3D Part-Based Sparse Tracker with Automatic Synchronization and Registration

Adel Bibi; Tianzhu Zhang; Bernard Ghanem

doi:10.1109/CVPR.2016.160

3D Part-Based Sparse Tracker with Automatic Synchronization and Registration

Adel Bibi, Tianzhu Zhang, Bernard Ghanem

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

63 Scopus citations

Abstract

In this paper, we present a part-based sparse tracker in a particle filter framework where both the motion and appearance model are formulated in 3D. The motion model is adaptive and directed according to a simple yet powerful occlusion handling paradigm, which is intrinsically fused in the motion model. Also, since 3D trackers are sensitive to synchronization and registration noise in the RGB and depth streams, we propose automated methods to solve these two issues. Extensive experiments are conducted on a popular RGBD tracking benchmark, which demonstrate that our tracker can achieve superior results, outperforming many other recent and state-of-the-art RGBD trackers.

Original language	English (US)
Title of host publication	2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISBN (Print)	9781467388511
DOIs	https://doi.org/10.1109/CVPR.2016.160
State	Published - Dec 13 2016

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: Research in this publication was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.

Access to Document

10.1109/CVPR.2016.160

Cite this

@inproceedings{6448f0601fe8410b8a5c97962cf96e90,

title = "3D Part-Based Sparse Tracker with Automatic Synchronization and Registration",

abstract = "In this paper, we present a part-based sparse tracker in a particle filter framework where both the motion and appearance model are formulated in 3D. The motion model is adaptive and directed according to a simple yet powerful occlusion handling paradigm, which is intrinsically fused in the motion model. Also, since 3D trackers are sensitive to synchronization and registration noise in the RGB and depth streams, we propose automated methods to solve these two issues. Extensive experiments are conducted on a popular RGBD tracking benchmark, which demonstrate that our tracker can achieve superior results, outperforming many other recent and state-of-the-art RGBD trackers.",

author = "Adel Bibi and Tianzhu Zhang and Bernard Ghanem",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: Research in this publication was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.",

year = "2016",

month = dec,

day = "13",

doi = "10.1109/CVPR.2016.160",

language = "English (US)",

isbn = "9781467388511",

booktitle = "2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

TY - GEN

T1 - 3D Part-Based Sparse Tracker with Automatic Synchronization and Registration

AU - Bibi, Adel

AU - Zhang, Tianzhu

AU - Ghanem, Bernard

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: Research in this publication was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.

PY - 2016/12/13

Y1 - 2016/12/13

N2 - In this paper, we present a part-based sparse tracker in a particle filter framework where both the motion and appearance model are formulated in 3D. The motion model is adaptive and directed according to a simple yet powerful occlusion handling paradigm, which is intrinsically fused in the motion model. Also, since 3D trackers are sensitive to synchronization and registration noise in the RGB and depth streams, we propose automated methods to solve these two issues. Extensive experiments are conducted on a popular RGBD tracking benchmark, which demonstrate that our tracker can achieve superior results, outperforming many other recent and state-of-the-art RGBD trackers.

AB - In this paper, we present a part-based sparse tracker in a particle filter framework where both the motion and appearance model are formulated in 3D. The motion model is adaptive and directed according to a simple yet powerful occlusion handling paradigm, which is intrinsically fused in the motion model. Also, since 3D trackers are sensitive to synchronization and registration noise in the RGB and depth streams, we propose automated methods to solve these two issues. Extensive experiments are conducted on a popular RGBD tracking benchmark, which demonstrate that our tracker can achieve superior results, outperforming many other recent and state-of-the-art RGBD trackers.

UR - http://hdl.handle.net/10754/622773

UR - http://ieeexplore.ieee.org/document/7780529/

U2 - 10.1109/CVPR.2016.160

DO - 10.1109/CVPR.2016.160

M3 - Conference contribution

SN - 9781467388511

BT - 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

3D Part-Based Sparse Tracker with Automatic Synchronization and Registration

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this