{"id":"https://openalex.org/W4385422154","doi":"https://doi.org/10.3390/rs15153778","title":"YOLO-ViT-Based Method for Unmanned Aerial Vehicle Infrared Vehicle Target Detection","display_name":"YOLO-ViT-Based Method for Unmanned Aerial Vehicle Infrared Vehicle Target Detection","publication_year":2023,"publication_date":"2023-07-29","ids":{"openalex":"https://openalex.org/W4385422154","doi":"https://doi.org/10.3390/rs15153778"},"language":"en","primary_location":{"id":"doi:10.3390/rs15153778","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15153778","pdf_url":"https://www.mdpi.com/2072-4292/15/15/3778/pdf?version=1690625644","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/15/15/3778/pdf?version=1690625644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025545388","display_name":"Xiaofeng Zhao","orcid":"https://orcid.org/0000-0003-0316-7220"},"institutions":[{"id":"https://openalex.org/I4210130660","display_name":"Xi'an High Tech University","ror":"https://ror.org/03vt7za95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210130660"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Zhao","raw_affiliation_strings":["Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","Xi'an Research Institute of High-Tech, Xi'an 710025, China"],"affiliations":[{"raw_affiliation_string":"Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","institution_ids":["https://openalex.org/I4210130660"]},{"raw_affiliation_string":"Xi'an Research Institute of High-Tech, Xi'an 710025, China","institution_ids":["https://openalex.org/I4210130660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083751702","display_name":"Yuting Xia","orcid":"https://orcid.org/0000-0002-1681-2869"},"institutions":[{"id":"https://openalex.org/I4210130660","display_name":"Xi'an High Tech University","ror":"https://ror.org/03vt7za95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210130660"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuting Xia","raw_affiliation_strings":["Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","Xi'an Research Institute of High-Tech, Xi'an 710025, China"],"affiliations":[{"raw_affiliation_string":"Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","institution_ids":["https://openalex.org/I4210130660"]},{"raw_affiliation_string":"Xi'an Research Institute of High-Tech, Xi'an 710025, China","institution_ids":["https://openalex.org/I4210130660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401859","display_name":"Wenwen Zhang","orcid":"https://orcid.org/0000-0002-3183-0344"},"institutions":[{"id":"https://openalex.org/I4210130660","display_name":"Xi'an High Tech University","ror":"https://ror.org/03vt7za95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210130660"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwen Zhang","raw_affiliation_strings":["Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","Xi'an Research Institute of High-Tech, Xi'an 710025, China"],"affiliations":[{"raw_affiliation_string":"Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","institution_ids":["https://openalex.org/I4210130660"]},{"raw_affiliation_string":"Xi'an Research Institute of High-Tech, Xi'an 710025, China","institution_ids":["https://openalex.org/I4210130660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325387","display_name":"Chao Zheng","orcid":"https://orcid.org/0000-0002-9981-4623"},"institutions":[{"id":"https://openalex.org/I4210130660","display_name":"Xi'an High Tech University","ror":"https://ror.org/03vt7za95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210130660"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zheng","raw_affiliation_strings":["Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","Xi'an Research Institute of High-Tech, Xi'an 710025, China"],"affiliations":[{"raw_affiliation_string":"Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","institution_ids":["https://openalex.org/I4210130660"]},{"raw_affiliation_string":"Xi'an Research Institute of High-Tech, Xi'an 710025, China","institution_ids":["https://openalex.org/I4210130660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100622105","display_name":"Zhili Zhang","orcid":"https://orcid.org/0000-0003-4894-5495"},"institutions":[{"id":"https://openalex.org/I4210130660","display_name":"Xi'an High Tech University","ror":"https://ror.org/03vt7za95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210130660"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhili Zhang","raw_affiliation_strings":["Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","Xi'an Research Institute of High-Tech, Xi'an 710025, China"],"affiliations":[{"raw_affiliation_string":"Xi\u2019an Research Institute of High-Tech, Xi\u2019an 710025, China","institution_ids":["https://openalex.org/I4210130660"]},{"raw_affiliation_string":"Xi'an Research Institute of High-Tech, Xi'an 710025, China","institution_ids":["https://openalex.org/I4210130660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083751702"],"corresponding_institution_ids":["https://openalex.org/I4210130660"],"apc_list":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":57.2021,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":{"value":0.99894615,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"15","issue":"15","first_page":"3778","last_page":"3778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9944999814033508,"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":0.983299970626831,"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":0.7794754505157471},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.707317054271698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.659041166305542},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5840730667114258},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.4724422097206116},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4601936638355255},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4558880925178528},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4551721215248108},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4400157034397125},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4207857847213745},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2107885181903839}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794754505157471},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.707317054271698