of Existing Datasets: A Preliminary Investigation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392402424","doi":"https://doi.org/10.5220/0012570700003660"},"language":"en","primary_location":{"id":"doi:10.5220/0012570700003660","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012570700003660","pdf_url":null,"source":null,"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 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.5220/0012570700003660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047753722","display_name":"I. Nikolov","orcid":"https://orcid.org/0000-0002-4952-8848"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Ivan Nikolov","raw_affiliation_strings":["Computer Graphics Group, Department of Architecture, Design and Media Technology, Aalborg University, Aalborg, Denmark, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Graphics Group, Department of Architecture, Design and Media Technology, Aalborg University, Aalborg, Denmark, --- Select a Country ---","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047753722"],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02606346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9577999711036682,"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"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9577999711036682,"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"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9470999836921692,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9101999998092651,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/pedestrian","display_name":"Pedestrian","score":0.7598159313201904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6791537404060364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5657041072845459},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4392586946487427},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.4243134558200836},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3997443616390228},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39918452501296997},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3409254252910614},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13876932859420776},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.05742371082305908}],"concepts":[{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.7598159313201904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791537404060364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5657041072845459},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4392586946487427},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.4243134558200836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3997443616390228},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39918452501296997},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3409254252910614},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13876932859420776},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.05742371082305908}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0012570700003660","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012570700003660","pdf_url":null,"source":null,"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 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/80ddfb4c-c6fb-4ccb-9107-5927af80c0c3","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/80ddfb4c-c6fb-4ccb-9107-5927af80c0c3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0012570700003660","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012570700003660","pdf_url":null,"source":null,"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 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.44999998807907104,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2392100589","https://openalex.org/W2512789322","https://openalex.org/W3122828758","https://openalex.org/W2101960027","https://openalex.org/W4205958986","https://openalex.org/W2197846993","https://openalex.org/W49697837","https://openalex.org/W2586575957","https://openalex.org/W2972620127","https://openalex.org/W2981141433"],"abstract_inverted_index":{"The":[0],"requirements":[1],"for":[2,7,63,185],"more":[3,5,22,44,138,183],"and":[4,12,21,29,47,83,116,146,158,179],"data":[6,42],"training":[8,84],"deep":[9],"learning":[10],"surveillance":[11],"object":[13],"detection":[14],"models":[15],"have":[16],"resulted":[17],"in":[18,58],"slower":[19],"deployment":[20],"costs":[23],"connected":[24],"to":[25,33,104,119,175],"dataset":[26,66],"gathering,":[27],"annotation,":[28],"testing.":[30],"One":[31],"way":[32],"help":[34],"with":[35],"this":[36,167,177],"is":[37],"the":[38,68,98,102,114,144,172],"use":[39,69],"of":[40,70,76,81,92,101,107,148,156,161,166,189],"synthetic":[41,60,162],"giving":[43],"varied":[45],"scenarios":[46],"not":[48,130],"requiring":[49],"manual":[50],"annotation.":[51],"We":[52,95,123],"present":[53],"our":[54],"initial":[55],"exploratory":[56],"work":[57],"generating":[59],"pedestrian":[61],"augmentations":[62],"an":[64],"existing":[65],"through":[67],"variational":[71,86],"autoencoders.":[72],"Our":[73],"method":[74],"consists":[75],"creating":[77],"a":[78,85,89,149,154,186],"large":[79],"number":[80],"backgrounds":[82],"autoencoder":[87,103],"on":[88,113,153],"small":[90,159],"subset":[91],"annotated":[93],"pedestrians.":[94],"then":[96],"interpolate":[97],"latent":[99],"space":[100],"generate":[105],"variations":[106],"these":[108],"pedestrians,":[109],"calculate":[110],"their":[111],"positions":[112],"backgrounds,":[115],"blend":[117],"them":[118],"create":[120],"new":[121],"images.":[122,163],"show":[124],"that":[125],"even":[126],"though":[127],"we":[128,141,169],"do":[129],"achieve":[131],"as":[132,135],"good":[133],"results":[134],"just":[136],"adding":[137],"real":[139,157],"images,":[140],"can":[142],"boost":[143],"performance":[145],"robustness":[147],"YoloV5":[150],"model":[151],"trained":[152],"mix":[155],"amounts":[160],"As":[164],"part":[165],"paper,":[168],"also":[170],"propose":[171],"next":[173],"steps":[174],"expand":[176],"approach":[178],"make":[180],"it":[181],"much":[182],"useful":[184],"wider":[187],"array":[188],"datasets.":[190]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}