{"id":"https://openalex.org/W4401810676","doi":"https://doi.org/10.3390/s24165404","title":"Enhanced Detection and Recognition of Road Objects in Infrared Imaging Using Multi-Scale Self-Attention","display_name":"Enhanced Detection and Recognition of Road Objects in Infrared Imaging Using Multi-Scale Self-Attention","publication_year":2024,"publication_date":"2024-08-21","ids":{"openalex":"https://openalex.org/W4401810676","doi":"https://doi.org/10.3390/s24165404","pmid":"https://pubmed.ncbi.nlm.nih.gov/39205101"},"language":"en","primary_location":{"id":"doi:10.3390/s24165404","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24165404","pdf_url":"https://www.mdpi.com/1424-8220/24/16/5404/pdf?version=1724378173","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","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/1424-8220/24/16/5404/pdf?version=1724378173","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113345241","display_name":"Poyi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Poyi Liu","raw_affiliation_strings":["School of Communication Engineering, Wuhan University of Technology, Wuhan 430070, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Wuhan University of Technology, Wuhan 430070, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109767877","display_name":"Yunkang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunkang Zhang","raw_affiliation_strings":["School of Communication Engineering, Wuhan University of Technology, Wuhan 430070, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Wuhan University of Technology, Wuhan 430070, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012628011","display_name":"Guanlun Guo","orcid":"https://orcid.org/0000-0002-4239-4285"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanlun Guo","raw_affiliation_strings":["School of Automotive Engineering, Wuhan University of Technology, Wuhan 430070, China"],"raw_orcid":"https://orcid.org/0000-0002-4239-4285","affiliations":[{"raw_affiliation_string":"School of Automotive Engineering, Wuhan University of Technology, Wuhan 430070, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101074366","display_name":"Jiale Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Ding","raw_affiliation_strings":["School of Safety and Emergency Management, Wuhan University of Technology, Wuhan 430070, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Safety and Emergency Management, Wuhan University of Technology, Wuhan 430070, China","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012628011"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.8975,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75106386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"24","issue":"16","first_page":"5404","last_page":"5404"},"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9922999739646912,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9916999936103821,"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":0.7588596343994141},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7026934623718262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.587004542350769},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4910616874694824},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4631824493408203},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46030715107917786},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4529402256011963},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.4244476556777954},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4148615896701813},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36169320344924927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34130075573921204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588596343994141},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7026934623718262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.587004542350769},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4910616874694824},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4631824493408203},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46030715107917786},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4529402256011963},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.4244476556777954},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4148615896701813},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36169320344924927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34130075573921204},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":5,"locations":[{"id":"doi:10.3390/s24165404","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24165404","pdf_url":"https://www.mdpi.com/1424-8220/24/16/5404/pdf?version=1724378173","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},{"id":"pmid:39205101","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39205101","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":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11359053","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11359053","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11359053/pdf/sensors-24-05404.