File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TPAMI.2014.2360380
- Scopus: eid_2-s2.0-84926435930
- WOS: WOS:000352533000012
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Shape tracking with occlusions via coarse-to-fine region-based sobolev descent
Title | Shape tracking with occlusions via coarse-to-fine region-based sobolev descent |
---|---|
Authors | |
Keywords | deformable templates Object segmentation from video object tracking occlusions optical flow shape metrics |
Issue Date | 2015 |
Citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, v. 37, n. 5, p. 1053-1066 How to Cite? |
Abstract | We present a method to track the shape of an object from video. The method uses a joint shape and appearance model of the object, which is propagated to match shape and radiance in subsequent frames, determining object shape. Self-occlusions and dis-occlusions of the object from camera and object motion pose difficulties to joint shape and appearance models in tracking. They are unable to adapt to new shape and appearance information, leading to inaccurate shape detection. In this work, we model self-occlusions and dis-occlusions in a joint shape and appearance tracking framework. Self-occlusions and the warp to propagate the model are coupled, thus we formulate a joint optimization problem. We derive a coarse-to-fine optimization method, advantageous in tracking, that initially perturbs the model by coarse perturbations before transitioning to finer-scale perturbations seamlessly. This coarse-to-fine behavior is automatically induced by gradient descent on a novel infinite-dimensional Riemannian manifold that we introduce. The manifold consists of planar parameterized regions, and the metric that we introduce is a novel Sobolev metric. Experiments on video exhibiting occlusions/dis-occlusions, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy. |
Persistent Identifier | http://hdl.handle.net/10722/325292 |
ISSN | 2023 Impact Factor: 20.8 2023 SCImago Journal Rankings: 6.158 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, Yanchao | - |
dc.contributor.author | Sundaramoorthi, Ganesh | - |
dc.date.accessioned | 2023-02-27T07:31:17Z | - |
dc.date.available | 2023-02-27T07:31:17Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, v. 37, n. 5, p. 1053-1066 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10722/325292 | - |
dc.description.abstract | We present a method to track the shape of an object from video. The method uses a joint shape and appearance model of the object, which is propagated to match shape and radiance in subsequent frames, determining object shape. Self-occlusions and dis-occlusions of the object from camera and object motion pose difficulties to joint shape and appearance models in tracking. They are unable to adapt to new shape and appearance information, leading to inaccurate shape detection. In this work, we model self-occlusions and dis-occlusions in a joint shape and appearance tracking framework. Self-occlusions and the warp to propagate the model are coupled, thus we formulate a joint optimization problem. We derive a coarse-to-fine optimization method, advantageous in tracking, that initially perturbs the model by coarse perturbations before transitioning to finer-scale perturbations seamlessly. This coarse-to-fine behavior is automatically induced by gradient descent on a novel infinite-dimensional Riemannian manifold that we introduce. The manifold consists of planar parameterized regions, and the metric that we introduce is a novel Sobolev metric. Experiments on video exhibiting occlusions/dis-occlusions, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Pattern Analysis and Machine Intelligence | - |
dc.subject | deformable templates | - |
dc.subject | Object segmentation from video | - |
dc.subject | object tracking | - |
dc.subject | occlusions | - |
dc.subject | optical flow | - |
dc.subject | shape metrics | - |
dc.title | Shape tracking with occlusions via coarse-to-fine region-based sobolev descent | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TPAMI.2014.2360380 | - |
dc.identifier.scopus | eid_2-s2.0-84926435930 | - |
dc.identifier.volume | 37 | - |
dc.identifier.issue | 5 | - |
dc.identifier.spage | 1053 | - |
dc.identifier.epage | 1066 | - |
dc.identifier.isi | WOS:000352533000012 | - |