Loading…
Contour grouping with shape manifold and distance transform
Object detection in clutter or occlusion is a hard problem in computer vision. We propose an object detection method based on contour grouping. Two stages are included: a novel distance transform is applied to match templates to the test image so that candidates and locations of the object are obtai...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 4 |
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Zou Qi Luo Siwei Huang Yaping Li Yan |
| description | Object detection in clutter or occlusion is a hard problem in computer vision. We propose an object detection method based on contour grouping. Two stages are included: a novel distance transform is applied to match templates to the test image so that candidates and locations of the object are obtained; verification using shape manifold is performed to preclude outliers and identify the prior. We use the prior combined with bottom-up edge information to produce the final grouping result. Our contribution lies in two aspects: one is the novel distance transform saves much searching space; the other is introducing shape manifold in verifying candidates of grouping. Experiments show our method achieves considerable accuracy in occlusion and background clutter. Specially, the only feature used is edge and contour rather than combination of multi features. |
| doi_str_mv | 10.1109/ICPR.2008.4761578 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_4761578</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4761578</ieee_id><sourcerecordid>4761578</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-6ede4ca0fd9f82ae5216babb3b29af95028e06ec86a55555aa28b483c4f1df403</originalsourceid><addsrcrecordid>eNpVkMtKw0AUhscbWGsfQNzMCySeM7fM4EpC1UJBke7LSTLTjjQXJini24vYjf_mW3zwLX7G7hByRHAPq_L9IxcANleFQV3YM7ZwhUUllBJYaHPOZsJKzApV6It_TrlLNkPQmCmj8ZrdjOMngACp7Yw9ln039cfEd6k_DrHb8a847fm4p8HzlroY-kPDqWt4E8eJutrzKVE3hj61t-wq0GH0ixPnbPO83JSv2frtZVU-rbPoYMqMb7yqCULjghXktUBTUVXJSjgKToOwHoyvrSH9OyJhK2VlrQI2QYGcs_u_bPTeb4cUW0rf29MN8geTDk07</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Contour grouping with shape manifold and distance transform</title><source>IEEE Xplore All Conference Series</source><creator>Zou Qi ; Luo Siwei ; Huang Yaping ; Li Yan</creator><creatorcontrib>Zou Qi ; Luo Siwei ; Huang Yaping ; Li Yan</creatorcontrib><description>Object detection in clutter or occlusion is a hard problem in computer vision. We propose an object detection method based on contour grouping. Two stages are included: a novel distance transform is applied to match templates to the test image so that candidates and locations of the object are obtained; verification using shape manifold is performed to preclude outliers and identify the prior. We use the prior combined with bottom-up edge information to produce the final grouping result. Our contribution lies in two aspects: one is the novel distance transform saves much searching space; the other is introducing shape manifold in verifying candidates of grouping. Experiments show our method achieves considerable accuracy in occlusion and background clutter. Specially, the only feature used is edge and contour rather than combination of multi features.</description><identifier>ISSN: 1051-4651</identifier><identifier>ISBN: 9781424421749</identifier><identifier>ISBN: 1424421748</identifier><identifier>EISSN: 2831-7475</identifier><identifier>EISBN: 9781424421756</identifier><identifier>EISBN: 1424421756</identifier><identifier>DOI: 10.1109/ICPR.2008.4761578</identifier><language>eng</language><publisher>IEEE</publisher><subject>Boosting ; Computer vision ; Information technology ; Management training ; Object detection ; Object recognition ; Performance evaluation ; Shape ; Support vector machines ; Testing</subject><ispartof>2008 19th International Conference on Pattern Recognition, 2008, p.1-4</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4761578$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4761578$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zou Qi</creatorcontrib><creatorcontrib>Luo Siwei</creatorcontrib><creatorcontrib>Huang Yaping</creatorcontrib><creatorcontrib>Li Yan</creatorcontrib><title>Contour grouping with shape manifold and distance transform</title><title>2008 19th International Conference on Pattern Recognition</title><addtitle>ICPR</addtitle><description>Object detection in clutter or occlusion is a hard problem in computer vision. We propose an object detection method based on contour grouping. Two stages are included: a novel distance transform is applied to match templates to the test image so that candidates and locations of the object are obtained; verification using shape manifold is performed to preclude outliers and identify the prior. We use the prior combined with bottom-up edge information to produce the final grouping result. Our contribution lies in two aspects: one is the novel distance transform saves much searching space; the other is introducing shape manifold in verifying candidates of grouping. Experiments show our method achieves considerable accuracy in occlusion and background clutter. Specially, the only feature used is edge and contour rather than combination of multi features.