{"id":"https://openalex.org/W4402264124","doi":"https://doi.org/10.1109/igarss53475.2024.10640832","title":"Detection of Small Objects from UAV Imagery via an Improved Swin Transformer","display_name":"Detection of Small Objects from UAV Imagery via an Improved Swin Transformer","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4402264124","doi":"https://doi.org/10.1109/igarss53475.2024.10640832"},"language":"en","primary_location":{"id":"doi:10.1109/igarss53475.2024.10640832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10640832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100303123","display_name":"Weidong Liang","orcid":"https://orcid.org/0000-0002-8290-3216"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Weidong Liang","raw_affiliation_strings":["University of Waterloo,Department of Systems Design Engineering,Waterloo,Canada,N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Systems Design Engineering,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114221504","display_name":"Jingtian Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jingtian Tan","raw_affiliation_strings":["University of Waterloo,Department of Geography and Environmental Management,Waterloo,Canada,N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Geography and Environmental Management,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049403375","display_name":"Hongjie He","orcid":"https://orcid.org/0000-0003-3839-5821"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hongjie He","raw_affiliation_strings":["University of Waterloo,Department of Geography and Environmental Management,Waterloo,Canada,N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Geography and Environmental Management,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017266329","display_name":"Hongzhang Xu","orcid":"https://orcid.org/0000-0002-6407-3917"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hongzhang Xu","raw_affiliation_strings":["University of Waterloo,Department of Geography and Environmental Management,Waterloo,Canada,N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Geography and Environmental Management,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100613889","display_name":"Jonathan Li","orcid":"https://orcid.org/0000-0001-7899-0049"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jonathan Li","raw_affiliation_strings":["University of Waterloo,Department of Systems Design Engineering,Waterloo,Canada,N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Systems Design Engineering,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":8.1628,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97891838,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9134","last_page":"9138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.6967072486877441},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5739079117774963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5297026634216309},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5247958898544312},{"id":"https://openalex.org/keywords/aerial-imagery","display_name":"Aerial imagery","score":0.41262906789779663},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13134276866912842},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09225189685821533},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07544821500778198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967072486877441},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5739079117774963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5297026634216309},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5247958898544312},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.41262906789779663},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13134276866912842},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09225189685821533},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07544821500778198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igarss53475.2024.10640832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10640832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2962777203","https://openalex.org/W2963470893","https://openalex.org/W2964101377","https://openalex.org/W2964241181","https://openalex.org/W2964444661","https://openalex.org/W3025800305","https://openalex.org/W3090286019","https://openalex.org/W3107867277","https://openalex.org/W3138516171","https://openalex.org/W3175515048","https://openalex.org/W3208645658","https://openalex.org/W4200335308","https://openalex.org/W4385245566","https://openalex.org/W6757817989","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2772917594","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Automated":[0],"detection":[1,58,104,115,233],"of":[2,10,22,74,101,130,137],"small":[3,68,102,231],"objects":[4,48],"such":[5],"as":[6],"vehicles":[7,18],"in":[8,27,49,77,108],"images":[9,51,110],"complex":[11,106],"urban":[12],"environments":[13],"taken":[14],"by":[15,196],"unmanned":[16],"aerial":[17],"(UAVs)":[19],"is":[20,60],"one":[21],"the":[23,72,90,99,114,119,126,133,179,192],"most":[24],"challenging":[25],"tasks":[26],"computer":[28],"vision":[29],"and":[30,111,132,151,182,199,213,220,228],"remote":[31],"sensing":[32],"communities.":[33],"Convolutional":[34],"neural":[35],"networks":[36],"(CNNs)-based":[37],"deep":[38],"learning":[39],"models":[40],"have":[41],"been":[42],"widely":[43],"used":[44],"to":[45,67,71,93],"automatically":[46],"detect":[47],"UAV":[50,109,180,235],"given":[52],"their":[53,57],"high":[54],"performance.":[55],"However,":[56],"accuracy":[59],"still":[61],"unsatisfactory,":[62],"particularly":[63],"when":[64],"it":[65,160],"comes":[66],"objects,":[69],"due":[70],"shortcomings":[73],"CNNs.":[75],"Therefore,":[76],"this":[78],"study,":[79],"we":[80],"propose":[81],"a":[82,145,152,162],"Swin":[83,91,120],"Transformer-based":[84],"model":[85,123],"that":[86,165,187],"incorporates":[87,161],"convolutions":[88,131],"with":[89,169,211,214],"Transformer":[92,217],"extract":[94],"more":[95],"local":[96,127],"information,":[97],"mitigating":[98],"problem":[100],"object":[103,232],"from":[105,234],"backgrounds":[107],"further":[112],"improving":[113],"accuracy.":[116],"By":[117],"using":[118],"Transformer,":[121],"our":[122,188],"leverages":[124],"both":[125],"feature":[128,135],"extraction":[129],"global":[134],"modeling":[136],"transformers.":[138],"The":[139],"framework":[140],"comprises":[141],"two":[142],"primary":[143],"modules:":[144],"Local":[146],"Context":[147],"Enhancement":[148],"(LCE)":[149],"module":[150],"Residual":[153],"U-Feature":[154],"Pyramid":[155,215],"Network":[156],"(RSU-FPN)":[157],"module.":[158],"Additionally,":[159],"loss":[163,168],"function":[164],"combines":[166],"L1":[167],"Normalized":[170],"Gaussian":[171],"Wasserstein":[172],"Distance.":[173],"Our":[174],"experimental":[175],"results":[176],"obtained":[177],"on":[178,230],"Detection":[181],"Tracking":[183],"(UAVDT)":[184],"dataset":[185],"indicated":[186],"proposed":[189],"method":[190],"increased":[191],"average":[193],"precision":[194],"(AP)":[195],"21.6%,":[197],"22.3%":[198],"25.5%":[200],"over":[201],"Cascade":[202],"Region-based":[203],"CNN":[204,209],"(R-CNN),":[205],"Faster":[206],"Region":[207],"based":[208],"(R-CNN)":[210],"ResNet-50":[212],"Vision":[216],"(PVT)":[218],"B0,":[219],"Dynamic":[221],"R-CNN":[222],"detectors,":[223],"respectively,":[224],"indicating":[225],"its":[226],"effectiveness":[227],"reliability":[229],"images.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}