{"id":"https://openalex.org/W4391620719","doi":"https://doi.org/10.1109/access.2024.3363413","title":"Enhancing UAV Aerial Image Analysis: Integrating Advanced SAHI Techniques With Real-Time Detection Models on the VisDrone Dataset","display_name":"Enhancing UAV Aerial Image Analysis: Integrating Advanced SAHI Techniques With Real-Time Detection Models on the VisDrone Dataset","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391620719","doi":"https://doi.org/10.1109/access.2024.3363413"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3363413","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3363413","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10423771.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10423771.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108999648","display_name":"MUHAMMAD MUZAMMUL","orcid":"https://orcid.org/0000-0002-9859-6054"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"M. Muzammul","raw_affiliation_strings":["Department of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062081377","display_name":"Abdulmohsen Algarni","orcid":"https://orcid.org/0000-0002-7556-958X"},"institutions":[{"id":"https://openalex.org/I82952536","display_name":"King Khalid University","ror":"https://ror.org/052kwzs30","country_code":"SA","type":"education","lineage":["https://openalex.org/I82952536"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Abdulmohsen Algarni","raw_affiliation_strings":["Department of Computer Science, King Khalid University, Abha, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, King Khalid University, Abha, Saudi Arabia","institution_ids":["https://openalex.org/I82952536"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091859381","display_name":"Yazeed Yasin Ghadi","orcid":"https://orcid.org/0000-0002-7121-495X"},"institutions":[{"id":"https://openalex.org/I161913731","display_name":"Al Ain University","ror":"https://ror.org/023abrt21","country_code":"AE","type":"education","lineage":["https://openalex.org/I161913731"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Yazeed Yasin Ghadi","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Al Ain University, Al Ain, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Al Ain University, Al Ain, United Arab Emirates","institution_ids":["https://openalex.org/I161913731"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073073869","display_name":"Muhammad Assam","orcid":"https://orcid.org/0000-0001-7331-5351"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muhammad Assam","raw_affiliation_strings":["Department of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108999648"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":73.9867,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.99926989,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"21621","last_page":"21633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.996399998664856,"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":0.996399998664856,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.995199978351593,"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/computer-science","display_name":"Computer science","score":0.7500057816505432},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.6475808024406433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6224588751792908},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5675696134567261},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4585340917110443},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44861119985580444},{"id":"https://openalex.org/keywords/aerial-imagery","display_name":"Aerial imagery","score":0.44328173995018005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.359785795211792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500057816505432},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.6475808024406433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6224588751792908},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5675696134567261},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4585340917110443},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44861119985580444},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.44328173995018005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.359785795211792}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3363413","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3363413","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10423771.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1a589668284f4a1ba999872e2c3eb420","is_oa":true,"landing_page_url":"https://doaj.org/article/1a589668284f4a1ba999872e2c3eb420","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":"IEEE Access, Vol 12, Pp 21621-21633 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3363413","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3363413","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10423771.