{"id":"https://openalex.org/W4319990398","doi":"https://doi.org/10.1109/tim.2023.3241825","title":"Real-Time Object Detection Network in UAV-Vision Based on CNN and Transformer","display_name":"Real-Time Object Detection Network in UAV-Vision Based on CNN and Transformer","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4319990398","doi":"https://doi.org/10.1109/tim.2023.3241825"},"language":"en","primary_location":{"id":"doi:10.1109/tim.2023.3241825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2023.3241825","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Instrumentation and Measurement","raw_type":"journal-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/A5100419650","display_name":"Tao Ye","orcid":"https://orcid.org/0000-0002-1814-530X"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]},{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Ye","raw_affiliation_strings":["School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China","State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1814-530X","affiliations":[{"raw_affiliation_string":"School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]},{"raw_affiliation_string":"State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065969806","display_name":"Wenyang Qin","orcid":"https://orcid.org/0000-0003-1086-7321"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]},{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyang Qin","raw_affiliation_strings":["School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China","Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1086-7321","affiliations":[{"raw_affiliation_string":"School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043083428","display_name":"Zongyang Zhao","orcid":"https://orcid.org/0000-0002-0318-3549"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]},{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongyang Zhao","raw_affiliation_strings":["School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China","State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0318-3549","affiliations":[{"raw_affiliation_string":"School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]},{"raw_affiliation_string":"State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061333610","display_name":"Xiaozhi Gao","orcid":"https://orcid.org/0000-0001-5843-2832"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiaozhi Gao","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Kuopio, Finland"],"raw_orcid":"https://orcid.org/0000-0001-5843-2832","affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Kuopio, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049420539","display_name":"Xiangpeng Deng","orcid":"https://orcid.org/0000-0002-1035-4668"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]},{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangpeng Deng","raw_affiliation_strings":["School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China","Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1035-4668","affiliations":[{"raw_affiliation_string":"School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058619128","display_name":"Yu Ouyang","orcid":"https://orcid.org/0000-0002-8329-0562"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]},{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Ouyang","raw_affiliation_strings":["School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China","Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8329-0562","affiliations":[{"raw_affiliation_string":"School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"State Key Laboratory of Coal Mining and Clean Utilization, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Intelligent Mining and Robotics, Ministry of Emergency Management, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.4905,"has_fulltext":false,"cited_by_count":147,"citation_normalized_percentile":{"value":0.99494469,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"72","issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9973000288009644,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9970999956130981,"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":0.8127790689468384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6672853231430054},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5955116152763367},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5787127614021301},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5760117173194885},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.566912055015564},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5293964743614197},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.43429073691368103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3503686487674713},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10368648171424866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127790689468384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6672853231430054},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5955116152763367},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5787127614021301},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5760117173194885},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.566912055015564},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5293964743614197},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.43429073691368103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3503686487674713},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10368648171424866},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tim.2023.3241825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2023.3241825","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Instrumentation