{"id":"https://openalex.org/W4392904697","doi":"https://doi.org/10.1109/icassp48485.2024.10448458","title":"Sod-Uav: Small Object Detection For Unmanned Aerial Vehicle Images Via Improved Yolov7","display_name":"Sod-Uav: Small Object Detection For Unmanned Aerial Vehicle Images Via Improved Yolov7","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904697","doi":"https://doi.org/10.1109/icassp48485.2024.10448458"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100340449","display_name":"Yujie Li","orcid":"https://orcid.org/0000-0002-5801-4937"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Li","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613594","display_name":"Yifu Wang","orcid":"https://orcid.org/0000-0001-5937-2261"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifu Wang","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656555","display_name":"Zihang Ma","orcid":"https://orcid.org/0009-0000-6021-7605"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihang Ma","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488030","display_name":"Xinghe Wang","orcid":"https://orcid.org/0009-0000-3255-6626"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghe Wang","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101844143","display_name":"Yutao Tang","orcid":"https://orcid.org/0000-0002-2306-1880"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Tang","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5343935"],"apc_list":null,"apc_paid":null,"fwci":4.0707,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.94926292,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7610","last_page":"7614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9927999973297119,"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/object-detection","display_name":"Object detection","score":0.8316750526428223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8215458989143372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6957665681838989},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6172558069229126},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6097479462623596},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.572588324546814},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.49953770637512207},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4946591556072235},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.45016297698020935},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.4441378712654114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.330876886844635},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24556279182434082}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.8316750526428223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215458989143372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6957665681838989},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6172558069229126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6097479462623596},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.572588324546814},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.49953770637512207},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4946591556072235},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.45016297698020935},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.4441378712654114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.330876886844635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24556279182434082},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2963150697","https://openalex.org/W2995926063","https://openalex.org/W3034971973","https://openalex.org/W3144426752","https://openalex.org/W3171660447","https://openalex.org/W3206795908","https://openalex.org/W3208645658","https://openalex.org/W4212774754","https://openalex.org/W4225550216","https://openalex.org/W4293584584","https://openalex.org/W4297676427","https://openalex.org/W4372263412","https://openalex.org/W4386076325","https://openalex.org/W6620707391","https://openalex.org/W6750227808","https://openalex.org/W6843239693"],"related_works":["https://openalex.org/W4206776094","https://openalex.org/W3154920669","https://openalex.org/W3121197456","https://openalex.org/W4396860960","https://openalex.org/W4390482660","https://openalex.org/W2972256598","https://openalex.org/W4388813151","https://openalex.org/W2610408157","https://openalex.org/W2612465689","https://openalex.org/W4284972948"],"abstract_inverted_index":{"Detecting":[0],"small":[1,39,61,74,145],"objects":[2],"in":[3,64,143],"Unmanned":[4],"Aerial":[5],"Vehicle":[6],"(UAV)":[7],"images":[8,23],"is":[9],"pivotal":[10],"for":[11,60],"a":[12,34],"multitude":[13],"of":[14,20,36],"applications.":[15],"Given":[16],"the":[17,22,79,94,106,113,118,132],"high-altitude":[18],"perspective":[19],"UAVs,":[21],"they":[24],"capture":[25],"often":[26],"feature":[27],"intricate":[28],"backgrounds,":[29],"pronounced":[30],"object":[31,62,75,146],"heterogeneity,":[32],"and":[33,77,101,127],"plethora":[35],"sparsely":[37],"situated":[38],"targets.":[40],"These":[41],"characteristics":[42],"pose":[43],"significant":[44],"challenges":[45],"to":[46,73,85,115,123],"conventional":[47],"detection":[48,63,76,95,119],"algorithms.":[49],"In":[50],"response,":[51],"we":[52,92],"introduce":[53],"an":[54],"enhanced":[55],"YOLOv7-based":[56],"technique":[57],"specifically":[58],"tailored":[59],"UAV":[65],"images.":[66],"Our":[67],"approach":[68],"adds":[69],"more":[70],"layers":[71],"dedicated":[72],"leverages":[78],"Bi-directional":[80],"Feature":[81],"Pyramid":[82],"Network":[83],"(BiFPN)":[84],"extract":[86],"features":[87],"across":[88],"diverse":[89],"scales.":[90],"Furthermore,":[91],"enhance":[93],"heads":[96],"by":[97],"standardizing":[98],"channel":[99],"configurations":[100],"incorporate":[102],"attention":[103],"mechanisms":[104],"through":[105],"dynamic":[107],"head":[108,120],"framework":[109],"(DyHead).":[110],"This":[111],"allows":[112],"model":[114],"adaptively":[116],"modify":[117],"structure,":[121],"catering":[122],"varying":[124],"scales,":[125],"tasks,":[126],"features.":[128],"Preliminary":[129],"results":[130],"on":[131],"VisDrone2019":[133],"dataset":[134],"indicate":[135],"that":[136],"our":[137],"method":[138],"surpasses":[139],"existing":[140],"state-of-the-art":[141],"algorithms":[142],"UAV-based":[144],"detection.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
