{"id":"https://openalex.org/W2963376049","doi":"https://doi.org/10.1109/icassp.2019.8683446","title":"Learning by Inertia: Self-supervised Monocular Visual Odometry for Road Vehicles","display_name":"Learning by Inertia: Self-supervised Monocular Visual Odometry for Road Vehicles","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2963376049","doi":"https://doi.org/10.1109/icassp.2019.8683446","mag":"2963376049"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086326894","display_name":"Chengze Wang","orcid":"https://orcid.org/0000-0003-2349-6427"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengze Wang","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, 710072, P. R. China","School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, 710072, P. R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334801","display_name":"Yuan Yuan","orcid":"https://orcid.org/0000-0003-3352-0662"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Yuan","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, 710072, P. R. China","School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, 710072, P. R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341186","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0001-6164-6786"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, 710072, P. R. China","School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, 710072, P. R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.2745,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57974251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2252","last_page":"2256"},"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":0.9998000264167786,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9954000115394592,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8207210302352905},{"id":"https://openalex.org/keywords/visual-odometry","display_name":"Visual odometry","score":0.7783454060554504},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7063308954238892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6730136871337891},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6315162181854248},{"id":"https://openalex.org/keywords/odometry","display_name":"Odometry","score":0.6281659603118896},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6191020607948303},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5536231398582458},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4921531081199646},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.4384228587150574},{"id":"https://openalex.org/keywords/inertia","display_name":"Inertia","score":0.4243013262748718},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3105735182762146},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.20529061555862427},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17009013891220093}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8207210302352905},{"id":"https://openalex.org/C5799516","wikidata":"https://www.wikidata.org/wiki/Q4110915","display_name":"Visual odometry","level":3,"score":0.7783454060554504},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7063308954238892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6730136871337891},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6315162181854248},{"id":"https://openalex.org/C49441653","wikidata":"https://www.wikidata.org/wiki/Q2014717","display_name":"Odometry","level":4,"score":0.6281659603118896},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6191020607948303},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5536231398582458},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4921531081199646},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.4384228587150574},{"id":"https://openalex.org/C110407247","wikidata":"https://www.wikidata.org/wiki/Q122508","display_name":"Inertia","level":2,"score":0.4243013262748718},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3105735182762146},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.20529061555862427},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17009013891220093},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W292075967","https://openalex.org/W603908379","https://openalex.org/W1527702126","https://openalex.org/W1803059841","https://openalex.org/W2071499765","https://openalex.org/W2108134361","https://openalex.org/W2115579991","https://openalex.org/W2133665775","https://openalex.org/W2150066425","https://openalex.org/W2171740948","https://openalex.org/W2259424905","https://openalex.org/W2333777777","https://openalex.org/W2340897893","https://openalex.org/W2474281075","https://openalex.org/W2520707372","https://openalex.org/W2535547924","https://openalex.org/W2561074213","https://openalex.org/W2608018946","https://openalex.org/W2609883120","https://openalex.org/W2951234442","https://openalex.org/W2963906250","https://openalex.org/W2964314455","https://openalex.org/W3100388886","https://openalex.org/W3102327032","https://openalex.org/W6610537083","https://openalex.org/W6618372016","https://openalex.org/W6685261749","https://openalex.org/W6703848168","https://openalex.org/W6736260464","https://openalex.org/W6744864977"],"related_works":["https://openalex.org/W2979950214","https://openalex.org/W87609089","https://openalex.org/W3024737167","https://openalex.org/W2414561716","https://openalex.org/W3161199934","https://openalex.org/W2303855011","https://openalex.org/W2312326526","https://openalex.org/W2412578866","https://openalex.org/W3105866016","https://openalex.org/W4312703710"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,70,125],"present":[4],"iDVO":[5],"(inertia-embedded":[6],"deep":[7,30,174],"visual":[8,15],"odometry),":[9],"a":[10,44],"self-supervised":[11],"learning":[12],"based":[13],"monocular":[14,173],"odometry":[16],"(VO)":[17],"for":[18],"road":[19,57,110],"vehicles.":[20],"When":[21],"modelling":[22],"the":[23,34,38,50,54,68,72,78,84,88,96,107,113,117,127,133,141,150,160,164],"geometric":[24],"consistency":[25],"within":[26],"adjacent":[27],"frames,":[28],"most":[29,66],"VO":[31,175],"methods":[32],"ignore":[33],"temporal":[35,114],"continuity":[36],"of":[37,67,109],"camera":[39,92,137],"pose,":[40],"which":[41,82,145],"results":[42,165],"in":[43,49,65,135,149],"very":[45],"severe":[46],"jagged":[47],"fluctuation":[48],"velocity":[51],"curves.":[52],"With":[53],"observation":[55],"that":[56],"vehicles":[58,111],"tend":[59],"to":[60,76,86,131,171],"perform":[61],"smooth":[62],"dynamic":[63,128],"characteristics":[64],"time,":[69],"design":[71],"inertia":[73],"loss":[74],"function":[75],"describe":[77],"abnormal":[79],"motion":[80,138],"variation,":[81],"assists":[83],"model":[85],"learn":[87],"consecutiveness":[89,115],"from":[90],"long-term":[91],"ego-motion.":[93],"Based":[94],"on":[95,159],"recurrent":[97],"convolutional":[98],"neural":[99],"network":[100],"(RCNN)":[101],"architecture,":[102],"our":[103],"method":[104,156],"implicitly":[105],"models":[106],"dynamics":[108],"and":[112,144,163,176],"by":[116,139],"extended":[118],"Long":[119],"Short-Term":[120],"Memory":[121],"(LSTM)":[122],"block.":[123],"Furthermore,":[124],"develop":[126],"hard-edge":[129],"mask":[130],"handle":[132],"non-consistency":[134,152],"fast":[136],"blocking":[140],"boundary":[142],"part":[143],"generates":[146],"more":[147],"efficiency":[148],"whole":[151],"mask.":[153],"The":[154],"proposed":[155],"is":[157],"evaluated":[158],"KITTI":[161],"dataset,":[162],"demonstrate":[166],"state-of-the-art":[167],"performance":[168],"with":[169],"respect":[170],"other":[172],"SLAM":[177],"approaches.":[178]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}