Pyramidal Image Segmentation Based on U-Net for Automatic Multiscale Crater Extraction
To extract craters with a radius greater than 10 km more effectively from lunar digital elevation maps, pyramidal image segmentation based on the U-Net model is proposed, and the conversion relationship between the multilayer image pyramid and the geographic coordinates of the crater is established....
Gespeichert in:
| Veröffentlicht in: | Sensors and materials 2022-01, Vol.34 (1), p.237 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 1 |
| container_start_page | 237 |
| container_title | Sensors and materials |
| container_volume | 34 |
| creator | Hong, Zhonghua Fan, Ziyang Zhou, Ruyan Pan, Haiyan Zhang, Yun Han, Yanling Wang, Jing Yang, Shuhu Jin, Yanmin |
| description | To extract craters with a radius greater than 10 km more effectively from lunar digital elevation maps, pyramidal image segmentation based on the U-Net model is proposed, and the conversion relationship between the multilayer image pyramid and the geographic coordinates of the crater is established. The crater image pyramid method ensures the full coverage of the study area with a small number of images and that each crater exists in several images with different resolutions. The proposed method can effectively improve the detection performance of large-scale craters and solve the migration problem when stitching together craters from large-scale images. This method recovered 85.48% of the craters with a radius greater than 10 km in an artificially annotated dataset, found 1044 new craters, and extended the maximum radius of detected craters from 72 km in randomly cropped image segmentation to 200 km. It was estimated by visual interpretation that approximately 82.09% of these new craters are real. Also, the recall reaches 90.17% when the new real craters are added to the true craters. |
| doi_str_mv | 10.18494/SAM3564 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2626960574</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2626960574</sourcerecordid><originalsourceid>FETCH-LOGICAL-c355t-c046385c6261041cd791e524f12b0487b2627b20d8018e2ebd15024661731dd63</originalsourceid><addsrcrecordid>eNotUE1Lw0AUXETBUAv-hAUvXqJvP5McY6laaFWo9Ro2u5uSkjR1dwP237vaXt57MDNvhkHolsADyXnBH9flignJL1BCORMp5LK4RAkUhKe8YOIaTb3fAQDJBUgqE_T1cXSqb43q8KJXW4vXdtvbfVChHfb4SXlrcDw26ZsNuBkcLscw9BHVeDV2ofVadRbPnArW4flPcEr_KW_QVaM6b6fnPUGb5_nn7DVdvr8sZuUy1UyIkGrgkuVCxygEONEmK4gVlDeE1sDzrKaSxgEmj4kttbUhAiiXkmSMGCPZBN2d_h7c8D1aH6rdMLp9tKyiVBYSRMYj6_7E0m7w3tmmOri2V-5YEaj-i6vOxbFfv0tdcA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2626960574</pqid></control><display><type>article</type><title>Pyramidal Image Segmentation Based on U-Net for Automatic Multiscale Crater Extraction</title><source>DOAJ Directory of Open Access Journals</source><source>Alma/SFX Local Collection</source><source>EZB Electronic Journals Library</source><creator>Hong, Zhonghua ; Fan, Ziyang ; Zhou, Ruyan ; Pan, Haiyan ; Zhang, Yun ; Han, Yanling ; Wang, Jing ; Yang, Shuhu ; Jin, Yanmin</creator><creatorcontrib>Hong, Zhonghua ; Fan, Ziyang ; Zhou, Ruyan ; Pan, Haiyan ; Zhang, Yun ; Han, Yanling ; Wang, Jing ; Yang, Shuhu ; Jin, Yanmin</creatorcontrib><description>To extract craters with a radius greater than 10 km more effectively from lunar digital elevation maps, pyramidal image segmentation based on the U-Net model is proposed, and the conversion relationship between the multilayer image pyramid and the geographic coordinates of the crater is established. The crater image pyramid method ensures the full coverage of the study area with a small number of images and that each crater exists in several images with different resolutions. The proposed method can effectively improve the detection performance of large-scale craters and solve the migration problem when stitching together craters from large-scale images. This method recovered 85.48% of the craters with a radius greater than 10 km in an artificially annotated dataset, found 1044 new craters, and extended the maximum radius of detected craters from 72 km in randomly cropped image segmentation to 200 km. It was estimated by visual interpretation that approximately 82.09% of these new craters are real. Also, the recall reaches 90.17% when the new real craters are added to the true craters.