and Measurement","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G605670348","display_name":null,"funder_award_id":"2021-CMCU-KF012","funder_id":"https://openalex.org/F4320327474","funder_display_name":"State Key Laboratory of Coal Combustion"},{"id":"https://openalex.org/G8796064408","display_name":null,"funder_award_id":"L221018","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320327474","display_name":"State Key Laboratory of Coal Combustion","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1503655232","https://openalex.org/W1536680647","https://openalex.org/W1965877721","https://openalex.org/W2043552486","https://openalex.org/W2102605133","https://openalex.org/W2194775991","https://openalex.org/W2502312327","https://openalex.org/W2510352715","https://openalex.org/W2546888793","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2605995529","https://openalex.org/W2792542990","https://openalex.org/W2894878591","https://openalex.org/W2899607431","https://openalex.org/W2963037989","https://openalex.org/W2963346150","https://openalex.org/W2963351448","https://openalex.org/W2963681621","https://openalex.org/W2963857746","https://openalex.org/W2964444661","https://openalex.org/W2966102073","https://openalex.org/W3034971973","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3103461182","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3141511756","https://openalex.org/W3172509117","https://openalex.org/W3199346931","https://openalex.org/W3203974803","https://openalex.org/W3210586215","https://openalex.org/W3215916782","https://openalex.org/W4214493665","https://openalex.org/W4221138453","https://openalex.org/W4288325606","https://openalex.org/W4289792659","https://openalex.org/W4293584584","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6714138976","https://openalex.org/W6724804524","https://openalex.org/W6750227808","https://openalex.org/W6784094891","https://openalex.org/W6788135285","https://openalex.org/W6792401950","https://openalex.org/W6795463671","https://openalex.org/W6801484901","https://openalex.org/W6804061671"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4313906399","https://openalex.org/W4321487865","https://openalex.org/W2811106690","https://openalex.org/W4239306820","https://openalex.org/W2947043951","https://openalex.org/W2318112981","https://openalex.org/W4312417841","https://openalex.org/W4225147082","https://openalex.org/W2969228573"],"abstract_inverted_index":{"Unmanned":[0],"aerial":[1],"vehicles":[2],"(UAVs)":[3],"play":[4],"an":[5,152,209],"important":[6],"role":[7],"in":[8,45,53,184,232,248,270],"conducting":[9],"automatic":[10],"patrol":[11],"inspections":[12],"of":[13,20,30,88,91,115,146,149,169,177,203,225,242,260,267],"cities,":[14],"which":[15,197],"can":[16,198],"ensure":[17],"the":[18,27,34,86,111,132,137,144,166,174,185,194,218,223,226,271],"safety":[19],"urban":[21],"residents\u2019":[22],"life":[23],"and":[24,26,59,103,109,140,263],"property":[25],"normal":[28],"operation":[29],"cities.":[31],"However,":[32],"during":[33],"inspection":[35],"process,":[36],"problems":[37],"may":[38],"arise.":[39],"For":[40],"example,":[41],"numerous":[42],"small":[43,92,116],"objects":[44,52,171],"UAV":[46,54,80,250],"images":[47,55],"are":[48,56,64],"difficult":[49],"to":[50,83,101,130,135,164,192,221,228],"detect,":[51],"severely":[57],"occluded,":[58],"requirements":[60],"for":[61,79],"real-time":[62,74,120],"performances":[63],"posed.":[65],"To":[66,118,142],"address":[67],"these":[68],"issues,":[69],"we":[70,94,122],"first":[71],"propose":[72],"a":[73,96,124,200,239,257,264],"object":[75],"detection":[76,240,258,265],"network":[77,134],"(RTD-Net)":[78],"images.":[81],"Besides,":[82],"deal":[84],"with":[85,180],"lack":[87],"visual":[89],"features":[90,105,148],"objects,":[93,151],"design":[95,123],"feature":[97,112,126],"fusion":[98],"module":[99,128],"(FFM)":[100],"interact":[102],"fuse":[104],"at":[106],"different":[107],"levels":[108],"improve":[110,165,222],"expression":[113],"ability":[114,168,224],"objects.":[117,178],"achieve":[119],"detection,":[121],"lightweight":[125],"extraction":[127],"(LEM)":[129],"build":[131],"backbone":[133],"control":[136],"calculation":[138,204],"quantity":[139],"parameters.":[141],"solve":[143],"issue":[145],"discontinuous":[147],"occluded":[150,170],"efficient":[153],"convolutional":[154,158,190],"transformer":[155],"block":[156],"(ECTB)-based":[157],"multihead":[159,181],"self-attention":[160,182],"(CMHSA)":[161],"is":[162,214],"designed":[163,215],"recognition":[167],"by":[172],"extracting":[173],"context":[175],"information":[176],"Compared":[179],"(MHSA)":[183],"traditional":[186],"transformer,":[187],"CMHSA":[188],"uses":[189],"projection":[191],"replace":[193],"position-linear":[195],"projection,":[196],"reduce":[199],"large":[201],"amount":[202],"without":[205],"performance":[206],"loss.":[207],"Finally,":[208],"attention":[210,219,230],"prediction":[211],"head":[212],"(APH)":[213],"based":[216],"on":[217],"mechanism":[220],"model":[227],"extract":[229],"regions":[231],"complex":[233],"scenarios.":[234],"The":[235],"proposed":[236],"method":[237],"reaches":[238],"accuracy":[241,259],"86.4%":[243],"mean":[244],"average":[245],"precision":[246],"(mAP)":[247],"our":[249],"image":[251],"dataset.":[252],"In":[253],"addition,":[254],"it":[255],"achieves":[256],"86.0%":[261],"mAP":[262],"speed":[266],"33.4":[268],"frames/s":[269],"NVIDIA":[272],"Jeston":[273],"TX2":[274],"embedded":[275],"device.":[276]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":76},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":10}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}