{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/50664"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/50664","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Depth map recovery from videos","abstract":"The depth map of a video is a very important piece of information. Recovering the depth map of a video expands a 2D video into its 3rd dimension, and creates new possibilities, such as, object insertion, conversion to 3D, shallow depth of field simulation. In this work, we introduce our approach of recovering depth maps from a video sequence with a moving camera and moving objects. Our approach isolates moving objects of each frame and estimates the depth of the scene and the moving objects separately. It takes advantage of the fact that the surfaces that belong to the same object share similar optical flow angles, and have smooth optical flow angle gradients, that can be exploited to recover object boundaries, thereby isolating moving objects from the static part of the scene. \\\\ It recovers the relative depth of the static part of the scene by calculating the likelihood of a pixel belonging to the farthest background using the magnitude of the optical flow and recovered 3D points. It then estimates the depth of moving objects by finding a statistically most likely actual size of the object and converting the actual size to its actual depth. Finally, we reinsert the estimated depth moving object into the estimated depth of the rest of the scene.","abstract_html":"The depth map of a video is a very important piece of information. Recovering the depth map of a video expands a 2D video into its 3rd dimension, and creates new possibilities, such as, object insertion, conversion to 3D, shallow depth of field simulation. In this work, we introduce our approach of recovering depth maps from a video sequence with a moving camera and moving objects. Our approach isolates moving objects of each frame and estimates the depth of the scene and the moving objects separately. It takes advantage of the fact that the surfaces that belong to the same object share similar optical flow angles, and have smooth optical flow angle gradients, that can be exploited to recover object boundaries, thereby isolating moving objects from the static part of the scene. \\\\ It recovers the relative depth of the static part of the scene by calculating the likelihood of a pixel belonging to the farthest background using the magnitude of the optical flow and recovered 3D points. It then estimates the depth of moving objects by finding a statistically most likely actual size of the object and converting the actual size to its actual depth. Finally, we reinsert the estimated depth moving object into the estimated depth of the rest of the scene.","abstract_has_math":false,"creators":["Wang, Jiqin"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Forsyth, David A."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-09-16T17:25:02Z","date_published":"2014-09-16T17:25:02Z","updated_at":"2026-07-22T22:25:40Z","subjects":["depth map recovery","computer vision","motion segmentation"],"languages":["en"],"rights":["Copyright 2014 Jiqin Wang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/50664","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Forsyth, David A."]},{"key":"dc:creator","label":"Author","values":["Wang, Jiqin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2014-09-16T17:25:02Z","2014-08","2014-09-16"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["depth map recovery","computer vision","motion segmentation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2014 Jiqin Wang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/50664"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The depth map of a video is a very important piece of information. Recovering the depth map of a video expands a 2D video into its 3rd dimension, and creates new possibilities, such as, object insertion, conversion to 3D, shallow depth of field simulation. In this work, we introduce our approach of recovering depth maps from a video sequence with a moving camera and moving objects. Our approach isolates moving objects of each frame and estimates the depth of the scene and the moving objects separately. It takes advantage of the fact that the surfaces that belong to the same object share similar optical flow angles, and have smooth optical flow angle gradients, that can be exploited to recover object boundaries, thereby isolating moving objects from the static part of the scene. \\\\ It recovers the relative depth of the static part of the scene by calculating the likelihood of a pixel belonging to the farthest background using the magnitude of the optical flow and recovered 3D points. It then estimates the depth of moving objects by finding a statistically most likely actual size of the object and converting the actual size to its actual depth. Finally, we reinsert the estimated depth moving object into the estimated depth of the rest of the scene.","Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2014-07-24T13:26:42Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Wang_Jiqin.pdf: 35891911 bytes, checksum: 50b2f3c147657b1f45db6f182de37acb (MD5)","Made available in DSpace on 2014-09-16T17:25:02Z (GMT). No. of bitstreams: 2 Jiqin_Wang.pdf: 35891911 bytes, checksum: 50b2f3c147657b1f45db6f182de37acb (MD5) license.txt: 4059 bytes, checksum: ba6b86aee33a58a0b8390e12603798e0 (MD5)"]},{"key":"dc:title","label":"Title","values":["Depth map recovery from videos"]}]}],"canonical_facts":{"dc:contributor":["Forsyth, David A."],"dc:creator":["Wang, Jiqin"],"dc:date":["2014-09-16T17:25:02Z","2014-08","2014-09-16"],"dc:description":["The depth map of a video is a very important piece of information. Recovering the depth map of a video expands a 2D video into its 3rd dimension, and creates new possibilities, such as, object insertion, conversion to 3D, shallow depth of field simulation. In this work, we introduce our approach of recovering depth maps from a video sequence with a moving camera and moving objects. Our approach isolates moving objects of each frame and estimates the depth of the scene and the moving objects separately. It takes advantage of the fact that the surfaces that belong to the same object share similar optical flow angles, and have smooth optical flow angle gradients, that can be exploited to recover object boundaries, thereby isolating moving objects from the static part of the scene. \\\\ It recovers the relative depth of the static part of the scene by calculating the likelihood of a pixel belonging to the farthest background using the magnitude of the optical flow and recovered 3D points. It then estimates the depth of moving objects by finding a statistically most likely actual size of the object and converting the actual size to its actual depth. Finally, we reinsert the estimated depth moving object into the estimated depth of the rest of the scene.","Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2014-07-24T13:26:42Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Wang_Jiqin.pdf: 35891911 bytes, checksum: 50b2f3c147657b1f45db6f182de37acb (MD5)","Made available in DSpace on 2014-09-16T17:25:02Z (GMT). No. of bitstreams: 2 Jiqin_Wang.pdf: 35891911 bytes, checksum: 50b2f3c147657b1f45db6f182de37acb (MD5) license.txt: 4059 bytes, checksum: ba6b86aee33a58a0b8390e12603798e0 (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/50664"],"dc:language":["en"],"dc:rights":["Copyright 2014 Jiqin Wang"],"dc:subject":["depth map recovery","computer vision","motion segmentation"],"dc:title":["Depth map recovery from videos"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:40Z"}