{"id":"https://openalex.org/W4416798615","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249079","title":"From Blurry to Brilliant Detection: YOLO-Based Aerial Object Detection with Super Resolution","display_name":"From Blurry to Brilliant Detection: YOLO-Based Aerial Object Detection with Super Resolution","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798615","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249079"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5001551009","display_name":"Ragib Amin Nihal","orcid":"https://orcid.org/0000-0002-3876-3033"},"institutions":[{"id":"https://openalex.org/I4210118579","display_name":"Systems Biology Institute","ror":"https://ror.org/02c7akf81","country_code":"JP","type":"nonprofit","lineage":["https://openalex.org/I4210118579"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ragib Amin Nihal","raw_affiliation_strings":["Institute of Science Tokyo,Systems and Control Engineering,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Systems and Control Engineering,Japan","institution_ids":["https://openalex.org/I4210118579"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042063575","display_name":"Benjamin Yen","orcid":"https://orcid.org/0000-0002-6958-7319"},"institutions":[{"id":"https://openalex.org/I4210118579","display_name":"Systems Biology Institute","ror":"https://ror.org/02c7akf81","country_code":"JP","type":"nonprofit","lineage":["https://openalex.org/I4210118579"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Benjamin Yen","raw_affiliation_strings":["Institute of Science Tokyo,Systems and Control Engineering,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Systems and Control Engineering,Japan","institution_ids":["https://openalex.org/I4210118579"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071399636","display_name":"Takeshi Ashizawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118579","display_name":"Systems Biology Institute","ror":"https://ror.org/02c7akf81","country_code":"JP","type":"nonprofit","lineage":["https://openalex.org/I4210118579"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Ashizawa","raw_affiliation_strings":["Institute of Science Tokyo,Systems and Control Engineering,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Systems and Control Engineering,Japan","institution_ids":["https://openalex.org/I4210118579"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"institutions":[{"id":"https://openalex.org/I4210118579","display_name":"Systems Biology Institute","ror":"https://ror.org/02c7akf81","country_code":"JP","type":"nonprofit","lineage":["https://openalex.org/I4210118579"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":["Institute of Science Tokyo,Systems and Control Engineering,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Systems and Control Engineering,Japan","institution_ids":["https://openalex.org/I4210118579"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I4210118579","display_name":"Systems Biology Institute","ror":"https://ror.org/02c7akf81","country_code":"JP","type":"nonprofit","lineage":["https://openalex.org/I4210118579"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Institute of Science Tokyo,Systems and Control Engineering,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Systems and Control Engineering,Japan","institution_ids":["https://openalex.org/I4210118579"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210118579"],"apc_list":null,"apc_paid":null,"fwci":2.6469,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91498842,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1922","last_page":"1927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.33820000290870667,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.33820000290870667,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.1940000057220459,"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/T11038","display_name":"Advanced SAR Imaging Techniques","score":0.1356000006198883,"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/object-detection","display_name":"Object detection","score":0.7128000259399414},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.6841999888420105},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5422999858856201},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5317000150680542},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5295000076293945},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5102999806404114},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.4781999886035919},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4740999937057495},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44769999384880066},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.421099990606308}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7694000005722046},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7128000259399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940000057220459},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6852999925613403},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.6841999888420105},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.4781999886035919},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44769999384880066},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4115000069141388},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.4009999930858612},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.3001999855041504},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C141239990","wikidata":"https://www.wikidata.org/wiki/Q957423","display_name":"Superresolution","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C159078339","wikidata":"https://www.wikidata.org/wiki/Q959005","display_name":"Hyperspectral imaging","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C38785706","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Interest point detection","level":5,"score":0.25589999556541443},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C39499422","wikidata":"https://www.wikidata.org/wiki/Q697320","display_name":"Corner detection","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2176924101","https://openalex.org/W2512351403","https://openalex.org/W2913012218","https://openalex.org/W2952773607","https://openalex.org/W2962749812","https://openalex.org/W2963470893","https://openalex.org/W3137565378","https://openalex.org/W3159166099","https://openalex.org/W3210586215","https://openalex.org/W4286433453","https://openalex.org/W4308516693","https://openalex.org/W4320002812","https://openalex.org/W4327785494","https://openalex.org/W4328125637","https://openalex.org/W4378222290","https://openalex.org/W4385423746","https://openalex.org/W4385801363","https://openalex.org/W4404891123"],"related_works":[],"abstract_inverted_index":{"Aerial":[0],"object":[1,7,173],"detection":[2,51,174],"presents":[3],"challenges":[4],"from":[5,16,70],"small":[6,172],"sizes,":[8],"high":[9],"density":[10],"clustering,":[11],"and":[12,18,89],"image":[13],"quality":[14],"degradation":[15],"distance":[17],"motion":[19],"blur.":[20],"These":[21],"factors":[22],"create":[23],"an":[24,53,84],"information":[25,69],"bottleneck":[26],"where":[27],"limited":[28],"pixel":[29],"representation":[30],"cannot":[31],"encode":[32],"sufficient":[33],"discriminative":[34],"features.":[35],"B2BDet":[36],"addresses":[37],"this":[38],"with":[39,80,103,160],"a":[40],"two-stage":[41],"framework":[42],"that":[43,61,119],"applies":[44],"domain-specific":[45],"super-resolution":[46,120],"during":[47],"inference,":[48],"followed":[49],"by":[50],"using":[52,111],"enhanced":[54],"YOLOv5":[55],"architecture.":[56],"Unlike":[57],"training-time":[58],"superresolution":[59],"approaches":[60,168],"enhance":[62],"learned":[63],"representations,":[64],"our":[65],"method":[66,156],"recovers":[67],"visual":[68],"each":[71],"input":[72],"image.":[73],"The":[74,155],"approach":[75],"combines":[76],"aerial-optimized":[77],"SRGAN":[78],"fine-tuning":[79],"architectural":[81,134],"innovations":[82],"including":[83],"Efficient":[85],"Attention":[86],"Module":[87],"(EAM)":[88],"Cross-Layer":[90],"Feature":[91],"Pyramid":[92],"Network":[93],"(CLFPN).":[94],"Evaluation":[95],"across":[96],"four":[97],"aerial":[98],"datasets":[99],"shows":[100],"performance":[101],"gains,":[102],"VisDrone":[104],"achieving":[105,170],"<tex":[106,123,137,144],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[107,124,138,145],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$52.5":[108],"\\%":[109],"\\text{mAP}$</tex>":[110],"only":[112],"27.7":[113],"M":[114],"parameters.":[115],"Ablation":[116],"studies":[117],"show":[118],"preprocessing":[121],"contributes":[122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{+":[125,139,146],"2.":[126,140],"6":[127],"\\%}":[128],"\\mathbf{m":[129],"A":[130],"P}$</tex>":[131],"improvement":[132,151],"while":[133,169],"enhancements":[135],"add":[136],"9":[141],"\\%}$</tex>,":[142],"yielding":[143],"5.":[147],"5":[148],"\\%}$</tex>":[149],"total":[150],"over":[152],"baseline":[153],"YOLOv5.":[154],"achieves":[157],"computational":[158],"efficiency":[159],"53.8":[161],"%":[162],"parameter":[163],"reduction":[164],"compared":[165],"to":[166],"recent":[167],"strong":[171],"performance.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}