A Label Refining Framework Based on Road Matching and Integration Algorithm for Road Extraction
Road network plays an important role in the fields of navigation, urban planning, and transportation. Extracting road network data from imagery based on machine learning models is an efficient and economical method for obtaining road network data. In order to save labor costs, crowdsourced data can...
Gespeichert in:
| Veröffentlicht in: | IEEE journal of selected topics in applied earth observations and remote sensing 2024, Vol.17, p.19548-19564 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 19564 |
|---|---|
| container_issue | |
| container_start_page | 19548 |
| container_title | IEEE journal of selected topics in applied earth observations and remote sensing |
| container_volume | 17 |
| creator | Ma, Guodong Zhang, Meng Yang, Jian Shi, Zekai Ren, Haoyuan Zhang, Yaowei |
| description | Road network plays an important role in the fields of navigation, urban planning, and transportation. Extracting road network data from imagery based on machine learning models is an efficient and economical method for obtaining road network data. In order to save labor costs, crowdsourced data can be employed to automatically acquire the labels for model training. In response to the current challenges in road extraction, such as the limited number of labeled samples, low precision of sample labels generated from crowdsourced data, and difficulty in obtaining accurate road label data, which lead to low-quality, incomplete, and inaccurate road extraction, this study proposes a label refining framework based on a road matching and integrate algorithm. Labels are generated from OpenStreetMap (OSM) vector data, and roads are extracted from very high resolution orthoimage using the U-net model. The extracted roads are then matched and integrated with the original data to generate refined labels, which are employed for further model training and road extraction. Experimental results demonstrate that this process can overcome the poor quality of samples directly generated from the OSM data, i.e., the label refining framework led to significant improvements with respect to the completeness, accuracy, and quality of the road network extraction results. |
| doi_str_mv | 10.1109/JSTARS.2024.3486744 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_10736971</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10736971</ieee_id><doaj_id>oai_doaj_org_article_4e017b2857b849dea7a1193034199abb</doaj_id><sourcerecordid>3127769505</sourcerecordid><originalsourceid>FETCH-LOGICAL-c289t-37093c3d9f901e2458186893f652ad62e28768f7d97675d6765aaaa215b49dc63</originalsourceid><addsrcrecordid>eNpNUclOwzAQtRBIlOUL4GCJc4r35VgQhaIipAJnaxI7JaWNwQkC_h6XIMRcRpp5783yEDqhZEwpsee3D4-TxcOYESbGXBilhdhBI0YlLajkcheNqOW2oIKIfXTQdStCFNOWj5Cb4DmUYY0XoW7apl3iaYJN-IjpBV9AFzyOLV5E8PgO-up5C4DW41nbh2WCvsndyXoZU9M_b3Ad04C9-uwTVNvuEdqrYd2F4998iJ6mV4-XN8X8_np2OZkXFTO2L7gmllfc29oSGpiQhhplLK-VZOAVC8xoZWrtrVZaeqWVhBz5wlJYXyl-iGaDro-wcq-p2UD6chEa91OIaekg9U21Dk4EQnXJjNSlyeQAGmh-D-GCWgtlmbXOBq3XFN_eQ9e7VXxPbV7fccq0VlYSmVF8QFUpdl0K9d9UStzWFTe44rauuF9XMut0YDUhhH8MzZXVlH8DqNyG9Q</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3127769505</pqid></control><display><type>article</type><title>A Label Refining Framework Based on Road Matching and Integration Algorithm for Road Extraction</title><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Ma, Guodong ; Zhang, Meng ; Yang, Jian ; Shi, Zekai ; Ren, Haoyuan ; Zhang, Yaowei</creator><creatorcontrib>Ma, Guodong ; Zhang, Meng ; Yang, Jian ; Shi, Zekai ; Ren, Haoyuan ; Zhang, Yaowei</creatorcontrib><description>Road network plays an important role in the fields of navigation, urban planning, and transportation. Extracting road network data from imagery based on machine learning models is an efficient and economical method for obtaining road network data. In order to save labor costs, crowdsourced data can be employed to automatically acquire the labels for model training. In response to the current challenges in road extraction, such as the limited number of labeled samples, low precision of sample labels generated from crowdsourced data, and difficulty in obtaining accurate road label data, which lead to low-quality, incomplete, and inaccurate road extraction, this study proposes a label refining framework based on a road matching and integrate algorithm. Labels are generated from OpenStreetMap (OSM) vector data, and roads are extracted from very high resolution orthoimage using the U-net model. The extracted roads are then matched and integrated with the original data to generate refined labels, which are employed for further model training and road extraction. Experimental results demonstrate that this process can overcome the poor quality of samples directly generated from the OSM data, i.e., the label refining framework led to significant improvements with respect to the completeness, accuracy, and quality of the road network extraction results.