{"id":"https://openalex.org/W6963886746","doi":"https://doi.org/10.2312/pg.20241327","title":"SPDD-YOLO for Small Object Detection in UAV Images","display_name":"SPDD-YOLO for Small Object Detection in UAV Images","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6963886746","doi":"https://doi.org/10.2312/pg.20241327"},"language":"en","primary_location":{"id":"doi:10.2312/pg.20241327","is_oa":true,"landing_page_url":"https://doi.org/10.2312/pg.20241327","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2312/pg.20241327","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xue, Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I55654194","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019","country_code":"CN","type":"education","lineage":["https://openalex.org/I55654194"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue, Xiang","raw_affiliation_strings":["Inner Mongolia University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University of Technology, China","institution_ids":["https://openalex.org/I55654194"]}]},{"author_position":"middle","author":{"id":null,"display_name":"JI, Yatu","orcid":"https://orcid.org/0000-0001-6460-9921"},"institutions":[{"id":"https://openalex.org/I55654194","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019","country_code":"CN","type":"education","lineage":["https://openalex.org/I55654194"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JI, Yatu","raw_affiliation_strings":["Inner Mongolia University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-6460-9921","affiliations":[{"raw_affiliation_string":"Inner Mongolia University of Technology, China","institution_ids":["https://openalex.org/I55654194"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I55654194","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019","country_code":"CN","type":"education","lineage":["https://openalex.org/I55654194"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":["Inner Mongolia University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University of Technology, China","institution_ids":["https://openalex.org/I55654194"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu, H. T.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, H. T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ren, Q. D. E. J.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Q. D. E. J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shi, B.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, N. E.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, N. E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lu, M.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhuang, X. F.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, X. F.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42450698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7702999711036682,"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":0.7702999711036682,"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":0.10490000247955322,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.022099999710917473,"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/focus","display_name":"Focus (optics)","score":0.6840000152587891},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6456000208854675},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5913000106811523},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5454000234603882},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.529699981212616},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41670000553131104},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7423999905586243},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7249000072479248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063000202178955},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6840000152587891},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6456000208854675},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5454000234603882},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C150627866","wikidata":"https://www.wikidata.org/wiki/Q1076893","display_name":"Field of view","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2312/pg.20241327","is_oa":true,"landing_page_url":"https://doi.org/10.2312/pg.20241327","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.2312/pg.20241327","is_oa":true,"landing_page_url":"https://doi.org/10.2312/pg.20241327","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Aerial":[0],"images":[1],"captured":[2],"by":[3,71,137],"drones":[4],"often":[5],"suffer":[6],"from":[7],"blurriness":[8],"and":[9,35,42,112,135,140],"low":[10],"resolution,":[11],"which":[12,104],"is":[13],"particularly":[14],"problematic":[15],"for":[16],"small":[17,69],"targets.":[18],"In":[19],"such":[20],"scenarios,":[21],"the":[22,39,59,73,80,85,89,106,114,124,129],"YOLO":[23],"object":[24],"detection":[25],"algorithm":[26],"tends":[27],"to":[28,38,64,91],"confuse":[29],"or":[30],"misidentify":[31],"targets":[32,70],"like":[33],"bicycles":[34],"tricycles":[36],"due":[37],"complex":[40],"features":[41,67],"local":[43,66,95],"similarities.":[44],"To":[45],"address":[46],"these":[47],"issues,":[48],"this":[49],"paper":[50],"proposes":[51],"a":[52],"SPDD-YOLO":[53],"model":[54,60,90,131],"based":[55],"on":[56,94,123],"YOLOv8.":[57],"Firstly,":[58],"enhances":[61],"its":[62],"ability":[63],"extract":[65],"of":[68],"introducing":[72],"Spatial-to-":[74],"Depth":[75],"Module":[76,117],"(SPDM).":[77],"Secondly,":[78],"addressing":[79],"issue":[81],"that":[82,128],"SPDM":[83],"reduces":[84],"receptive":[86,107],"field,":[87],"leading":[88],"overly":[92],"focus":[93],"features,":[96],"we":[97],"introduced":[98],"Deep":[99,115],"Separable":[100],"Dilated":[101,116],"Convolution":[102],"(DSDC),":[103],"expands":[105],"field":[108],"while":[109],"reducing":[110],"parameters":[111],"forms":[113],"(DDM)":[118],"together":[119],"with":[120],"SPDM.":[121],"Experiments":[122],"VisDrone2019":[125],"dataset":[126],"demonstrate":[127],"proposed":[130],"improved":[132],"precision,":[133],"recall,":[134],"mAP50":[136],"5.8%,":[138],"5.7%,":[139],"6.4%,":[141],"respectively.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}