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/6","display_name":"Clean water and sanitation"}],"awards":[{"id":"https://openalex.org/G1380584810","display_name":null,"funder_award_id":"R.G.P","funder_id":"https://openalex.org/F4320324433","funder_display_name":"King Khalid University"},{"id":"https://openalex.org/G2284997536","display_name":null,"funder_award_id":"RGP.2/549/44","funder_id":"https://openalex.org/F4320324433","funder_display_name":"King Khalid University"}],"funders":[{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"},{"id":"https://openalex.org/F4320324433","display_name":"King Khalid University","ror":"https://ror.org/052kwzs30"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391620719.pdf","grobid_xml":"https://content.openalex.org/works/W4391620719.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1945662732","https://openalex.org/W2545630289","https://openalex.org/W2788451552","https://openalex.org/W2973851319","https://openalex.org/W2986358680","https://openalex.org/W2992514052","https://openalex.org/W3011680783","https://openalex.org/W3014810590","https://openalex.org/W3047386722","https://openalex.org/W3147986556","https://openalex.org/W3210997334","https://openalex.org/W4214626977","https://openalex.org/W4225630686","https://openalex.org/W4280610169","https://openalex.org/W4283822762","https://openalex.org/W4293193591","https://openalex.org/W4309550045","https://openalex.org/W4312771325","https://openalex.org/W4313318248","https://openalex.org/W4313594102","https://openalex.org/W4319298454","https://openalex.org/W4321596265","https://openalex.org/W4322503836","https://openalex.org/W4377107818","https://openalex.org/W4383113433","https://openalex.org/W4383904388","https://openalex.org/W4385074390","https://openalex.org/W4387319246","https://openalex.org/W4387712936","https://openalex.org/W4402754006","https://openalex.org/W6846615964","https://openalex.org/W6851531119"],"related_works":["https://openalex.org/W4390482660","https://openalex.org/W2972256598","https://openalex.org/W2610408157","https://openalex.org/W4388813151","https://openalex.org/W4283696875","https://openalex.org/W2342958307","https://openalex.org/W2612465689","https://openalex.org/W4284972948","https://openalex.org/W4396860960","https://openalex.org/W4283327355"],"abstract_inverted_index":{"This":[0],"research":[1,100],"presents":[2],"a":[3,40,79,108,126,174,203],"groundbreaking":[4],"approach":[5],"in":[6,73,94,114,170,198,230],"aerial":[7,75,116,210],"image":[8,141,228],"analysis":[9,176,229],"by":[10,66],"integrating":[11,187],"the":[12,20,28,34,57,103,123,136,139,149,153,167,178,184,190,217],"Real-Time":[13],"Detection":[14],"and":[15,49,69,85,97,146,173,208],"Recognition":[16],"(RT-DETR-X)":[17],"model":[18,131],"with":[19,189],"Slicing":[21],"Aided":[22],"Hyper":[23],"Inference":[24],"(SAHI)":[25],"methodology,":[26],"utilizing":[27],"VisDrone-DET":[29,104],"dataset.":[30],"Aimed":[31],"at":[32],"enhancing":[33],"efficiency":[35],"of":[36,42,63,111,138,152,159,166,177,186],"drone":[37,199],"technology":[38],"across":[39],"spectrum":[41],"applications,":[43],"including":[44],"water":[45],"conservancy,":[46],"geological":[47],"exploration,":[48],"military":[50],"operations,":[51],"this":[52,181],"study":[53,134],"focuses":[54],"on":[55],"harnessing":[56],"real-time,":[58],"end-to-end":[59],"object":[60],"detection":[61,158,200,219],"capabilities":[62],"RT-DETR-X.":[64],"Characterized":[65],"its":[67],"high-speed":[68],"high-accuracy":[70],"performance,":[71],"particularly":[72],"UAV":[74,115,231],"photography,":[76],"RT-DETR-X":[77],"demonstrates":[78],"remarkable":[80],"54.8%":[81],"Average":[82],"Precision":[83],"(AP)":[84],"74":[86],"frames":[87],"per":[88],"second":[89],"(FPS),":[90],"surpassing":[91],"similar":[92],"models":[93],"both":[95],"speed":[96],"accuracy.":[98],"The":[99,133,193,212],"thoroughly":[101],"examines":[102],"dataset,":[105],"which":[106],"encompasses":[107],"diverse":[109],"range":[110],"small":[112],"targets":[113],"photography":[117],"scenes.":[118],"Covering":[119],"10":[120],"distinct":[121],"categories,":[122],"dataset":[124,142],"provides":[125],"robust":[127],"platform":[128],"for":[129,143,156,206,226],"rigorous":[130],"testing.":[132],"emphasizes":[135],"utilization":[137],"original":[140],"comprehensive":[144],"training":[145],"evaluation,":[147],"alongside":[148],"practical":[150],"implementation":[151],"SAHI":[154,191],"method":[155],"enhanced":[157],"small-scale":[160],"objects.":[161],"Through":[162],"an":[163],"in-depth":[164],"exploration":[165],"model\u2019s":[168,218],"performance":[169],"various":[171],"scenarios":[172],"detailed":[175],"environmental":[179],"setup,":[180],"paper":[182],"underscores":[183],"impact":[185],"RT-DETR":[188],"approach.":[192],"findings":[194],"reveal":[195],"significant":[196],"progress":[197],"technologies,":[201],"offering":[202],"holistic":[204],"framework":[205],"effective":[207],"efficient":[209],"surveillance.":[211],"integration":[213],"not":[214],"only":[215],"boosts":[216],"accuracy":[220],"but":[221],"also":[222],"opens":[223],"new":[224],"avenues":[225],"advanced":[227],"applications.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":9}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}