</description><subject>Boosting</subject><subject>Computer vision</subject><subject>Information technology</subject><subject>Management training</subject><subject>Object detection</subject><subject>Object recognition</subject><subject>Performance evaluation</subject><subject>Shape</subject><subject>Support vector machines</subject><subject>Testing</subject><issn>1051-4651</issn><issn>2831-7475</issn><isbn>9781424421749</isbn><isbn>1424421748</isbn><isbn>9781424421756</isbn><isbn>1424421756</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpVkMtKw0AUhscbWGsfQNzMCySeM7fM4EpC1UJBke7LSTLTjjQXJini24vYjf_mW3zwLX7G7hByRHAPq_L9IxcANleFQV3YM7ZwhUUllBJYaHPOZsJKzApV6It_TrlLNkPQmCmj8ZrdjOMngACp7Yw9ln039cfEd6k_DrHb8a847fm4p8HzlroY-kPDqWt4E8eJutrzKVE3hj61t-wq0GH0ixPnbPO83JSv2frtZVU-rbPoYMqMb7yqCULjghXktUBTUVXJSjgKToOwHoyvrSH9OyJhK2VlrQI2QYGcs_u_bPTeb4cUW0rf29MN8geTDk07</recordid><startdate>200812</startdate><enddate>200812</enddate><creator>Zou Qi</creator><creator>Luo Siwei</creator><creator>Huang Yaping</creator><creator>Li Yan</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200812</creationdate><title>Contour grouping with shape manifold and distance transform</title><author>Zou Qi ; Luo Siwei ; Huang Yaping ; Li Yan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-6ede4ca0fd9f82ae5216babb3b29af95028e06ec86a55555aa28b483c4f1df403</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Boosting</topic><topic>Computer vision</topic><topic>Information technology</topic><topic>Management training</topic><topic>Object detection</topic><topic>Object recognition</topic><topic>Performance evaluation</topic><topic>Shape</topic><topic>Support vector machines</topic><topic>Testing</topic><toplevel>online_resources</toplevel><creatorcontrib>Zou Qi</creatorcontrib><creatorcontrib>Luo Siwei</creatorcontrib><creatorcontrib>Huang Yaping</creatorcontrib><creatorcontrib>Li Yan</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zou Qi</au><au>Luo Siwei</au><au>Huang Yaping</au><au>Li Yan</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Contour grouping with shape manifold and distance transform</atitle><btitle>2008 19th International Conference on Pattern Recognition</btitle><stitle>ICPR</stitle><date>2008-12</date><risdate>2008</risdate><spage>1</spage><epage>4</epage><pages>1-4</pages><issn>1051-4651</issn><eissn>2831-7475</eissn><isbn>9781424421749</isbn><isbn>1424421748</isbn><eisbn>9781424421756</eisbn><eisbn>1424421756</eisbn><abstract>Object detection in clutter or occlusion is a hard problem in computer vision. We propose an object detection method based on contour grouping. Two stages are included: a novel distance transform is applied to match templates to the test image so that candidates and locations of the object are obtained; verification using shape manifold is performed to preclude outliers and identify the prior. We use the prior combined with bottom-up edge information to produce the final grouping result. Our contribution lies in two aspects: one is the novel distance transform saves much searching space; the other is introducing shape manifold in verifying candidates of grouping. Experiments show our method achieves considerable accuracy in occlusion and background clutter. Specially, the only feature used is edge and contour rather than combination of multi features.</abstract><pub>IEEE</pub><doi>10.1109/ICPR.2008.4761578</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1051-4651 |
| ispartof | 2008 19th International Conference on Pattern Recognition, 2008, p.1-4 |
| issn | 1051-4651 2831-7475 |
| language | eng |
| recordid | cdi_ieee_primary_4761578 |
| source | IEEE Xplore All Conference Series |
| subjects | Boosting Computer vision Information technology Management training Object detection Object recognition Performance evaluation Shape Support vector machines Testing |
| title | Contour grouping with shape manifold and distance transform |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T16%3A52%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Contour%20grouping%20with%20shape%20manifold%20and%20distance%20transform&rft.btitle=2008%2019th%20International%20Conference%20on%20Pattern%20Recognition&rft.au=Zou%20Qi&rft.date=2008-12&rft.spage=1&rft.epage=4&rft.pages=1-4&rft.issn=1051-4651&rft.eissn=2831-7475&rft.isbn=9781424421749&rft.isbn_list=1424421748&rft_id=info:doi/10.1109/ICPR.2008.4761578&rft.eisbn=9781424421756&rft.eisbn_list=1424421756&rft_dat=%3Cieee_CHZPO%3E4761578%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-6ede4ca0fd9f82ae5216babb3b29af95028e06ec86a55555aa28b483c4f1df403%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4761578&rfr_iscdi=true |