{"id":"https://openalex.org/W7134058030","doi":"https://doi.org/10.3233/faia260003","title":"Small Target Detection Algorithm in Aerial Images Based on Improved RT-DETR","display_name":"Small Target Detection Algorithm in Aerial Images Based on Improved RT-DETR","publication_year":2026,"publication_date":"2026-03-04","ids":{"openalex":"https://openalex.org/W7134058030","doi":"https://doi.org/10.3233/faia260003"},"language":null,"primary_location":{"id":"doi:10.3233/faia260003","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia260003","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia260003","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128224934","display_name":"Haoran Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I31590910","display_name":"Jianghan University","ror":"https://ror.org/041c9x778","country_code":"CN","type":"education","lineage":["https://openalex.org/I31590910"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Yu","raw_affiliation_strings":["School of Artificial Intelligence, Jianghan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jianghan University, China","institution_ids":["https://openalex.org/I31590910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128276460","display_name":"Jing Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I31590910","display_name":"Jianghan University","ror":"https://ror.org/041c9x778","country_code":"CN","type":"education","lineage":["https://openalex.org/I31590910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhou","raw_affiliation_strings":["School of Artificial Intelligence, Jianghan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jianghan University, China","institution_ids":["https://openalex.org/I31590910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5128224934"],"corresponding_institution_ids":["https://openalex.org/I31590910"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59001696,"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":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8574000000953674,"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":0.8574000000953674,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.0737999975681305,"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/T11133","display_name":"UAV Applications and Optimization","score":0.006399999838322401,"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/object-detection","display_name":"Object detection","score":0.708299994468689},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6632999777793884},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6539999842643738},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.5855000019073486},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5590999722480774},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5012000203132629},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4945000112056732},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4767000079154968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190999984741211},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.708299994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6931999921798706},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6632999777793884},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6539999842643738},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.5855000019073486},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.29660001397132874},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.29409998655319214},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia260003","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia260003","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia260003","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia260003","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"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],"image":[1],"object":[2,125,153,189],"detection":[3,27,126,154,175,190],"faces":[4],"the":[5,25,30,47,52,78,97,103,130,150,169],"challenge":[6],"of":[7,10],"dense":[8],"distribution":[9],"small":[11,124,144,188],"objects,":[12],"which":[13],"are":[14],"difficult":[15],"to":[16,20,50,68,95,101,133],"be":[17],"detected":[18],"due":[19],"too":[21],"few":[22],"features,":[23],"damaging":[24],"whole":[26],"performance":[28],"in":[29,191],"complex":[31,192],"scenes.":[32],"To":[33],"address":[34],"this":[35],"issue,":[36],"we":[37,60,88,120],"propose":[38,89],"a":[39,63,90,122],"Small":[40],"Target":[41],"Detection":[42],"Transformer":[43],"(ST-DETR)":[44],"based":[45,128],"on":[46,129,149],"RT-DETR":[48],"architecture":[49],"implement":[51],"systematic":[53],"optimization":[54],"tailored":[55],"for":[56,82,143,187],"aerial":[57,152,193],"scenarios.":[58],"Specifically,":[59],"first":[61],"introduce":[62],"cross-scale":[64],"feature":[65,74],"fusion":[66],"module":[67],"enhance":[69],"multi-scale":[70],"representation":[71],"with":[72,84,109],"hierarchical":[73],"integration,":[75],"effectively":[76],"improving":[77,115],"model\u2019s":[79],"recognition":[80],"capability":[81],"objects":[83],"different":[85],"sizes.":[86],"Then":[87],"novel":[91],"Wise-MPDIoU":[92],"loss":[93],"function":[94],"leverage":[96],"dynamic":[98],"weighting":[99],"mechanism":[100],"heighten":[102],"subtle":[104],"differences":[105],"among":[106],"bounding":[107,116],"boxes":[108],"similar":[110],"aspect":[111],"ratios,":[112],"thus":[113],"significantly":[114],"box":[117],"regression.":[118],"Finally,":[119],"establish":[121],"dedicated":[123],"head":[127],"P2":[131],"layer":[132],"more":[134],"accurately":[135],"extract":[136],"fine-grained":[137],"textures":[138],"and":[139,164,173,185],"spatial":[140],"features":[141],"crucial":[142],"target":[145],"localization.":[146],"Experimental":[147],"results":[148],"SkyFusion":[151],"dataset":[155],"demonstrate":[156],"that":[157],"our":[158],"proposed":[159],"ST-DETR":[160],"achieving":[161],"4.7%":[162],"mAP50":[163],"2.3%":[165],"mAP50:95":[166],"gains":[167],"over":[168],"baseline":[170],"model":[171],"RT-DETR,":[172],"its":[174,183],"accuracy":[176],"also":[177],"outperforms":[178],"other":[179],"popular":[180],"models,":[181],"validating":[182],"effectiveness":[184],"robustness":[186],"images.":[194]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-07T00:00:00"}