</description><identifier>ISSN: 1939-1404</identifier><identifier>EISSN: 2151-1535</identifier><identifier>DOI: 10.1109/JSTARS.2024.3486744</identifier><identifier>CODEN: IJSTHZ</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Accuracy ; Algorithms ; Biological system modeling ; Crowdsourcing ; Data mining ; Data models ; Digital mapping ; Image acquisition ; Image resolution ; Labels ; Labour costs ; Machine learning ; Matching ; Navigation ; OpenStreetMap ; Refining ; Remote sensing ; road extraction ; road matching ; Roads ; Roads & highways ; satellite imagery ; Semantic segmentation ; Training ; Transportation networks ; U-Net ; Urban planning ; Vectors</subject><ispartof>IEEE journal of selected topics in applied earth observations and remote sensing, 2024, Vol.17, p.19548-19564</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c289t-37093c3d9f901e2458186893f652ad62e28768f7d97675d6765aaaa215b49dc63</cites><orcidid>0000-0002-8744-2922</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,861,2096,4010,27904,27905,27906</link.rule.ids></links><search><creatorcontrib>Ma, Guodong</creatorcontrib><creatorcontrib>Zhang, Meng</creatorcontrib><creatorcontrib>Yang, Jian</creatorcontrib><creatorcontrib>Shi, Zekai</creatorcontrib><creatorcontrib>Ren, Haoyuan</creatorcontrib><creatorcontrib>Zhang, Yaowei</creatorcontrib><title>A Label Refining Framework Based on Road Matching and Integration Algorithm for Road Extraction</title><title>IEEE journal of selected topics in applied earth observations and remote sensing</title><addtitle>JSTARS</addtitle><description>Road network plays an important role in the fields of navigation, urban planning, and transportation. Extracting road network data from imagery based on machine learning models is an efficient and economical method for obtaining road network data. In order to save labor costs, crowdsourced data can be employed to automatically acquire the labels for model training. In response to the current challenges in road extraction, such as the limited number of labeled samples, low precision of sample labels generated from crowdsourced data, and difficulty in obtaining accurate road label data, which lead to low-quality, incomplete, and inaccurate road extraction, this study proposes a label refining framework based on a road matching and integrate algorithm. Labels are generated from OpenStreetMap (OSM) vector data, and roads are extracted from very high resolution orthoimage using the U-net model. The extracted roads are then matched and integrated with the original data to generate refined labels, which are employed for further model training and road extraction. Experimental results demonstrate that this process can overcome the poor quality of samples directly generated from the OSM data, i.e., the label refining framework led to significant improvements with respect to the completeness, accuracy, and quality of the road network extraction results.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Biological system modeling</subject><subject>Crowdsourcing</subject><subject>Data mining</subject><subject>Data models</subject><subject>Digital mapping</subject><subject>Image acquisition</subject><subject>Image resolution</subject><subject>Labels</subject><subject>Labour costs</subject><subject>Machine learning</subject><subject>Matching</subject><subject>Navigation</subject><subject>OpenStreetMap</subject><subject>Refining</subject><subject>Remote sensing</subject><subject>road extraction</subject><subject>road matching</subject><subject>Roads</subject><subject>Roads & highways</subject><subject>satellite imagery</subject><subject>Semantic segmentation</subject><subject>Training</subject><subject>Transportation networks</subject><subject>U-Net</subject><subject>Urban planning</subject><subject>Vectors</subject><issn>1939-1404</issn><issn>2151-1535</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUclOwzAQtRBIlOUL4GCJc4r35VgQhaIipAJnaxI7JaWNwQkC_h6XIMRcRpp5783yEDqhZEwpsee3D4-TxcOYESbGXBilhdhBI0YlLajkcheNqOW2oIKIfXTQdStCFNOWj5Cb4DmUYY0XoW7apl3iaYJN-IjpBV9AFzyOLV5E8PgO-up5C4DW41nbh2WCvsndyXoZU9M_b3Ad04C9-uwTVNvuEdqrYd2F4998iJ6mV4-XN8X8_np2OZkXFTO2L7gmllfc29oSGpiQhhplLK-VZOAVC8xoZWrtrVZaeqWVhBz5wlJYXyl-iGaDro-wcq-p2UD6chEa91OIaekg9U21Dk4EQnXJjNSlyeQAGmh-D-GCWgtlmbXOBq3XFN_eQ9e7VXxPbV7fccq0VlYSmVF8QFUpdl0K9d9UStzWFTe44rauuF9XMut0YDUhhH8MzZXVlH8DqNyG9Q</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Ma, Guodong</creator><creator>Zhang, Meng</creator><creator>Yang, Jian</creator><creator>Shi, Zekai</creator><creator>Ren, Haoyuan</creator><creator>Zhang, Yaowei</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7UA</scope><scope>8FD</scope><scope>C1K</scope><scope>F1W</scope><scope>FR3</scope><scope>H8D</scope><scope>H96</scope><scope>KR7</scope><scope>L.G</scope><scope>L7M</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-8744-2922</orcidid></search><sort><creationdate>2024</creationdate><title>A Label Refining Framework Based on Road Matching and Integration Algorithm for Road Extraction</title><author>Ma, Guodong ; Zhang, Meng ; Yang, Jian ; Shi, Zekai ; Ren, Haoyuan ; Zhang, Yaowei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c289t-37093c3d9f901e2458186893f652ad62e28768f7d97675d6765aaaa215b49dc63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Biological