C's: Sensing the Quality of Traffic Markings Using Camera-Attached Cars
Road maintenance requires local city governments to dedicate a substantial amount of funds in finding and repairing damaged traffic marks and pavements. In developed cities, the total road length is so large that the cost becomes unreasonably high. In this paper, we propose a method of sensing damag...
Gespeichert in:
| Veröffentlicht in: | SICE Journal of Control, Measurement, and System Integration Measurement, and System Integration, 2017, Vol.10(5), pp.393-401 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 401 |
|---|---|
| container_issue | 5 |
| container_start_page | 393 |
| container_title | SICE Journal of Control, Measurement, and System Integration |
| container_volume | 10 |
| creator | KAWASAKI, Takafumi KAWANO, Makoto IWAMOTO, Takeshi MATSUMOTO, Michito YONEZAWA, Takuro NAKAZAWA, Jin TOKUDA, Hideyuki |
| description | Road maintenance requires local city governments to dedicate a substantial amount of funds in finding and repairing damaged traffic marks and pavements. In developed cities, the total road length is so large that the cost becomes unreasonably high. In this paper, we propose a method of sensing damaged traffic marks from images captured by a camera mounted to a car, for the purpose of reducing road maintenance cost. In particular, we utilized convolutional neural networks (CNN), as well as linear support vector machines (SVM) and Random Forest, in developing a system of damage detection. The experiments used thousands of images captured in the wild and showed that the method can detect damages using CNN with 93% accuracy, at maximum, and at reasonable speed (55 images per second). |
| doi_str_mv | 10.9746/jcmsi.10.393 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_proquest_journals_2014453134</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_0f6d166d1e1f41e38c5992937832dd4a</doaj_id><sourcerecordid>2014453134</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2974-8b60191e2bee88023d102cee8c10bfdaccb3dc7dbdade4d79a180477e4e469c13</originalsourceid><addsrcrecordid>eNo9kMtOwzAQRSMEEhV0xwdEYsGGFL-a2GxQVUGpVIQQ7dqa2JM2oU2KnS7697gPsrA84zlzfXWj6I6SgcpE-lSZjS8HoeOKX0Q9KqVIlMrI5bFmiZBSXUd978ucCJoOhWBZL5qMH_xz_I21L-tl3K4w_trBumz3cVPEcwdFUZr4A9xPGPt4caTGsEEHyahtwazQht752-iqgLXH_vm-iRZvr_PxezL7nEzHo1liWHCZyDwlVFFkOaKUhHFLCTOhNpTkhQVjcm5NZnMLFoXNFFBJRJahQJEqQ_lNND3p2gYqvXXlBtxeN1Dq40PjlhpcW5o1alKklqbhIC0ERS7NUCmmeCY5s1ZA0Lo_aW1d87tD3-qq2bk62NeMUCGGnHIRqMcTZVzjvcOi-5USfUheH5M_dCH5gL-c8Mq3sMQO_nfVwcPzRjcxK3Aaa_4HTvGMuw</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2014453134</pqid></control><display><type>article</type><title>C's: Sensing the Quality of Traffic Markings Using Camera-Attached Cars</title><source>EZB-FREE-00999 freely available EZB journals</source><creator>KAWASAKI, Takafumi ; KAWANO, Makoto ; IWAMOTO, Takeshi ; MATSUMOTO, Michito ; YONEZAWA, Takuro ; NAKAZAWA, Jin ; TOKUDA, Hideyuki</creator><creatorcontrib>KAWASAKI, Takafumi ; KAWANO, Makoto ; IWAMOTO, Takeshi ; MATSUMOTO, Michito ; YONEZAWA, Takuro ; NAKAZAWA, Jin ; TOKUDA, Hideyuki</creatorcontrib><description>Road maintenance requires local city governments to dedicate a substantial amount of funds in finding and repairing damaged traffic marks and pavements. In developed cities, the total road length is so large that the cost becomes unreasonably high. In this paper, we propose a method of sensing damaged traffic marks from images captured by a camera mounted to a car, for the purpose of reducing road maintenance cost. In particular, we utilized convolutional neural networks (CNN), as well as linear support vector machines (SVM) and Random Forest, in developing a system of damage detection. The experiments used thousands of images captured in the wild and showed that the method can detect damages using CNN with 93% accuracy, at maximum, and at reasonable speed (55 images per second).