{"id":"https://openalex.org/W4391331281","doi":"https://doi.org/10.1109/smc53992.2023.10394568","title":"Improved YOLOv7 Based on Transformer for Object Detection in UAV-Captured Images","display_name":"Improved YOLOv7 Based on Transformer for Object Detection in UAV-Captured Images","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391331281","doi":"https://doi.org/10.1109/smc53992.2023.10394568"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10394568","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5044301562","display_name":"Yuefan Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuefan Luo","raw_affiliation_strings":["Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032308367","display_name":"Qing Zhu","orcid":"https://orcid.org/0000-0003-1237-2322"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Zhu","raw_affiliation_strings":["Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003351770","display_name":"Zhen Zhou","orcid":"https://orcid.org/0009-0001-2112-3742"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Zhou","raw_affiliation_strings":["Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100294139","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0001-5363-9981"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064079145","display_name":"Jiaming Zhou","orcid":"https://orcid.org/0000-0002-2758-8196"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":["Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022780668","display_name":"Tianjian Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjian Jiang","raw_affiliation_strings":["Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005222486","display_name":"Yijiang Li","orcid":"https://orcid.org/0000-0003-0644-7199"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijiang Li","raw_affiliation_strings":["Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083472752","display_name":"Danwei Wang","orcid":"https://orcid.org/0000-0001-9669-4622"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Danwei Wang","raw_affiliation_strings":["School of Electrical and Electrical Engineering, Nanyang Technological University,Singapore,Rep. of Singapore,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electrical Engineering, Nanyang Technological University,Singapore,Rep. of Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025640070","display_name":"Yaonan Wang","orcid":"https://orcid.org/0000-0002-0519-6458"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaonan Wang","raw_affiliation_strings":["Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,National Engineering Research Center for Robot Visual Perception and Control Technology,Changsha,Hunan,China,410082","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3152","last_page":"3157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9796000123023987,"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/T11133","display_name":"UAV Applications and Optimization","score":0.9775999784469604,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7951231002807617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7886807918548584},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.730580747127533},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.7289066314697266},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7172832489013672},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5576742887496948},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5056972503662109},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4443502426147461},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4412064850330353},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4270767867565155},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3616238236427307},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07647156715393066}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7951231002807617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886807918548584},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.730580747127533},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.7289066314697266},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7172832489013672},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5576742887496948},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5056972503662109},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4443502426147461},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4412064850330353},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4270767867565155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3616238236427307},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07647156715393066},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10394568","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4579539271","display_name":null,"funder_award_id":"2022YFB3303800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4800737940","display_name":null,"funder_award_id":"62076091","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2102605133","https://openalex.org/W2120419212","https://openalex.org/W2161969291","https://openalex.org/W2164598857","https://openalex.org/W2565639579","https://openalex.org/W2608264083","https://openalex.org/W2752782242","https://openalex.org/W2769291631","https://openalex.org/W2797090510","https://openalex.org/W2797527871","https://openalex.org/W2884585870","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963786238","https://openalex.org/W2964241181","https://openalex.org/W3018757597","https://openalex.org/W3096609285","https://openalex.org/W3106250896","https://openalex.org/W3109857485","https://openalex.org/W3153249728","https://openalex.org/W4200154072","https://openalex.org/W4293584584","https://openalex.org/W4385245566","https://openalex.org/W4385346076","https://openalex.org/W4386076325"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W4327774218","https://openalex.org/W2059768187","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4379143281","https://openalex.org/W2605096541","https://openalex.org/W2969228573","https://openalex.org/W2963690996"],"abstract_inverted_index":{"As":[0],"the":[1,20,32,43,59,107,116,125],"drone":[2,66],"captures":[3],"image":[4,33,90],"targets":[5],"at":[6],"different":[7],"flying":[8],"altitudes,":[9],"their":[10],"scales":[11],"may":[12],"vary":[13],"significantly,":[14],"which":[15],"can":[16,76],"pose":[17],"challenges":[18],"for":[19],"object":[21,63,73,87],"detection":[22,64],"model":[23],"to":[24,40,57,103,134],"accurately":[25],"detect":[26],"them.":[27],"Additionally,":[28],"tiny":[29,62,72,81,86,110],"objects":[30,82],"in":[31,65],"contain":[34],"minimal":[35],"information,":[36],"making":[37],"them":[38],"difficult":[39],"distinguish":[41,84],"from":[42],"background.":[44,91],"To":[45],"overcome":[46],"these":[47],"two":[48],"challenges,":[49],"we":[50,69],"proposed":[51,117],"a":[52,71,97],"network":[53],"architecture":[54],"that":[55,75,115],"aims":[56],"improve":[58],"accuracy":[60,121],"of":[61,80,109,122],"images.":[67],"Specially,":[68],"designed":[70],"detector(TOD)":[74],"effectively":[77],"extract":[78],"features":[79,88],"and":[83,89,128],"between":[85],"Furthermore,":[92],"this":[93],"TOD":[94],"module":[95],"contains":[96],"Convolutional":[98],"Visual":[99],"Attention":[100],"Network":[101],"(CVAN)":[102],"better":[104],"focus":[105],"on":[106,124],"regions":[108],"objects.":[111],"Experimental":[112],"results":[113],"demonstrate":[114],"method":[118],"achieves":[119],"mAP@.5":[120],"53.9%":[123],"VisDrone2021-test-dev":[126],"dataset":[127],"improves":[129],"by":[130],"2.8":[131],"%":[132],"compared":[133],"YOLOv7.":[135]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}