{"id":"https://openalex.org/W3089109701","doi":"https://doi.org/10.2352/issn.2470-1173.2020.8.imawm-084","title":"A New Training Model for Object Detection in Aerial Images","display_name":"A New Training Model for Object Detection in Aerial Images","publication_year":2020,"publication_date":"2020-01-26","ids":{"openalex":"https://openalex.org/W3089109701","doi":"https://doi.org/10.2352/issn.2470-1173.2020.8.imawm-084","mag":"3089109701"},"language":"en","primary_location":{"id":"doi:10.2352/issn.2470-1173.2020.8.imawm-084","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2020.8.imawm-084","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/105547/1/EI_2020_art00002_Geng-YANG.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101848201","display_name":"Geng Yang","orcid":"https://orcid.org/0000-0001-7740-2401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng YANG","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009893012","display_name":"Yu Geng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Geng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101584016","display_name":"Qin Li","orcid":"https://orcid.org/0000-0001-5220-9090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin LI","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045562050","display_name":"Jane You","orcid":"https://orcid.org/0000-0002-8181-4836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jane YOU","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112568709","display_name":"Mingpeng Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingpeng Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10337581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"8","first_page":"84","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9966999888420105,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.995199978351593,"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/overfitting","display_name":"Overfitting","score":0.8091254830360413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7148321866989136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7015435695648193},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7005478143692017},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5916697978973389},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5820695757865906},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.5719527006149292},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5101054310798645},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47563838958740234},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47557488083839417},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4745921790599823},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4561779201030731},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4200802743434906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38171663880348206},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2790803611278534},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1991572380065918},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12473440170288086}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8091254830360413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7148321866989136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7015435695648193},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7005478143692017},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5916697978973389},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5820695757865906},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.5719527006149292},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5101054310798645},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47563838958740234},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47557488083839417},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4745921790599823},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4561779201030731},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4200802743434906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38171663880348206},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2790803611278534},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1991572380065918},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12473440170288086},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.2352/issn.2470-1173.2020.8.imawm-084","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2020.8.imawm-084","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/105547","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/105547","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/105547/1/EI_2020_art00002_Geng-YANG.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/105547","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/105547","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/105547/1/EI_2020_art00002_Geng-YANG.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"},{"id":"https://openalex.org/F4320335803","display_name":"Shenzhen Fundamental Research and Discipline Layout project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3089109701.pdf","grobid_xml":"https://content.openalex.org/works/W3089109701.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W4388103534","https://openalex.org/W4318142952","https://openalex.org/W4312531262","https://openalex.org/W2072070946","https://openalex.org/W3129453529"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,17,24,157],"new":[4,158],"training":[5,71,170],"model":[6],"for":[7,35,124,155],"orientation":[8],"invariant":[9],"object":[10,37],"detection":[11],"in":[12,63,75,83,86,136],"aerial":[13,64],"images":[14,72],"by":[15,122,164],"extending":[16],"deep":[18],"learning":[19,94,106],"based":[20,27],"RetinaNet":[21],"which":[22,41,179],"is":[23,96,108,161],"single-stage":[25],"detector":[26],"on":[28,66,141],"feature":[29,43],"pyramid":[30],"networks":[31],"and":[32,59,103,120,127,172,185],"focal":[33],"loss":[34],"dense":[36],"detection.":[38],"Unlike":[39],"R3Det":[40],"applies":[42],"refinement":[44],"to":[45,53,88,148],"handle":[46],"rotating":[47],"objects,":[48],"we":[49],"proposed":[50,116,193],"further":[51],"improvement":[52,135],"cope":[54],"with":[55,138],"the":[56,133,142,149,166,169,189,192],"densely":[57],"arranged":[58],"class":[60],"imbalance":[61],"problems":[62],"imaging,":[65],"three":[67],"aspects:":[68],"1)":[69],"All":[70],"are":[73,100,112],"traversed":[74],"each":[76,84],"iteration":[77,85],"instead":[78],"of":[79,177,191],"only":[80],"one":[81],"image":[82],"order":[87],"cover":[89],"all":[90],"possibilities;":[91],"2)":[92],"The":[93,105,115,129,175],"rate":[95,107],"reduced":[97,109],"if":[98,110],"losses":[99,111,178],"not":[101,113],"reduced;":[102],"3)":[104],"changed.":[114],"method":[117],"was":[118],"calibrated":[119],"validated":[121],"comprehensive":[123],"performance":[125],"evaluation":[126],"benchmarking.":[128],"experiment":[130],"results":[131],"demonstrate":[132],"significant":[134],"comparison":[137],"R3Dec":[139],"approach":[140],"same":[143],"data":[144,152,159],"set.":[145,174],"In":[146],"addition":[147],"well-known":[150],"public":[151],"set":[153,160,171],"DOTA":[154],"benchmarking,":[156],"also":[162,187],"established":[163],"considering":[165],"balance":[167],"between":[168],"testing":[173],"map":[176],"dropped":[180],"down":[181],"smoothly":[182],"without":[183],"jitter":[184],"overfitting":[186],"illustrates":[188],"advantages":[190],"newmodel.":[194]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}