Improvement of stereo matching algorithm based on sum of gradient magnitude differences and semi-global method with refinement step
A new stereo matching algorithm which uses improved matching cost computation and optimisation using the semi-global method (SGM) is proposed. The absolute difference is sensitive to low textured regions and high noise on the stereo images with radiometric distortions. To get over these problems, su...
Gespeichert in:
| Veröffentlicht in: | Electronics letters 2018-07, Vol.54 (14), p.876-878 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 878 |
|---|---|
| container_issue | 14 |
| container_start_page | 876 |
| container_title | Electronics letters |
| container_volume | 54 |
| creator | Hamzah, R.A Ibrahim, H |
| description | A new stereo matching algorithm which uses improved matching cost computation and optimisation using the semi-global method (SGM) is proposed. The absolute difference is sensitive to low textured regions and high noise on the stereo images with radiometric distortions. To get over these problems, sum of gradient magnitude differences has been introduced at the first stage. This method is strong against the radiometric differences on the stereo images. Hence, this approach will reduce the error of preliminary data for stereo corresponding process. The SGM is used at the aggregation, and optimisation stage uses 16 different directions of 2D path. Additionally, the iterative guided filter is utilised at the refinement stage which minimises the errors and increases the accuracy. The proposed work produces accurate results and performs much better compared with some established algorithms based on the standard stereo benchmarking evaluation from the Middlebury and KITTI. |
| doi_str_mv | 10.1049/el.2017.3956 |
| format | Article |
| fullrecord | <record><control><sourceid>wiley_24P</sourceid><recordid>TN_cdi_crossref_primary_10_1049_el_2017_3956</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>ELL2BF05790</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3810-297d6c5dec0ba18cb96d3c4be7902b0f3cb1c7f35ddcce025fa9172bf4051e1b3</originalsourceid><addsrcrecordid>eNp9kLtOwzAUhi0EEhV04wE8MDCQ4hPHDRkBlYsUiQUktsiX49Qojis7BTHz4iQqAwMwneX7L-cn5ATYAlhRXWC3yBmUC16J5R6ZARcsqwBe9smMMeCZgKo4JPOUnGJQQLFkBczI54PfxPCGHvuBBkvTgBED9XLQa9e3VHZtiG5Ye6pkQkNDT9PWT2QbpXGTysu2d8PWIDXO2lHea0xU9oYm9C5ru6BkRz0O62Do--hFI1rX7yLHvM0xObCySzj_vkfk-Xb1dHOf1Y93DzdXdab5JbAsr0qz1MKgZkrCpVbV0nBdKCwrlitmuVagS8uFMVojy4WVFZS5sgUTgKD4ETnf-eoYUhpLNJvovIwfDbBm2rDBrpk2bKYNR1zs8HfX4ce_bLOq6_z6lomxyqg72-kcDs1r2MZ-fOqviNNf0FX9w3ljLP8CcMWQ8Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Improvement of stereo matching algorithm based on sum of gradient magnitude differences and semi-global method with refinement step</title><source>Wiley Online Library Open Access</source><creator>Hamzah, R.A ; Ibrahim, H</creator><creatorcontrib>Hamzah, R.A ; Ibrahim, H</creatorcontrib><description>A new stereo matching algorithm which uses improved matching cost computation and optimisation using the semi-global method (SGM) is proposed. The absolute difference is sensitive to low textured regions and high noise on the stereo images with radiometric distortions. To get over these problems, sum of gradient magnitude differences has been introduced at the first stage. This method is strong against the radiometric differences on the stereo images. Hence, this approach will reduce the error of preliminary data for stereo corresponding process. The SGM is used at the aggregation, and optimisation stage uses 16 different directions of 2D path. Additionally, the iterative guided filter is utilised at the refinement stage which minimises the errors and increases the accuracy. The proposed work produces accurate results and performs much better compared with some established algorithms based on the standard stereo benchmarking evaluation from the Middlebury and KITTI.