</description><identifier>ISSN: 0914-4935</identifier><identifier>EISSN: 2435-0869</identifier><identifier>DOI: 10.18494/SAM3564</identifier><language>eng</language><publisher>Tokyo: MYU Scientific Publishing Division</publisher><subject>Digital imaging ; Digital mapping ; Elevation ; Image segmentation ; Lunar craters ; Multilayers ; Stitching</subject><ispartof>Sensors and materials, 2022-01, Vol.34 (1), p.237</ispartof><rights>Copyright MYU Scientific Publishing Division 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c355t-c046385c6261041cd791e524f12b0487b2627b20d8018e2ebd15024661731dd63</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,861,27905,27906</link.rule.ids></links><search><creatorcontrib>Hong, Zhonghua</creatorcontrib><creatorcontrib>Fan, Ziyang</creatorcontrib><creatorcontrib>Zhou, Ruyan</creatorcontrib><creatorcontrib>Pan, Haiyan</creatorcontrib><creatorcontrib>Zhang, Yun</creatorcontrib><creatorcontrib>Han, Yanling</creatorcontrib><creatorcontrib>Wang, Jing</creatorcontrib><creatorcontrib>Yang, Shuhu</creatorcontrib><creatorcontrib>Jin, Yanmin</creatorcontrib><title>Pyramidal Image Segmentation Based on U-Net for Automatic Multiscale Crater Extraction</title><title>Sensors and materials</title><description>To extract craters with a radius greater than 10 km more effectively from lunar digital elevation maps, pyramidal image segmentation based on the U-Net model is proposed, and the conversion relationship between the multilayer image pyramid and the geographic coordinates of the crater is established. The crater image pyramid method ensures the full coverage of the study area with a small number of images and that each crater exists in several images with different resolutions. The proposed method can effectively improve the detection performance of large-scale craters and solve the migration problem when stitching together craters from large-scale images. This method recovered 85.48% of the craters with a radius greater than 10 km in an artificially annotated dataset, found 1044 new craters, and extended the maximum radius of detected craters from 72 km in randomly cropped image segmentation to 200 km. It was estimated by visual interpretation that approximately 82.09% of these new craters are real. Also, the recall reaches 90.17% when the new real craters are added to the true craters.</description><subject>Digital imaging</subject><subject>Digital mapping</subject><subject>Elevation</subject><subject>Image segmentation</subject><subject>Lunar craters</subject><subject>Multilayers</subject><subject>Stitching</subject><issn>0914-4935</issn><issn>2435-0869</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNotUE1Lw0AUXETBUAv-hAUvXqJvP5McY6laaFWo9Ro2u5uSkjR1dwP237vaXt57MDNvhkHolsADyXnBH9flignJL1BCORMp5LK4RAkUhKe8YOIaTb3fAQDJBUgqE_T1cXSqb43q8KJXW4vXdtvbfVChHfb4SXlrcDw26ZsNuBkcLscw9BHVeDV2ofVadRbPnArW4flPcEr_KW_QVaM6b6fnPUGb5_nn7DVdvr8sZuUy1UyIkGrgkuVCxygEONEmK4gVlDeE1sDzrKaSxgEmj4kttbUhAiiXkmSMGCPZBN2d_h7c8D1aH6rdMLp9tKyiVBYSRMYj6_7E0m7w3tmmOri2V-5YEaj-i6vOxbFfv0tdcA</recordid><startdate>20220101</startdate><enddate>20220101</enddate><creator>Hong, Zhonghua</creator><creator>Fan, Ziyang</creator><creator>Zhou, Ruyan</creator><creator>Pan, Haiyan</creator><creator>Zhang, Yun</creator><creator>Han, Yanling</creator><creator>Wang, Jing</creator><creator>Yang, Shuhu</creator><creator>Jin, Yanmin</creator><general>MYU Scientific Publishing Division</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7SR</scope><scope>7TB</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>FR3</scope><scope>JG9</scope><scope>L7M</scope></search><sort><creationdate>20220101</creationdate><title>Pyramidal Image Segmentation Based on