{"id":5156,"date":"2011-08-17T22:01:34","date_gmt":"2011-08-17T19:01:34","guid":{"rendered":"http:\/\/hgpu.org\/?p=5156"},"modified":"2011-08-18T21:12:17","modified_gmt":"2011-08-18T18:12:17","slug":"fast-boosting-trees-for-classification-pose-detection-and-boundary-detection-on-a-gpu","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=5156","title":{"rendered":"Fast boosting trees for classification, pose detection, and boundary detection on a GPU"},"content":{"rendered":"<p>Discriminative classifiers are often the computational bottleneck in medical imaging applications such as foreground\/background classification, 3D pose detection, and boundary delineation. To overcome this bottleneck, we propose a fast technique based on boosting tree classifiers adapted for GPU computation. Unlike standard tree-based algorithms, our method does not have any recursive calls which makes it GPU-friendly. The algorithm is integrated into an optimized Hierarchical Detection Network (HDN) for 3D pose detection and boundary detection in 3D medical images. On desktop GPUs, we demonstrate an 80x speedup in simple classification of Liver in MRI volumes, and 30x speedup in multi-object localization of fetal head structures in ultrasound images, and 10x speedup on 2.49 mm accurate Liver boundary detection in MRI.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Discriminative classifiers are often the computational bottleneck in medical imaging applications such as foreground\/background classification, 3D pose detection, and boundary delineation. To overcome this bottleneck, we propose a fast technique based on boosting tree classifiers adapted for GPU computation. Unlike standard tree-based algorithms, our method does not have any recursive calls which makes it GPU-friendly. [&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":[36,89,38,3],"tags":[1787,14,1788,807,20,379,208],"class_list":["post-5156","post","type-post","status-publish","format-standard","hentry","category-algorithms","category-nvidia-cuda","category-medicine","category-paper","tag-algorithms","tag-cuda","tag-medicine","tag-mri","tag-nvidia","tag-nvidia-geforce-gtx-480","tag-ultrasound"],"views":2163,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5156","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=5156"}],"version-history":[{"count":1,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5156\/revisions"}],"predecessor-version":[{"id":5181,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5156\/revisions\/5181"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5156"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5156"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5156"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}