</description><identifier>ISSN: 1882-4889</identifier><identifier>EISSN: 1884-9970</identifier><identifier>DOI: 10.9746/jcmsi.10.393</identifier><language>eng</language><publisher>Tokyo: The Society of Instrument and Control Engineers</publisher><subject>Artificial neural networks ; convolutional neural networks ; Damage detection ; deep learning ; Image detection ; image recognition ; inspection ; machine learning ; Maintenance costs ; Neural networks ; Road maintenance ; Road repairing ; Support vector machines</subject><ispartof>SICE Journal of Control, Measurement, and System Integration, 2017, Vol.10(5), pp.393-401</ispartof><rights>2017 The Society of Instrument and Control Engineers</rights><rights>Copyright Japan Science and Technology Agency 2017</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c2974-8b60191e2bee88023d102cee8c10bfdaccb3dc7dbdade4d79a180477e4e469c13</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>KAWASAKI, Takafumi</creatorcontrib><creatorcontrib>KAWANO, Makoto</creatorcontrib><creatorcontrib>IWAMOTO, Takeshi</creatorcontrib><creatorcontrib>MATSUMOTO, Michito</creatorcontrib><creatorcontrib>YONEZAWA, Takuro</creatorcontrib><creatorcontrib>NAKAZAWA, Jin</creatorcontrib><creatorcontrib>TOKUDA, Hideyuki</creatorcontrib><title>C's: Sensing the Quality of Traffic Markings Using Camera-Attached Cars</title><title>SICE Journal of Control, Measurement, and System Integration</title><addtitle>SICE JCMSI</addtitle><description>Road maintenance requires local city governments to dedicate a substantial amount of funds in finding and repairing damaged traffic marks and pavements. In developed cities, the total road length is so large that the cost becomes unreasonably high. In this paper, we propose a method of sensing damaged traffic marks from images captured by a camera mounted to a car, for the purpose of reducing road maintenance cost. In particular, we utilized convolutional neural networks (CNN), as well as linear support vector machines (SVM) and Random Forest, in developing a system of damage detection. The experiments used thousands of images captured in the wild and showed that the method can detect damages using CNN with 93% accuracy, at maximum, and at reasonable speed (55 images per second).</description><subject>Artificial neural networks</subject><subject>convolutional neural networks</subject><subject>Damage detection</subject><subject>deep learning</subject><subject>Image detection</subject><subject>image recognition</subject><subject>inspection</subject><subject>machine learning</subject><subject>Maintenance costs</subject><subject>Neural networks</subject><subject>Road maintenance</subject><subject>Road repairing</subject><subject>Support vector machines</subject><issn>1882-4889</issn><issn>1884-9970</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNo9kMtOwzAQRSMEEhV0xwdEYsGGFL-a2GxQVUGpVIQQ7dqa2JM2oU2KnS7697gPsrA84zlzfXWj6I6SgcpE-lSZjS8HoeOKX0Q9KqVIlMrI5bFmiZBSXUd978ucCJoOhWBZL5qMH_xz_I21L-tl3K4w_trBumz3cVPEcwdFUZr4A9xPGPt4caTGsEEHyahtwazQht752-iqgLXH_vm-iRZvr_PxezL7nEzHo1liWHCZyDwlVFFkOaKUhHFLCTOhNpTkhQVjcm5NZnMLFoXNFFBJRJahQJEqQ_lNND3p2gYqvXXlBtxeN1Dq40PjlhpcW5o1alKklqbhIC0ERS7NUCmmeCY5s1ZA0Lo_aW1d87tD3-qq2bk62NeMUCGGnHIRqMcTZVzjvcOi-5USfUheH5M_dCH5gL-c8Mq3sMQO_nfVwcPzRjcxK3Aaa_4HTvGMuw</recordid><startdate>20170901</startdate><enddate>20170901</enddate><creator>KAWASAKI, Takafumi</creator><creator>KAWANO, Makoto</creator><creator>IWAMOTO, Takeshi</creator><creator>MATSUMOTO, Michito</creator><creator>YONEZAWA, Takuro</creator><creator>NAKAZAWA, Jin</creator><creator>TOKUDA, Hideyuki</creator><general>The Society of Instrument and Control Engineers</general><general>Japan Science and Technology Agency</general><general>Taylor & Francis Group</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7TA</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JG9</scope><scope>L7M</scope><scope>DOA</scope></search><sort><creationdate>20170901</creationdate><title>C's: Sensing the Quality of Traffic Markings Using Camera-Attached Cars</title><author>KAWASAKI, Takafumi ; KAWANO, Makoto ; IWAMOTO, Takeshi ; MATSUMOTO, Michito ; YONEZAWA, Takuro ; NAKAZAWA, Jin ; TOKUDA, Hideyuki</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2974-8b60191e2bee88023d102cee8c10bfdaccb3dc7dbdade4d79a180477e4e469c13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Artificial neural networks</topic><topic>convolutional neural networks</topic><topic>Damage detection</topic><topic>deep learning</topic><topic>Image detection</topic><topic>image recognition</topic><topic>inspection</topic><topic>machine learning</topic><topic>Maintenance costs</topic><topic>Neural networks</topic><topic>Road maintenance</topic><topic>Road repairing</topic><topic>Support vector machines</topic><toplevel>online_resources</toplevel><creatorcontrib>KAWASAKI, Takafumi</creatorcontrib><creatorcontrib>KAWANO, Makoto</creatorcontrib><creatorcontrib>IWAMOTO, Takeshi</creatorcontrib><creatorcontrib>MATSUMOTO, Michito</creatorcontrib><creatorcontrib>YONEZAWA, Takuro</creatorcontrib><creatorcontrib>NAKAZAWA, Jin</creatorcontrib><creatorcontrib>TOKUDA, Hideyuki</creatorcontrib><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Materials Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>SICE Journal of Control, Measurement, and System Integration</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>KAWASAKI, Takafumi</au><au>KAWANO, Makoto</au><au>IWAMOTO, Takeshi</au><au>MATSUMOTO, Michito</au><au>YONEZAWA, Takuro</au><au>NAKAZAWA, Jin</au><au>TOKUDA, Hideyuki</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>C's: Sensing the Quality of Traffic Markings Using Camera-Attached Cars</atitle><jtitle>SICE Journal of Control, Measurement, and System Integration</jtitle><addtitle>SICE JCMSI</addtitle><date>2017-09-01</date><risdate>2017</risdate><volume>10</volume><issue>5</issue><spage>393</spage><epage>401</epage><pages>393-401</pages><issn>1882-4889</issn><eissn>1884-9970</eissn><abstract>Road maintenance requires local city governments to dedicate a substantial amount of funds in finding and repairing damaged traffic marks and pavements. In developed cities, the total road length is so large that the cost becomes unreasonably high. In this paper, we propose a method of sensing damaged traffic marks from images captured by a camera mounted to a car, for the purpose of reducing road maintenance cost. In particular, we utilized convolutional neural networks (CNN), as well as linear support vector machines (SVM) and Random Forest, in developing a system of damage detection. The experiments used thousands of images captured in the wild and showed that the method can detect damages using CNN with 93% accuracy, at maximum, and at reasonable speed (55 images per second).</abstract><cop>Tokyo</cop><pub>The Society of Instrument and Control Engineers</pub><doi>10.9746/jcmsi.10.393</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1882-4889 |
| ispartof | SICE Journal of Control, Measurement, and System Integration, 2017, Vol.10(5), pp.393-401 |
| issn | 1882-4889 1884-9970 |
| language | eng |
| recordid | cdi_proquest_journals_2014453134 |
| source | EZB-FREE-00999 freely available EZB journals |
| subjects | Artificial neural networks convolutional neural networks Damage detection deep learning Image detection image recognition inspection machine learning Maintenance costs Neural networks Road maintenance Road repairing Support vector machines |
| title | C's: Sensing the Quality of Traffic Markings Using Camera-Attached Cars |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T11%3A16%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=C's:%20Sensing%20the%20Quality%20of%20Traffic%20Markings%20Using%20Camera-Attached%20Cars&rft.jtitle=SICE%20Journal%20of%20Control,%20Measurement,%20and%20System%20Integration&rft.au=KAWASAKI,%20Takafumi&rft.date=2017-09-01&rft.volume=10&rft.issue=5&rft.spage=393&rft.epage=401&rft.pages=393-401&rft.issn=1882-4889&rft.eissn=1884-9970&rft_id=info:doi/10.9746/jcmsi.10.393&rft_dat=%3Cproquest_doaj_%3E2014453134%3C/proquest_doaj_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2014453134&rft_id=info:pmid/&rft_doaj_id=oai_doaj_org_article_0f6d166d1e1f41e38c5992937832dd4a&rfr_iscdi=true |