大葉大學圖書館 |

Leveraging Occlusions for Causal Video Object Segmentation.

紀錄類型:	書目-電子資源 : Monograph/item
書名/作者:	Leveraging Occlusions for Causal Video Object Segmentation.
作者:	Taylor, Brian.
出版者:	Ann Arbor : : ProQuest Dissertations & Theses, , 2016
面頁冊數:	114 p.
附註:	Source: Dissertation Abstracts International, Volume: 77-08(E), Section: B.
Contained By:	Dissertation Abstracts International77-08B(E).
標題:	Computer science.
ISBN:	9781339546315
摘要、提要註:	This thesis describes a framework leveraging occlusions as a cue for detecting objects and accurately localizing their boundaries throughout the course of a video. Triggered by the motion of objects in the scene, occlusions provide coarse knowledge of the spatial relationship of objects with respect to the viewer. While effective for detecting objects when motion is sufficient, we explore ways to reliably detect and track objects when motion is inadequate or difficult to estimate. In the first half, we incorporate semantic classifiers to provide cues when occlusions are weak, and observe occlusion and appearance information to be mutually beneficial, yielding results more resilient to failures of the component systems acting alone. Our system is evaluated on the semantic segmentation task. In the latter half, we drop semantics and instead devise a causal framework integrating segmentation results and occlusion cues from frames processed in the past. So long as objects move sufficiently with respect to the viewer at some point, they will be detected and subsequently tracked for the rest of the video. We evaluated our approach on the video object segmentation problem. The resulting system has the capability to automatically discover objects from occlusions in video and track their shapes as they evolve over time. Coarse depth is provided as a byproduct and the assignment of semantic category labels can be integrated in a natural way.

Leveraging Occlusions for Causal Video Object Segmentation.
Taylor, Brian.

Leveraging Occlusions for Causal Video Object Segmentation. - Ann Arbor : ProQuest Dissertations & Theses, 2016 - 114 p.

Source: Dissertation Abstracts International, Volume: 77-08(E), Section: B.

Thesis (Ph.D.)--University of California, Los Angeles, 2016.

This item is not available from ProQuest Dissertations & Theses.

This thesis describes a framework leveraging occlusions as a cue for detecting objects and accurately localizing their boundaries throughout the course of a video. Triggered by the motion of objects in the scene, occlusions provide coarse knowledge of the spatial relationship of objects with respect to the viewer. While effective for detecting objects when motion is sufficient, we explore ways to reliably detect and track objects when motion is inadequate or difficult to estimate. In the first half, we incorporate semantic classifiers to provide cues when occlusions are weak, and observe occlusion and appearance information to be mutually beneficial, yielding results more resilient to failures of the component systems acting alone. Our system is evaluated on the semantic segmentation task. In the latter half, we drop semantics and instead devise a causal framework integrating segmentation results and occlusion cues from frames processed in the past. So long as objects move sufficiently with respect to the viewer at some point, they will be detected and subsequently tracked for the rest of the video. We evaluated our approach on the video object segmentation problem. The resulting system has the capability to automatically discover objects from occlusions in video and track their shapes as they evolve over time. Coarse depth is provided as a byproduct and the assignment of semantic category labels can be integrated in a natural way.

ISBN: 9781339546315Subjects--Topical Terms:

182962
Computer science.

Leveraging Occlusions for Causal Video Object Segmentation.
LDR:02339nmm a2200277 4500 001 476181
005 20170614101402.5
008 181208s2016 ||||||||||||||||| ||eng d
020 $a 9781339546315
035 $a (MiAaPQ)AAI10036461
035 $a AAI10036461
040 $a MiAaPQ $c MiAaPQ
100 1 $a Taylor, Brian. $3 686714
245 1 0 $a Leveraging Occlusions for Causal Video Object Segmentation.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2016
300 $a 114 p.
500 $a Source: Dissertation Abstracts International, Volume: 77-08(E), Section: B.
500 $a Adviser: Stefano Soatto.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2016.
506 $a This item is not available from ProQuest Dissertations & Theses.
520 $a This thesis describes a framework leveraging occlusions as a cue for detecting objects and accurately localizing their boundaries throughout the course of a video. Triggered by the motion of objects in the scene, occlusions provide coarse knowledge of the spatial relationship of objects with respect to the viewer. While effective for detecting objects when motion is sufficient, we explore ways to reliably detect and track objects when motion is inadequate or difficult to estimate. In the first half, we incorporate semantic classifiers to provide cues when occlusions are weak, and observe occlusion and appearance information to be mutually beneficial, yielding results more resilient to failures of the component systems acting alone. Our system is evaluated on the semantic segmentation task. In the latter half, we drop semantics and instead devise a causal framework integrating segmentation results and occlusion cues from frames processed in the past. So long as objects move sufficiently with respect to the viewer at some point, they will be detected and subsequently tracked for the rest of the video. We evaluated our approach on the video object segmentation problem. The resulting system has the capability to automatically discover objects from occlusions in video and track their shapes as they evolve over time. Coarse depth is provided as a byproduct and the assignment of semantic category labels can be integrated in a natural way.
590 $a School code: 0031.
650 4 $a Computer science. $3 182962
690 $a 0984
710 2 0 $a University of California, Los Angeles. $b Computer Science. $3 686715
773 0 $t Dissertation Abstracts International $g 77-08B(E).
790 $a 0031
791 $a Ph.D.
792 $a 2016
793 $a English