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.659041166305542},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5840730667114258},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.4724422097206116},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4601936638355255},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4558880925178528},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4551721215248108},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4400157034397125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4207857847213745},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2107885181903839},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/rs15153778","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15153778","pdf_url":"https://www.mdpi.com/2072-4292/15/15/3778/pdf?version=1690625644","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:62544d2ae1f348feb85ba214ffcd3814","is_oa":true,"landing_page_url":"https://doaj.org/article/62544d2ae1f348feb85ba214ffcd3814","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 15, Iss 15, p 3778 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2072-4292/15/15/3778/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/rs15153778","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing; Volume 15; Issue 15; Pages: 3778","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/rs15153778","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15153778","pdf_url":"https://www.mdpi.com/2072-4292/15/15/3778/pdf?version=1690625644","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6085767305","display_name":null,"funder_award_id":"41404022","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"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385422154.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2102605133","https://openalex.org/W2587248218","https://openalex.org/W2963037989","https://openalex.org/W2963163009","https://openalex.org/W2963456480","https://openalex.org/W2979709753","https://openalex.org/W2987322772","https://openalex.org/W3110751712","https://openalex.org/W3118249006","https://openalex.org/W3121523901","https://openalex.org/W3125939453","https://openalex.org/W3131500599","https://openalex.org/W3157183890","https://openalex.org/W3164012963","https://openalex.org/W3198011468","https://openalex.org/W3201115457","https://openalex.org/W3206023204","https://openalex.org/W3210997334","https://openalex.org/W4221057665","https://openalex.org/W4225315053","https://openalex.org/W4282571178","https://openalex.org/W4285804308","https://openalex.org/W4286433453","https://openalex.org/W4286630479","https://openalex.org/W4288067097","https://openalex.org/W4313065862","https://openalex.org/W4313467118","https://openalex.org/W4319303306","https://openalex.org/W4319786986","https://openalex.org/W4323317962","https://openalex.org/W4324148989","https://openalex.org/W4328125637","https://openalex.org/W4362500802","https://openalex.org/W4366598917","https://openalex.org/W4385994788","https://openalex.org/W4398180460","https://openalex.org/W6668990524","https://openalex.org/W6679436768","https://openalex.org/W6810436493"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W3176213335","https://openalex.org/W2894651257","https://openalex.org/W3200590620","https://openalex.org/W4200172193","https://openalex.org/W4303926741"],"abstract_inverted_index":{"The":[0,184,199],"detection":[1,44,182],"of":[2,14,25,81,88,122,168,194,219,237,246,252],"infrared":[3,47,176,257],"vehicle":[4,48,258],"targets":[5,49,146,177],"by":[6,221,226],"UAVs":[7],"poses":[8],"significant":[9],"challenges":[10],"in":[11,30,112,143,207,216],"the":[12,58,61,68,76,82,86,89,103,109,113,118,123,129,132,140,152,160,166,192,195,203,210,217,229,240,250,253],"presence":[13],"complex":[15],"ground":[16],"backgrounds,":[17],"high":[18,31],"target":[19,43,124,259],"density,":[20],"and":[21,78,84,116,147,223],"a":[22,39,214,244],"large":[23],"proportion":[24],"small":[26,145,175],"targets,":[27],"which":[28,52,101,248],"result":[29],"false":[32],"alarm":[33],"rates.":[34],"To":[35],"alleviate":[36],"these":[37],"deficiencies,":[38],"novel":[40],"YOLOv7-based,":[41],"multi-scale":[42],"method":[45,106,155,254],"for":[46,173,255],"is":[50,53,65,98,156],"proposed,":[51],"termed":[54],"YOLO-ViT.":[55],"Firstly,":[56],"within":[57],"YOLOV7-based":[59],"framework,":[60],"lightweight":[62],"MobileViT":[63],"network":[64,72,96],"incorporated":[66],"as":[67],"feature":[69,114],"extraction":[70],"backbone":[71],"to":[73,107,138,158,165,209],"fully":[74],"extract":[75],"local":[77],"global":[79],"features":[80],"object":[83],"reduce":[85],"complexity":[87],"model.":[90],"Secondly,":[91],"an":[92,235],"innovative":[93],"C3-PANet":[94],"neural":[95],"structure":[97],"delicately":[99],"designed,":[100],"adopts":[102],"CARAFE":[104],"upsampling":[105],"utilize":[108],"semantic":[110],"information":[111],"map":[115],"improve":[117],"model\u2019s":[119],"recognition":[120],"accuracy":[121,142],"region.":[125],"In":[126],"conjunction":[127],"with":[128],"C3":[130],"structure,":[131],"receptive":[133],"field":[134],"will":[135],"be":[136],"increased":[137],"enhance":[139],"network\u2019s":[141],"recognizing":[144],"model":[148],"generalization":[149],"ability.":[150],"Finally,":[151],"K-means++":[153],"clustering":[154],"utilized":[157],"optimize":[159],"anchor":[161,169],"box":[162],"size,":[163],"leading":[164],"design":[167],"boxes":[170],"better":[171],"suited":[172],"detecting":[174],"from":[178],"UAVs,":[179],"thereby":[180],"improving":[181],"efficiency.":[183],"present":[185],"article":[186],"showcases":[187],"experimental":[188],"findings":[189],"attained":[190],"through":[191],"use":[193],"HIT-UAV":[196],"public":[197],"dataset.":[198],"results":[200],"demonstrate":[201],"that":[202],"enhanced":[204],"YOLO-ViT":[205],"approach,":[206],"comparison":[208],"original":[211],"method,":[212],"achieves":[213],"reduction":[215],"number":[218],"parameters":[220],"49.9%":[222],"floating-point":[224],"operations":[225],"67.9%.":[227],"Furthermore,":[228],"mean":[230],"average":[231],"precision":[232],"(mAP)":[233],"exhibits":[234],"improvement":[236],"0.9%":[238],"over":[239],"existing":[241],"algorithm,":[242],"reaching":[243],"value":[245],"94.5%,":[247],"validates":[249],"effectiveness":[251],"UAV":[256],"detection.":[260]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}