</description><identifier>ISSN: 0013-5194</identifier><identifier>ISSN: 1350-911X</identifier><identifier>EISSN: 1350-911X</identifier><identifier>DOI: 10.1049/el.2017.3956</identifier><language>eng</language><publisher>The Institution of Engineering and Technology</publisher><subject>2D path direction ; absolute difference ; distortion ; error reduction ; gradient methods ; Image and vision processing and display technology ; image filtering ; image matching ; improved matching cost computation ; iterative guided filter ; iterative methods ; low textured regions ; optimisation ; optimisation stage ; radiometric distortions ; radiometry ; refinement step ; semiglobal method ; SGM ; standard stereo benchmarking evaluation ; stereo corresponding process ; stereo image processing ; stereo images ; stereo matching algorithm ; sum of gradient magnitude differences</subject><ispartof>Electronics letters, 2018-07, Vol.54 (14), p.876-878</ispartof><rights>The Institution of Engineering and Technology</rights><rights>2020 The Institution of Engineering and Technology</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3810-297d6c5dec0ba18cb96d3c4be7902b0f3cb1c7f35ddcce025fa9172bf4051e1b3</citedby><cites>FETCH-LOGICAL-c3810-297d6c5dec0ba18cb96d3c4be7902b0f3cb1c7f35ddcce025fa9172bf4051e1b3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1049%2Fel.2017.3956$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1049%2Fel.2017.3956$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,11562,27924,27925,45574,45575,46052,46476</link.rule.ids><linktorsrc>$$Uhttps://onlinelibrary.wiley.com/doi/abs/10.1049%2Fel.2017.3956$$EView_record_in_Wiley-Blackwell$$FView_record_in_$$GWiley-Blackwell</linktorsrc></links><search><creatorcontrib>Hamzah, R.A</creatorcontrib><creatorcontrib>Ibrahim, H</creatorcontrib><title>Improvement of stereo matching algorithm based on sum of gradient magnitude differences and semi-global method with refinement step</title><title>Electronics letters</title><description>A new stereo matching algorithm which uses improved matching cost computation and optimisation using the semi-global method (SGM) is proposed. The absolute difference is sensitive to low textured regions and high noise on the stereo images with radiometric distortions. To get over these problems, sum of gradient magnitude differences has been introduced at the first stage. This method is strong against the radiometric differences on the stereo images. Hence, this approach will reduce the error of preliminary data for stereo corresponding process. The SGM is used at the aggregation, and optimisation stage uses 16 different directions of 2D path. Additionally, the iterative guided filter is utilised at the refinement stage which minimises the errors and increases the accuracy. The proposed work produces accurate results and performs much better compared with some established algorithms based on the standard stereo benchmarking evaluation from the Middlebury and KITTI.</description><subject>2D path direction</subject><subject>absolute difference</subject><subject>distortion</subject><subject>error reduction</subject><subject>gradient methods</subject><subject>Image and vision processing and display technology</subject><subject>image filtering</subject><subject>image matching</subject><subject>improved matching cost computation</subject><subject>iterative guided filter</subject><subject>iterative methods</subject><subject>low textured regions</subject><subject>optimisation</subject><subject>optimisation stage</subject><subject>radiometric distortions</subject><subject>radiometry</subject><subject>refinement step</subject><subject>semiglobal method</subject><subject>SGM</subject><subject>standard stereo benchmarking evaluation</subject><subject>stereo corresponding process</subject><subject>stereo image processing</subject><subject>stereo images</subject><subject>stereo matching algorithm</subject><subject>sum of gradient magnitude differences</subject><issn>0013-5194</issn><issn>1350-911X</issn><issn>1350-911X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNp9kLtOwzAUhi0EEhV04wE8MDCQ4hPHDRkBlYsUiQUktsiX49Qojis7BTHz4iQqAwMwneX7L-cn5ATYAlhRXWC3yBmUC16J5R6ZARcsqwBe9smMMeCZgKo4JPOUnGJQQLFkBczI54PfxPCGHvuBBkvTgBED9XLQa9e3VHZtiG5Ye6pkQkNDT9PWT2QbpXGTysu2d8PWIDXO2lHea0xU9oYm9C5ru6BkRz0O62Do--hFI1rX7yLHvM0xObCySzj_vkfk-Xb1dHOf1Y93DzdXdab5JbAsr0qz1MKgZkrCpVbV0nBdKCwrlitmuVagS8uFMVojy4WVFZS5sgUTgKD4ETnf-eoYUhpLNJvovIwfDbBm2rDBrpk2bKYNR1zs8HfX4ce_bLOq6_z6lomxyqg72-kcDs1r2MZ-fOqviNNf0FX9w3ljLP8CcMWQ8Q</recordid><startdate>20180712</startdate><enddate>20180712</enddate><creator>Hamzah, R.A</creator><creator>Ibrahim, H</creator><general>The Institution of Engineering and Technology</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20180712</creationdate><title>Improvement of stereo matching algorithm based on sum of gradient magnitude differences and semi-global method with refinement step</title><author>Hamzah, R.A ; Ibrahim, H</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3810-297d6c5dec0ba18cb96d3c4be7902b0f3cb1c7f35ddcce025fa9172bf4051e1b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>2D path direction</topic><topic>absolute difference</topic><topic>distortion</topic><topic>error reduction</topic><topic>gradient methods</topic><topic>Image and vision processing and display technology</topic><topic>image filtering</topic><topic>image matching</topic><topic>improved matching cost computation</topic><topic>iterative guided filter</topic><topic>iterative methods</topic><topic>low textured regions</topic><topic>optimisation</topic><topic>optimisation stage</topic><topic>radiometric distortions</topic><topic>radiometry</topic><topic>refinement step</topic><topic>semiglobal method</topic><topic>SGM</topic><topic>standard stereo benchmarking evaluation</topic><topic>stereo corresponding process</topic><topic>stereo image processing</topic><topic>stereo images</topic><topic>stereo matching algorithm</topic><topic>sum of gradient magnitude differences</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hamzah, R.A</creatorcontrib><creatorcontrib>Ibrahim, H</creatorcontrib><collection>CrossRef</collection><jtitle>Electronics letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hamzah, R.A</au><au>Ibrahim, H</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improvement of stereo matching algorithm based on sum of gradient magnitude differences and semi-global method with refinement step</atitle><jtitle>Electronics letters</jtitle><date>2018-07-12</date><risdate>2018</risdate><volume>54</volume><issue>14</issue><spage>876</spage><epage>878</epage><pages>876-878</pages><issn>0013-5194</issn><issn>1350-911X</issn><eissn>1350-911X</eissn><abstract>A new stereo matching algorithm which uses improved matching cost computation and optimisation using the semi-global method (SGM) is proposed. The absolute difference is sensitive to low textured regions and high noise on the stereo images with radiometric distortions. To get over these problems, sum of gradient magnitude differences has been introduced at the first stage. This method is strong against the radiometric differences on the stereo images. Hence, this approach will reduce the error of preliminary data for stereo corresponding process. The SGM is used at the aggregation, and optimisation stage uses 16 different directions of 2D path. Additionally, the iterative guided filter is utilised at the refinement stage which minimises the errors and increases the accuracy. The proposed work produces accurate results and performs much better compared with some established algorithms based on the standard stereo benchmarking evaluation from the Middlebury and KITTI.</abstract><pub>The Institution of Engineering and Technology</pub><doi>10.1049/el.2017.3956</doi><tpages>3</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0013-5194 |
| ispartof | Electronics letters, 2018-07, Vol.54 (14), p.876-878 |
| issn | 0013-5194 1350-911X 1350-911X |
| language | eng |
| recordid | cdi_crossref_primary_10_1049_el_2017_3956 |
| source | Wiley Online Library Open Access |
| subjects | 2D path direction absolute difference distortion error reduction gradient methods Image and vision processing and display technology image filtering image matching improved matching cost computation iterative guided filter iterative methods low textured regions optimisation optimisation stage radiometric distortions radiometry refinement step semiglobal method SGM standard stereo benchmarking evaluation stereo corresponding process stereo image processing stereo images stereo matching algorithm sum of gradient magnitude differences |
| title | Improvement of stereo matching algorithm based on sum of gradient magnitude differences and semi-global method with refinement step |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T23%3A21%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-wiley_24P&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Improvement%20of%20stereo%20matching%20algorithm%20based%20on%20sum%20of%20gradient%20magnitude%20differences%20and%20semi-global%20method%20with%20refinement%20step&rft.jtitle=Electronics%20letters&rft.au=Hamzah,%20R.A&rft.date=2018-07-12&rft.volume=54&rft.issue=14&rft.spage=876&rft.epage=878&rft.pages=876-878&rft.issn=0013-5194&rft.eissn=1350-911X&rft_id=info:doi/10.1049/el.2017.3956&rft_dat=%3Cwiley_24P%3EELL2BF05790%3C/wiley_24P%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |