{"id":4068,"date":"2011-05-19T12:12:24","date_gmt":"2011-05-19T12:12:24","guid":{"rendered":"http:\/\/hgpu.org\/?p=4068"},"modified":"2011-05-19T12:12:24","modified_gmt":"2011-05-19T12:12:24","slug":"improved-poisson-matting-for-a-real-time-tele-presence-system-using-gpu","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=4068","title":{"rendered":"Improved Poisson Matting for a Real Time Tele-presence System Using GPU"},"content":{"rendered":"<p>In this paper, an improved Poisson matting method is proposed to segment participants in real-time at a tele-presence session from their background. In order to improve the matting process, we introduce the concept of color distance and extend the standard Poisson matting using patch matching. The idea of patch based matching algorithm, which is widely used in texture synthesis is adopted here to estimate the foreground and background color more precisely in complex scenes. A set of experimental results demonstrate the accuracy and robustness of the proposed method. We also present a GPU (Graphics Processing Unit) implementation of the algorithm capable of an average speed-up of 25 times compared to its CPU implementation.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In this paper, an improved Poisson matting method is proposed to segment participants in real-time at a tele-presence session from their background. In order to improve the matting process, we introduce the concept of color distance and extend the standard Poisson matting using patch matching. The idea of patch based matching algorithm, which is widely [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[36,11,33,3],"tags":[1787,1782,1786,297],"class_list":["post-4068","post","type-post","status-publish","format-standard","hentry","category-algorithms","category-computer-science","category-image-processing","category-paper","tag-algorithms","tag-computer-science","tag-image-processing","tag-real-time-graphics"],"views":2082,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/4068","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4068"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/4068\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4068"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4068"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4068"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}