system modeling</topic><topic>Crowdsourcing</topic><topic>Data mining</topic><topic>Data models</topic><topic>Digital mapping</topic><topic>Image acquisition</topic><topic>Image resolution</topic><topic>Labels</topic><topic>Labour costs</topic><topic>Machine learning</topic><topic>Matching</topic><topic>Navigation</topic><topic>OpenStreetMap</topic><topic>Refining</topic><topic>Remote sensing</topic><topic>road extraction</topic><topic>road matching</topic><topic>Roads</topic><topic>Roads & highways</topic><topic>satellite imagery</topic><topic>Semantic segmentation</topic><topic>Training</topic><topic>Transportation networks</topic><topic>U-Net</topic><topic>Urban planning</topic><topic>Vectors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ma, Guodong</creatorcontrib><creatorcontrib>Zhang, Meng</creatorcontrib><creatorcontrib>Yang, Jian</creatorcontrib><creatorcontrib>Shi, Zekai</creatorcontrib><creatorcontrib>Ren, Haoyuan</creatorcontrib><creatorcontrib>Zhang, Yaowei</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Water Resources Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources</collection><collection>Civil Engineering Abstracts</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) Professional</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE journal of selected topics in applied earth observations and remote sensing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ma, Guodong</au><au>Zhang, Meng</au><au>Yang, Jian</au><au>Shi, Zekai</au><au>Ren, Haoyuan</au><au>Zhang, Yaowei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Label Refining Framework Based on Road Matching and Integration Algorithm for Road Extraction</atitle><jtitle>IEEE journal of selected topics in applied earth observations and remote sensing</jtitle><stitle>JSTARS</stitle><date>2024</date><risdate>2024</risdate><volume>17</volume><spage>19548</spage><epage>19564</epage><pages>19548-19564</pages><issn>1939-1404</issn><eissn>2151-1535</eissn><coden>IJSTHZ</coden><abstract>Road network plays an important role in the fields of navigation, urban planning, and transportation. Extracting road network data from imagery based on machine learning models is an efficient and economical method for obtaining road network data. In order to save labor costs, crowdsourced data can be employed to automatically acquire the labels for model training. In response to the current challenges in road extraction, such as the limited number of labeled samples, low precision of sample labels generated from crowdsourced data, and difficulty in obtaining accurate road label data, which lead to low-quality, incomplete, and inaccurate road extraction, this study proposes a label refining framework based on a road matching and integrate algorithm. Labels are generated from OpenStreetMap (OSM) vector data, and roads are extracted from very high resolution orthoimage using the U-net model. The extracted roads are then matched and integrated with the original data to generate refined labels, which are employed for further model training and road extraction. Experimental results demonstrate that this process can overcome the poor quality of samples directly generated from the OSM data, i.e., the label refining framework led to significant improvements with respect to the completeness, accuracy, and quality of the road network extraction results.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/JSTARS.2024.3486744</doi><tpages>17</tpages><orcidid>https://orcid.org/0000-0002-8744-2922</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1939-1404 |
| ispartof | IEEE journal of selected topics in applied earth observations and remote sensing, 2024, Vol.17, p.19548-19564 |
| issn | 1939-1404 2151-1535 |
| language | eng |
| recordid | cdi_ieee_primary_10736971 |
| source | DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Accuracy Algorithms Biological system modeling Crowdsourcing Data mining Data models Digital mapping Image acquisition Image resolution Labels Labour costs Machine learning Matching Navigation OpenStreetMap Refining Remote sensing road extraction road matching Roads Roads & highways satellite imagery Semantic segmentation Training Transportation networks U-Net Urban planning Vectors |
| title | A Label Refining Framework Based on Road Matching and Integration Algorithm for Road Extraction |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T07%3A44%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Label%20Refining%20Framework%20Based%20on%20Road%20Matching%20and%20Integration%20Algorithm%20for%20Road%20Extraction&rft.jtitle=IEEE%20journal%20of%20selected%20topics%20in%20applied%20earth%20observations%20and%20remote%20sensing&rft.au=Ma,%20Guodong&rft.date=2024&rft.volume=17&rft.spage=19548&rft.epage=19564&rft.pages=19548-19564&rft.issn=1939-1404&rft.eissn=2151-1535&rft.coden=IJSTHZ&rft_id=info:doi/10.1109/JSTARS.2024.3486744&rft_dat=%3Cproquest_ieee_%3E3127769505%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3127769505&rft_id=info:pmid/&rft_ieee_id=10736971&rft_doaj_id=oai_doaj_org_article_4e017b2857b849dea7a1193034199abb&rfr_iscdi=true |