{"id":"https://openalex.org/W7126395228","doi":"https://doi.org/10.1145/3784713.3784714","title":"Improved YOLOv10 Algorithm for Remote Sensing Object Detection","display_name":"Improved YOLOv10 Algorithm for Remote Sensing Object Detection","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W7126395228","doi":"https://doi.org/10.1145/3784713.3784714"},"language":null,"primary_location":{"id":"doi:10.1145/3784713.3784714","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784713.3784714","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 7th International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784713.3784714","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124554337","display_name":"Bolin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bolin Wang","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124553057","display_name":"Haowei Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haowei Wu","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124544352","display_name":"Yang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wu","raw_affiliation_strings":["Information Support Force Engineering University, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Information Support Force Engineering University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I75900474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5124554337"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72777351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8942999839782715,"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":0.8942999839782715,"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":0.010900000110268593,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.008899999782443047,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/feature","display_name":"Feature (linguistics)","score":0.6620000004768372},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6446999907493591},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4722999930381775},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4494999945163727},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4433000087738037},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39149999618530273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152000069618225},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6620000004768372},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6446999907493591},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5188999772071838},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.49309998750686646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4729999899864197},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42800000309944153},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3784713.3784714","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784713.3784714","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 7th International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3784713.3784714","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784713.3784714","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 7th International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2102605133","https://openalex.org/W2125556102","https://openalex.org/W2962749812","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963420686","https://openalex.org/W3094897602","https://openalex.org/W3155257528","https://openalex.org/W3176482836","https://openalex.org/W4394697163","https://openalex.org/W4402318494","https://openalex.org/W4415795831"],"related_works":[],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,32,76,100,135],"UAV":[3,136],"(Unmanned":[4],"Aerial":[5],"Vehicle)":[6],"remote":[7,137],"sensing":[8,138],"technology":[9],"has":[10],"led":[11],"to":[12],"an":[13,128],"increasing":[14],"need":[15],"for":[16,131],"lightweight":[17],"object":[18,34],"detection":[19,122],"algorithms.":[20],"To":[21],"address":[22],"the":[23,30,39,48,57,63,74,87,114,132],"computational":[24,125],"limitations":[25],"faced":[26],"by":[27,104,108],"UAVs":[28],"and":[29,54,59,80,106,124],"complexities":[31],"multi-scale":[33,68],"detection,":[35],"this":[36],"paper":[37],"proposes":[38],"Iterative":[40,49],"Attention":[41,50],"Fusion":[42,52],"YOLOv10":[43],"algorithm":[44,65,93],"(iFIA-YOLOv10).":[45],"By":[46],"incorporating":[47],"Feature":[51],"mechanism":[53],"coupled":[55],"with":[56],"Focaler-IoU":[58],"Inner-IoU":[60],"loss":[61],"functions,":[62],"proposed":[64,115],"exhibits":[66],"stronger":[67],"feature":[69,78],"interaction":[70],"capabilities,":[71],"effectively":[72],"mitigating":[73],"issues":[75],"small-target":[77],"suppression":[79],"large-target":[81],"localization":[82],"ambiguity.":[83],"Experimental":[84],"results":[85],"on":[86],"DOTA1.0":[88],"dataset":[89],"demonstrate":[90],"that":[91],"our":[92],"achieves":[94,117],"a":[95,118],"mean":[96],"Average":[97],"Precision":[98],"(mAP)":[99],"53.7%,":[101],"outperforming":[102],"YOLOv8":[103],"3.7%":[105],"TPH-YOLOv5":[107],"8.1%.":[109],"With":[110],"only":[111],"2.79M":[112],"parameters,":[113],"model":[116],"favorable":[119],"balance":[120],"between":[121],"accuracy":[123],"efficiency,":[126],"providing":[127],"efficient":[129],"solution":[130],"engineering":[133],"application":[134],"images.":[139]},"counts_by_year":[],"updated_date":"2026-02-03T00:53:05.648605","created_date":"2026-02-02T00:00:00"}