{"id":"https://openalex.org/W4413376436","doi":"https://doi.org/10.3390/jimaging11080285","title":"MSConv-YOLO: An Improved Small Target Detection Algorithm Based on YOLOv8","display_name":"MSConv-YOLO: An Improved Small Target Detection Algorithm Based on YOLOv8","publication_year":2025,"publication_date":"2025-08-21","ids":{"openalex":"https://openalex.org/W4413376436","doi":"https://doi.org/10.3390/jimaging11080285","pmid":"https://pubmed.ncbi.nlm.nih.gov/40863494"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging11080285","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11080285","pdf_url":"https://www.mdpi.com/2313-433X/11/8/285/pdf?version=1755778614","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/11/8/285/pdf?version=1755778614","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Linli Yang","orcid":"https://orcid.org/0009-0007-5100-8183"},"institutions":[{"id":"https://openalex.org/I82284825","display_name":"Cranfield University","ror":"https://ror.org/05cncd958","country_code":"GB","type":"education","lineage":["https://openalex.org/I82284825"]},{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Linli Yang","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China","Faculty of Engineering and Applied Sciences, Cranfield University, Cranfield, Bedford MK43 0AL, UK"],"raw_orcid":"https://orcid.org/0009-0007-5100-8183","affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Faculty of Engineering and Applied Sciences, Cranfield University, Cranfield, Bedford MK43 0AL, UK","institution_ids":["https://openalex.org/I82284825"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029727932","display_name":"Barmak Honarvar Shakibaei Asli","orcid":"https://orcid.org/0000-0003-1519-9596"},"institutions":[{"id":"https://openalex.org/I82284825","display_name":"Cranfield University","ror":"https://ror.org/05cncd958","country_code":"GB","type":"education","lineage":["https://openalex.org/I82284825"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Barmak Honarvar Shakibaei Asli","raw_affiliation_strings":["Faculty of Engineering and Applied Sciences, Cranfield University, Cranfield, Bedford MK43 0AL, UK"],"raw_orcid":"https://orcid.org/0000-0003-1519-9596","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Applied Sciences, Cranfield University, Cranfield, Bedford MK43 0AL, UK","institution_ids":["https://openalex.org/I82284825"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029727932"],"corresponding_institution_ids":["https://openalex.org/I82284825"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":3.0131,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9212132,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"11","issue":"8","first_page":"285","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.996999979019165,"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":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.8764957189559937},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6489672660827637},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6173720359802246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5421901345252991},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4796498417854309},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43291473388671875},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.42441385984420776},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4139522910118103},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3763430714607239},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.350361704826355},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33460432291030884},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33151865005493164},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3209337592124939},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2027662992477417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8764957189559937},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6489672660827637},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6173720359802246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5421901345252991},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4796498417854309},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43291473388671875},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.42441385984420776},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4139522910118103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3763430714607239},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.350361704826355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33460432291030884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33151865005493164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3209337592124939},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2027662992477417},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging11080285","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11080285","pdf_url":"https://www.mdpi.com/2313-433X/11/8/285/pdf?version=1755778614","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:40863494","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40863494","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":null},{"id":"pmh:oai:doaj.org/article:f926f8f2834a4d469f54bb1bd2d522af","is_oa":true,"landing_page_url":"https://doaj.org/article/f926f8f2834a4d469f54bb1bd2d522af","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 11, Iss 8, p 285 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11195474","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12387663","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging11080285","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11080285","pdf_url":"https://www.mdpi.com/2313-433X/11/8/285/pdf?version=1755778614","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413376436.pdf","grobid_xml":"https://content.openalex.org/works/W4413376436.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2109255472","https://openalex.org/W2531409750","https://openalex.org/W2594258618","https://openalex.org/W2963857746","https://openalex.org/W2972006294","https://openalex.org/W3005363112","https://openalex.org/W3016641475","https://openalex.org/W3033131612","https://openalex.org/W3034971973","https://openalex.org/W3035406940","https://openalex.org/W3042011474","https://openalex.org/W3120757908","https://openalex.org/W3157163063","https://openalex.org/W4291819654","https://openalex.org/W4311343530","https://openalex.org/W4319789280","https://openalex.org/W4323318524","https://openalex.org/W4327652243","https://openalex.org/W4385453180","https://openalex.org/W4385839827","https://openalex.org/W4387503356","https://openalex.org/W4388807184","https://openalex.org/W4390638513","https://openalex.org/W4391986043","https://openalex.org/W4393170784","https://openalex.org/W4399030933","https://openalex.org/W4399769149","https://openalex.org/W4400233820","https://openalex.org/W4401894250","https://openalex.org/W4404294235","https://openalex.org/W4404613893","https://openalex.org/W4407565317","https://openalex.org/W4407749638","https://openalex.org/W4408330910","https://openalex.org/W4409337907"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Small":[0],"object":[1,190],"detection":[2,56,126,191],"in":[3,128,162,168,192],"UAV":[4,193],"aerial":[5],"imagery":[6],"presents":[7,182],"significant":[8],"challenges":[9],"due":[10],"to":[11,31,54,113,136,188,214],"scale":[12],"variations,":[13],"sparse":[14],"feature":[15,87],"representation,":[16],"and":[17,78,119,134,140,164,184,212],"complex":[18,216],"backgrounds.":[19],"To":[20],"address":[21],"these":[22],"issues,":[23],"this":[24],"paper":[25,181],"focuses":[26],"on":[27,146,209],"practical":[28,183],"engineering":[29,186],"improvements":[30],"the":[32,62,93,101,121,129,147,154,174],"existing":[33],"YOLOv8s":[34,156],"framework,":[35],"rather":[36],"than":[37],"proposing":[38],"a":[39,70,108,124,159,165],"fundamentally":[40],"new":[41,202],"algorithm.":[42],"We":[43],"introduce":[44],"MultiScaleConv-YOLO":[45],"(MSConv-YOLO),":[46],"an":[47,196],"enhanced":[48],"model":[49],"that":[50,74,151],"integrates":[51],"well-established":[52],"techniques":[53],"improve":[55,114],"performance":[57],"for":[58,116],"small":[59,117,189],"targets.":[60],"Specifically,":[61],"proposed":[63],"approach":[64],"introduces":[65],"three":[66],"key":[67],"improvements:":[68],"(1)":[69],"MultiScaleConv":[71],"(MSConv)":[72],"module":[73],"combines":[75],"depthwise":[76],"separable":[77],"dilated":[79],"convolutions":[80],"with":[81,97],"varying":[82],"dilation":[83],"rates,":[84],"enhancing":[85],"multi-scale":[86],"extraction":[88],"while":[89],"maintaining":[90],"efficiency;":[91],"(2)":[92],"replacement":[94],"of":[95,123,177],"CIoU":[96],"WIoU":[98],"v3":[99],"as":[100],"bounding":[102],"box":[103],"regression":[104],"loss,":[105],"which":[106],"incorporates":[107],"dynamic":[109],"non-monotonic":[110],"focusing":[111],"mechanism":[112],"localization":[115],"targets;":[118],"(3)":[120],"addition":[122],"high-resolution":[125],"head":[127],"neck-head":[130],"structure,":[131],"leveraging":[132],"FPN":[133],"PAN":[135],"preserve":[137],"fine-grained":[138],"features":[139],"ensure":[141],"full-scale":[142],"coverage.":[143],"Experimental":[144],"results":[145],"VisDrone2019":[148],"dataset":[149],"show":[150],"MSConv-YOLO":[152],"outperforms":[153],"baseline":[155],"by":[157],"achieving":[158],"6.9%":[160],"improvement":[161],"mAP@0.5":[163],"6.3%":[166],"gain":[167],"recall.":[169],"Ablation":[170],"studies":[171],"further":[172],"validate":[173],"complementary":[175],"impact":[176],"each":[178],"enhancement.":[179],"This":[180],"effective":[185],"enhancements":[187],"scenarios,":[194],"offering":[195],"improved":[197],"solution":[198],"without":[199],"introducing":[200],"entirely":[201],"theoretical":[203],"constructs.":[204],"Future":[205],"work":[206],"will":[207],"focus":[208],"lightweight":[210],"deployment":[211],"adaptation":[213],"more":[215],"environments.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}