{"id":"https://openalex.org/W4405786076","doi":"https://doi.org/10.1109/iros58592.2024.10802476","title":"ODTFormer: Efficient Obstacle Detection and Tracking with Stereo Cameras Based on Transformer","display_name":"ODTFormer: Efficient Obstacle Detection and Tracking with Stereo Cameras Based on Transformer","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786076","doi":"https://doi.org/10.1109/iros58592.2024.10802476","pmid":"https://pubmed.ncbi.nlm.nih.gov/40143961"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11938320/pdf/nihms-2062380.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102634570","display_name":"Tianye Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianye Ding","raw_affiliation_strings":["Northeastern University,Boston,MA,02115"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Boston,MA,02115","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402298","display_name":"Hongyu Li","orcid":"https://orcid.org/0000-0002-4588-9929"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyu Li","raw_affiliation_strings":["Brown University,Providence,RI,02912"],"affiliations":[{"raw_affiliation_string":"Brown University,Providence,RI,02912","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101739360","display_name":"H. W. Jiang","orcid":"https://orcid.org/0000-0002-2300-4237"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaizu Jiang","raw_affiliation_strings":["Northeastern University,Boston,MA,02115"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Boston,MA,02115","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102634570"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56387068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2024","issue":null,"first_page":"9721","last_page":"9728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","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/T10531","display_name":"Advanced Vision and Imaging","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":0.9997000098228455,"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":0.9994000196456909,"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-vision","display_name":"Computer vision","score":0.8025139570236206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7187902927398682},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.6842405200004578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6600568294525146},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5927867889404297},{"id":"https://openalex.org/keywords/stereopsis","display_name":"Stereopsis","score":0.5395130515098572},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.50042724609375},{"id":"https://openalex.org/keywords/stereo-camera","display_name":"Stereo camera","score":0.46741628646850586},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14610302448272705},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08177351951599121},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06360858678817749}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.8025139570236206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7187902927398682},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.6842405200004578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6600568294525146},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5927867889404297},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.5395130515098572},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.50042724609375},{"id":"https://openalex.org/C185078393","wikidata":"https://www.wikidata.org/wiki/Q313783","display_name":"Stereo camera","level":2,"score":0.46741628646850586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14610302448272705},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08177351951599121},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06360858678817749},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros58592.2024.10802476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmid:40143961","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40143961","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":"Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11938320","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11938320","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11938320/pdf/nihms-2062380.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Rep U S","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:11938320","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11938320","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11938320/pdf/nihms-2062380.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Rep U S","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G225842847","display_name":null,"funder_award_id":"10254","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G992241184","display_name":"RI: Small: Toward Efficient and Robust Dynamic Scene Understanding Based on Visual Correspondences","funder_award_id":"2310254","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405786076.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1921093919","https://openalex.org/W2129671742","https://openalex.org/W2165114467","https://openalex.org/W2259424905","https://openalex.org/W2565639579","https://openalex.org/W2604216058","https://openalex.org/W2908510526","https://openalex.org/W2913365477","https://openalex.org/W2948384918","https://openalex.org/W2954174912","https://openalex.org/W2970881233","https://openalex.org/W2984858187","https://openalex.org/W3122239467","https://openalex.org/W3133110313","https://openalex.org/W3135067689","https://openalex.org/W3159537771","https://openalex.org/W3172573759","https://openalex.org/W3186096360","https://openalex.org/W3195680177","https://openalex.org/W3202883604","https://openalex.org/W3216406996","https://openalex.org/W4206236307","https://openalex.org/W4293811845","https://openalex.org/W4294982669","https://openalex.org/W4312368247","https://openalex.org/W4312388571","https://openalex.org/W4312441173","https://openalex.org/W4312894406","https://openalex.org/W4366458436","https://openalex.org/W4383097509","https://openalex.org/W4383108576","https://openalex.org/W4383172048","https://openalex.org/W4385245566","https://openalex.org/W4386066358","https://openalex.org/W4386083035","https://openalex.org/W4386083121","https://openalex.org/W4390871877","https://openalex.org/W4390873564","https://openalex.org/W4392215009","https://openalex.org/W4405786633","https://openalex.org/W6757817989","https://openalex.org/W6762718338","https://openalex.org/W6784094891","https://openalex.org/W6851782402"],"related_works":["https://openalex.org/W2794103424","https://openalex.org/W1996530509","https://openalex.org/W2891167363","https://openalex.org/W2165574152","https://openalex.org/W2949709491","https://openalex.org/W307265996","https://openalex.org/W128884630","https://openalex.org/W2905493506","https://openalex.org/W1992486622","https://openalex.org/W2389564093"],"abstract_inverted_index":{"Obstacle":[0],"detection":[1,25,31,93],"and":[2,26,82],"tracking":[3,27,103],"represent":[4],"a":[5,18,40,108],"critical":[6],"component":[7],"in":[8,48,73,90],"robot":[9],"autonomous":[10],"navigation.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15],"propose":[16],"ODTFormer,":[17],"Transformer-based":[19],"model":[20,69,86],"that":[21],"addresses":[22],"both":[23],"obstacle":[24,92,102],"problems.":[28],"For":[29],"the":[30,49,58,62,91],"task,":[32],"our":[33,85],"approach":[34],"leverages":[35],"deformable":[36],"attention":[37],"to":[38,100,116],"construct":[39],"3D":[41],"cost":[42],"volume,":[43],"which":[44],"is":[45,121],"decoded":[46],"progressively":[47],"form":[50],"of":[51,110],"voxel":[52],"occupancy":[53],"grids.":[54],"We":[55,95],"further":[56],"track":[57],"obstacles":[59],"by":[60],"matching":[61],"voxels":[63],"between":[64],"consecutive":[65],"frames.":[66],"The":[67],"entire":[68],"can":[70],"be":[71],"optimized":[72],"an":[74],"end-to-end":[75],"manner.":[76],"Through":[77],"extensive":[78],"experiments":[79],"on":[80,123],"DrivingStereo":[81],"KITTI":[83],"benchmarks,":[84],"achieves":[87],"state-of-the-art":[88,101],"performance":[89],"task.":[94],"also":[96],"report":[97],"comparable":[98],"accuracy":[99],"models":[104],"while":[105],"requiring":[106],"only":[107],"fraction":[109],"their":[111],"computation":[112],"cost,":[113],"typically":[114],"ten-fold":[115],"twenty-fold":[117],"less.":[118],"Our":[119],"code":[120],"available":[122],"https://github.com/neu-vi/ODTFormer.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}