{"corpus_id":221680045,"paper_sha":"edfa289b5ab4f6b9dd12131f20b76a043205a61d","doi":"10.1109/IROS45743.2020.9340923","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":null,"dblp_id":"conf/iros/LiSKZXG20","acl_id":null,"title":"Lane Marking Verification for High Definition Map Maintenance Using Crowdsourced Images","year":2020,"publication_date":"2020-10-24","venue":"IEEE/RJS International Conference on Intelligent RObots and Systems","journal":{"name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","pages":"2324-2329","volume":null},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle","Conference"],"pubmed_pub_types":null,"s2_fields_of_study":["Computer Science","Engineering","Environmental Science"],"reference_count":30,"citation_count":7,"influential_citation_count":0,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Autonomous vehicles often rely on high-definition (HD) maps to navigate around. However, lane markings (LMs) are not necessarily static objects due to wear & tear from usage and road reconstruction & maintenance. Therefore, the wrong matching between LMs in the HD map and sensor readings may lead to erroneous localization or even cause traffic accidents. It is imperative to keep LMs up-to-date. However, frequently recollecting data with dedicated hardware and specialists to update HD maps is not only cost-prohibitive but also unviable. Here we propose to utilize crowdsourced images from multiple vehicles at different times to help verify LMs for HD map maintenance. We obtain the LM distribution in the image space by considering the camera pose uncertainty in perspective projection. Both LMs in HD map and LMs in the image are treated as observations of LM distributions which allow us to construct posterior conditional distribution (a.k.a Bayesian belief functions) of LMs from either sources. An LM is consistent if belief functions from the map and the image satisfy statistical hypothesis testing. We further extend the Bayesian belief model into a sequential belief update using crowdsourced images. LMs with a higher probability of existence are kept in the HD map whereas those with a lower probability of existence are removed from the HD map. We verify our approach using real data. Experimental results show that our method is capable of verifying and updating LMs in the HD map.","claims":[{"public_id":"cl_689158a37a21cafbb8daa5b8a72802f0","status":"active","text":"A lane marking is considered consistent if belief functions from the map and the image satisfy statistical hypothesis testing.","confidence":0.9,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_689158a37a21cafbb8daa5b8a72802f0"},{"public_id":"cl_422749d2e7ef3886aaa8cdaf6ccd42e9","status":"active","text":"Lane markings in HD maps can become outdated due to wear, tear, and road reconstruction, causing mismatches with sensor readings that may lead to erroneous localization or traffic accidents.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_422749d2e7ef3886aaa8cdaf6ccd42e9"},{"public_id":"cl_e9f0a3a99c6229f384e3f9dcc4325c6e","status":"active","text":"The Bayesian belief model is extended into a sequential belief update using crowdsourced images, keeping lane markings with higher probability of existence in the HD map and removing those with lower probability.","confidence":0.9,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_e9f0a3a99c6229f384e3f9dcc4325c6e"},{"public_id":"cl_1578afa5e1336b0e66c34af68c83de60","status":"active","text":"The method models lane marking distribution in image space by considering camera pose uncertainty in perspective projection, and treats both HD map lane markings and image lane markings as observations to construct Bayesian belief functions.","confidence":0.9,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_1578afa5e1336b0e66c34af68c83de60"},{"public_id":"cl_5764c44af36a87e144caad64c97f1448","status":"active","text":"The proposed method uses crowdsourced images from multiple vehicles at different times to verify lane markings for HD map maintenance, avoiding cost-prohibitive dedicated data collection.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_5764c44af36a87e144caad64c97f1448"}],"concepts":[{"public_id":"co_060ed173adecaa284337035948e7ab06","status":"active","name":"statistical hypothesis testing","description":"A test used to determine whether belief functions from map and image are consistent for a lane marking.","types":["method"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_060ed173adecaa284337035948e7ab06"},{"public_id":"co_322f4c26875149e4c05cbf33ff5bd9ad","status":"active","name":"sequential belief update","description":"An extension of the Bayesian belief model that updates lane marking existence probabilities using multiple crowdsourced images over time.","types":["algorithm"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_322f4c26875149e4c05cbf33ff5bd9ad"},{"public_id":"co_460835d168c4e8e3500b0a6936318f4e","status":"active","name":"probability of existence","description":"A computed probability indicating whether a lane marking should be kept or removed from the HD map.","types":["metric"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_460835d168c4e8e3500b0a6936318f4e"},{"public_id":"co_6c58dd7c5429f75de01e482526a5f683","status":"active","name":"erroneous localization","description":"Incorrect vehicle position estimation caused by mismatched lane markings between HD map and sensor readings.","types":["failure mode"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_6c58dd7c5429f75de01e482526a5f683"},{"public_id":"co_6ce6cf14a998d66d0c2dae11b4ac1e3b","status":"active","name":"HD map maintenance","description":"The process of keeping HD map lane markings up-to-date by verifying and updating them using crowdsourced data.","types":["task"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_6ce6cf14a998d66d0c2dae11b4ac1e3b"},{"public_id":"co_bd9f2d1b1bdfad65255893e84c8a10f6","status":"active","name":"HD maps","description":"High-definition maps used by autonomous vehicles for navigation, containing precise lane marking information.","types":["data resource"],"aliases":["high-definition maps"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_bd9f2d1b1bdfad65255893e84c8a10f6"},{"public_id":"co_ca816eb83b70737e34faed1d2a2b3ddf","status":"active","name":"crowdsourced images","description":"Images collected from multiple vehicles at different times, used to verify lane markings without dedicated hardware.","types":["data source"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ca816eb83b70737e34faed1d2a2b3ddf"},{"public_id":"co_d733591d85322aa34c286dca041b9dd1","status":"active","name":"Bayesian belief functions","description":"Posterior conditional distributions constructed from both HD map and image observations of lane markings.","types":["mathematical model"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_d733591d85322aa34c286dca041b9dd1"},{"public_id":"co_dee55c81c1b5a3f3412f05cf84ea985e","status":"active","name":"lane markings","description":"Road surface markings that guide vehicle positioning, subject to wear, tear, and reconstruction.","types":["road feature"],"aliases":["LMs"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_dee55c81c1b5a3f3412f05cf84ea985e"},{"public_id":"co_e4acd2ce0dff3e601ccd44643c64a279","status":"active","name":"camera pose uncertainty","description":"Uncertainty in the camera's position and orientation when projecting lane markings into image space.","types":["uncertainty source"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_e4acd2ce0dff3e601ccd44643c64a279"}],"external_ids":{"DOI":"10.1109/IROS45743.2020.9340923","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":null,"DBLP":"conf/iros/LiSKZXG20","ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/221680045","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":637185,"paper_uid":"c8ad89e1-9c5b-4c10-a7f0-25c2bcafb95b","canonical_identity":{"paper_id":637185,"paper_uid":"c8ad89e1-9c5b-4c10-a7f0-25c2bcafb95b","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/221680045"}