{"id":150572,"date":"2006-06-01T00:00:00","date_gmt":"2006-06-01T00:00:00","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/msr-research-item\/the-panum-proxy-algorithm-for-dense-stereo-matching-over-a-volume-of-interest\/"},"modified":"2018-10-16T20:02:32","modified_gmt":"2018-10-17T03:02:32","slug":"the-panum-proxy-algorithm-for-dense-stereo-matching-over-a-volume-of-interest","status":"publish","type":"msr-research-item","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/publication\/the-panum-proxy-algorithm-for-dense-stereo-matching-over-a-volume-of-interest\/","title":{"rendered":"The Panum Proxy Algorithm for Dense Stereo Matching over a Volume of Interest"},"content":{"rendered":"<p>Stereo matching algorithms conventionally match over a<br \/>\nrange of disparities sufficient to encompass all visible 3D<br \/>\nscene points. Human vision however does not do this. It<br \/>\nworks over a narrow band of disparities \u2014 Panum\u2019s fusional<br \/>\nband \u2014 whose typical range may be as little as 1\/20<br \/>\nof the full range of disparities for visible points. Points inside<br \/>\nthe band are fused visually and the remainder of points<br \/>\nare seen as \u201cdiplopic\u201d \u2014 that is with double vision. The<br \/>\nPanum band restriction is important also in machine vision,<br \/>\nboth with active (pan\/tilt) cameras, and with high resolution<br \/>\ncameras and digital pan\/tilt.<br \/>\nA probabilistic approach is presented for dense stereo<br \/>\nmatching under the Panum band restriction. First it is<br \/>\nshown that existing dense stereo algorithms are inadequate<br \/>\nin this problem setting. Secondly it is shown that the main<br \/>\nproblem is segmentation, separating the (left) image into<br \/>\nthe areas that fall respectively inside and outside the band.<br \/>\nThirdly, an approximation is derived that makes up for missing<br \/>\nout-of-band information with a \u201cproxy\u201d based on image<br \/>\nautocorrelation. Lastly it is shown that the Panum Proxy<br \/>\nalgorithm achieves accuracy close to what can be obtained<br \/>\nwhen the full disparity band is available.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Stereo matching algorithms conventionally match over a range of disparities sufficient to encompass all visible 3D scene points. Human vision however does not do this. It works over a narrow band of disparities \u2014 Panum\u2019s fusional band \u2014 whose typical range may be as little as 1\/20 of the full range of disparities for visible [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition","msr_chapter":"","msr_edition":"Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"2339\u20132346","msr_page_range_start":"2339","msr_page_range_end":"2346","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"A. Agarwal, A. Blake","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2006-06-01","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":2006,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[],"msr-publication-type":[193716],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-150572","msr-research-item","type-msr-research-item","status-publish","hentry","msr-locale-en_us"],"msr_publishername":"","msr_edition":"Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition","msr_affiliation":"","msr_published_date":"2006-06-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition","msr_pages_string":"2339\u20132346","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"209048","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"agarwal_cvpr06.pdf","viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2016\/02\/agarwal_cvpr06.pdf","id":209048,"label_id":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":209048,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2016\/02\/agarwal_cvpr06.pdf"}],"msr-author-ordering":[{"type":"text","value":"A. Agarwal","user_id":0,"rest_url":false},{"type":"text","value":"A. Blake","user_id":0,"rest_url":false},{"type":"user_nicename","value":"ablake","user_id":30797,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=ablake"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/150572","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/150572\/revisions"}],"predecessor-version":[{"id":519868,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/150572\/revisions\/519868"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=150572"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=150572"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=150572"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=150572"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=150572"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=150572"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=150572"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=150572"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=150572"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=150572"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=150572"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=150572"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=150572"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}