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:9670e8f5826342ab8d8c0a14c5e5fb8f","is_oa":true,"landing_page_url":"https://doaj.org/article/9670e8f5826342ab8d8c0a14c5e5fb8f","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":"Sensors, Vol 24, Iss 16, p 5404 (2024)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/24/16/5404/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s24165404","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Sensors","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s24165404","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24165404","pdf_url":"https://www.mdpi.com/1424-8220/24/16/5404/pdf?version=1724378173","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401810676.pdf","grobid_xml":"https://content.openalex.org/works/W4401810676.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2547673833","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2616247523","https://openalex.org/W2884561390","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963857746","https://openalex.org/W2972902861","https://openalex.org/W2980386799","https://openalex.org/W2988071854","https://openalex.org/W2996492103","https://openalex.org/W3102564565","https://openalex.org/W3126962163","https://openalex.org/W3171660447","https://openalex.org/W4200079737","https://openalex.org/W4223569781","https://openalex.org/W4285328243","https://openalex.org/W4289985668","https://openalex.org/W4310609591","https://openalex.org/W4327774073","https://openalex.org/W4362709296","https://openalex.org/W4385342336","https://openalex.org/W4385990351","https://openalex.org/W4386822428","https://openalex.org/W4387149600","https://openalex.org/W4387347230","https://openalex.org/W4388727515","https://openalex.org/W4389302184","https://openalex.org/W4389315420","https://openalex.org/W4389371100","https://openalex.org/W4389401522","https://openalex.org/W4389980504","https://openalex.org/W4390189930","https://openalex.org/W4390682402","https://openalex.org/W4391093222","https://openalex.org/W4391422261","https://openalex.org/W4392668854","https://openalex.org/W4393406044"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W4224009465","https://openalex.org/W2256933480","https://openalex.org/W4306674287","https://openalex.org/W3127668761"],"abstract_inverted_index":{"In":[0],"infrared":[1,37,85,213],"detection":[2,30,69,86,186,255],"scenarios,":[3],"detecting":[4],"and":[5,8,50,70,91,114,143,167,197,224,240,257,266],"recognizing":[6],"low-contrast":[7],"small-sized":[9],"targets":[10,83],"has":[11],"always":[12],"been":[13],"a":[14,67,75,103,235,241],"challenge":[15],"in":[16,23,84,136,159,238,244,253],"the":[17,51,93,98,116,128,133,145,160,175,190,201,230,247],"field":[18],"of":[19,119,221],"computer":[20],"vision,":[21],"particularly":[22],"complex":[24],"road":[25,82,214],"traffic":[26,215],"environments.":[27],"Traditional":[28],"target":[29,109],"methods":[31],"usually":[32],"perform":[33],"poorly":[34],"when":[35],"processing":[36,206,258],"small":[38,81,120,180,261],"targets,":[39,262],"mainly":[40],"due":[41],"to":[42,45,107,123,163,178,183,193],"their":[43],"inability":[44],"effectively":[46],"extract":[47],"key":[48],"features":[49,110,152,166],"significant":[52,251],"feature":[53,58,129,161],"loss":[54,126],"that":[55,227],"occurs":[56],"during":[57,127],"transmission.":[59],"To":[60],"address":[61],"these":[62],"issues,":[63],"this":[64,140],"paper":[65,141],"proposes":[66],"fast":[68],"recognition":[71],"model":[72,202],"based":[73,96],"on":[74,97,209,246],"multi-scale":[76],"self-attention":[77,105],"mechanism,":[78],"specifically":[79],"for":[80,204,260],"scenarios.":[87,207],"We":[88],"first":[89],"introduce":[90],"improve":[92],"DyHead":[94],"structure":[95,135],"YOLOv8":[99],"algorithm,":[100],"which":[101],"employs":[102],"multi-head":[104],"mechanism":[106],"capture":[108],"at":[111],"various":[112],"scales":[113],"enhance":[115,174],"model's":[117,176],"perception":[118],"targets.":[121,181],"Additionally,":[122],"prevent":[124],"information":[125],"transmission":[130],"process":[131],"via":[132],"FPN":[134],"traditional":[137],"YOLO":[138],"algorithms,":[139],"introduces":[142],"enhances":[144],"Gather-and-Distribute":[146],"Mechanism.":[147],"By":[148],"computing":[149],"dependencies":[150],"between":[151],"using":[153],"self-attention,":[154],"it":[155],"reallocates":[156],"attention":[157],"weights":[158],"maps":[162],"highlight":[164],"important":[165],"suppress":[168],"irrelevant":[169],"information.":[170],"These":[171],"improvements":[172],"significantly":[173],"capability":[177],"detect":[179],"Moreover,":[182],"further":[184],"increase":[185,243],"speed,":[187],"we":[188],"pruned":[189],"network":[191],"architecture":[192],"reduce":[194],"computational":[195],"complexity":[196],"parameter":[198],"count,":[199],"making":[200],"suitable":[203],"real-time":[205],"Experiments":[208],"our":[210,232],"self":[211],"built":[212],"dataset":[216],"(mainly":[217],"including":[218],"two":[219],"types":[220],"targets:":[222],"vehicles":[223],"people)":[225],"show":[226],"compared":[228],"with":[229,263],"baseline,":[231],"method":[233],"achieves":[234],"3.1%":[236],"improvement":[237],"AP":[239],"2.5%":[242],"mAP":[245],"VisDrone2019":[248],"dataset,":[249],"showing":[250],"enhancements":[252],"both":[254],"accuracy":[256],"speed":[259],"improved":[264],"robustness":[265],"adaptability.":[267]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}