U-Net for Automatic Multiscale Crater Extraction</title><author>Hong, Zhonghua ; Fan, Ziyang ; Zhou, Ruyan ; Pan, Haiyan ; Zhang, Yun ; Han, Yanling ; Wang, Jing ; Yang, Shuhu ; Jin, Yanmin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c355t-c046385c6261041cd791e524f12b0487b2627b20d8018e2ebd15024661731dd63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Digital imaging</topic><topic>Digital mapping</topic><topic>Elevation</topic><topic>Image segmentation</topic><topic>Lunar craters</topic><topic>Multilayers</topic><topic>Stitching</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hong, Zhonghua</creatorcontrib><creatorcontrib>Fan, Ziyang</creatorcontrib><creatorcontrib>Zhou, Ruyan</creatorcontrib><creatorcontrib>Pan, Haiyan</creatorcontrib><creatorcontrib>Zhang, Yun</creatorcontrib><creatorcontrib>Han, Yanling</creatorcontrib><creatorcontrib>Wang, Jing</creatorcontrib><creatorcontrib>Yang, Shuhu</creatorcontrib><creatorcontrib>Jin, Yanmin</creatorcontrib><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Materials Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Sensors and materials</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hong, Zhonghua</au><au>Fan, Ziyang</au><au>Zhou, Ruyan</au><au>Pan, Haiyan</au><au>Zhang, Yun</au><au>Han, Yanling</au><au>Wang, Jing</au><au>Yang, Shuhu</au><au>Jin, Yanmin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Pyramidal Image Segmentation Based on U-Net for Automatic Multiscale Crater Extraction</atitle><jtitle>Sensors and materials</jtitle><date>2022-01-01</date><risdate>2022</risdate><volume>34</volume><issue>1</issue><spage>237</spage><pages>237-</pages><issn>0914-4935</issn><eissn>2435-0869</eissn><abstract>To extract craters with a radius greater than 10 km more effectively from lunar digital elevation maps, pyramidal image segmentation based on the U-Net model is proposed, and the conversion relationship between the multilayer image pyramid and the geographic coordinates of the crater is established. The crater image pyramid method ensures the full coverage of the study area with a small number of images and that each crater exists in several images with different resolutions. The proposed method can effectively improve the detection performance of large-scale craters and solve the migration problem when stitching together craters from large-scale images. This method recovered 85.48% of the craters with a radius greater than 10 km in an artificially annotated dataset, found 1044 new craters, and extended the maximum radius of detected craters from 72 km in randomly cropped image segmentation to 200 km. It was estimated by visual interpretation that approximately 82.09% of these new craters are real. Also, the recall reaches 90.17% when the new real craters are added to the true craters.</abstract><cop>Tokyo</cop><pub>MYU Scientific Publishing Division</pub><doi>10.18494/SAM3564</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0914-4935 |
| ispartof | Sensors and materials, 2022-01, Vol.34 (1), p.237 |
| issn | 0914-4935 2435-0869 |
| language | eng |
| recordid | cdi_proquest_journals_2626960574 |
| source | DOAJ Directory of Open Access Journals; Alma/SFX Local Collection; EZB Electronic Journals Library |
| subjects | Digital imaging Digital mapping Elevation Image segmentation Lunar craters Multilayers Stitching |
| title | Pyramidal Image Segmentation Based on U-Net for Automatic Multiscale Crater Extraction |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T17%3A01%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Pyramidal%20Image%20Segmentation%20Based%20on%20U-Net%20for%20Automatic%20Multiscale%20Crater%20Extraction&rft.jtitle=Sensors%20and%20materials&rft.au=Hong,%20Zhonghua&rft.date=2022-01-01&rft.volume=34&rft.issue=1&rft.spage=237&rft.pages=237-&rft.issn=0914-4935&rft.eissn=2435-0869&rft_id=info:doi/10.18494/SAM3564&rft_dat=%3Cproquest_cross%3E2626960574%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2626960574&rft_id=info:pmid/&rfr_iscdi=true |