Home > Research > Publications & Outputs > Histogram of oriented principal components for ...

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Histogram of oriented principal components for cross-view action recognition

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Histogram of oriented principal components for cross-view action recognition. / Rahmani, Hossein; Mahmood, Arif; Huynh, Du et al.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 38, No. 12, 01.12.2016, p. 2430-2443.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Rahmani, H, Mahmood, A, Huynh, D & Mian, A 2016, 'Histogram of oriented principal components for cross-view action recognition', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 12, pp. 2430-2443. https://doi.org/10.1109/TPAMI.2016.2533389

APA

Rahmani, H., Mahmood, A., Huynh, D., & Mian, A. (2016). Histogram of oriented principal components for cross-view action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(12), 2430-2443. https://doi.org/10.1109/TPAMI.2016.2533389

Vancouver

Rahmani H, Mahmood A, Huynh D, Mian A. Histogram of oriented principal components for cross-view action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016 Dec 1;38(12):2430-2443. Epub 2016 Feb 25. doi: 10.1109/TPAMI.2016.2533389

Author

Rahmani, Hossein ; Mahmood, Arif ; Huynh, Du et al. / Histogram of oriented principal components for cross-view action recognition. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016 ; Vol. 38, No. 12. pp. 2430-2443.

Bibtex

@article{20fd5b3dbea145408b8c9ac6760349a2,
title = "Histogram of oriented principal components for cross-view action recognition",
abstract = "Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which are viewpoint dependent. In contrast, we directly process pointclouds for cross-view action recognition from unknown and unseen views. We propose the Histogram of Oriented Principal Components (HOPC) descriptor that is robust to noise, viewpoint, scale and action speed variations. At a 3D point, HOPC is computed by projecting the three scaled eigenvectors of the pointcloud within its local spatio-temporal support volume onto the vertices of a regular dodecahedron. HOPC is also used for the detection of Spatio-Temporal Keypoints (STK) in 3D pointcloud sequences so that view-invariant STK descriptors (or Local HOPC descriptors) at these key locations only are used for action recognition. We also propose a global descriptor computed from the normalized spatio-temporal distribution of STKs in 4-D, which we refer to as STK-D. We have evaluated the performance of our proposed descriptors against nine existing techniques on two cross-view and three single-view human action recognition datasets. The Experimental results show that our techniques provide significant improvement over state-of-the-art methods.",
keywords = "Spatio-temporal keypoint, pointcloud, view invariance",
author = "Hossein Rahmani and Arif Mahmood and Du Huynh and Ajmal Mian",
year = "2016",
month = dec,
day = "1",
doi = "10.1109/TPAMI.2016.2533389",
language = "English",
volume = "38",
pages = "2430--2443",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "12",

}

RIS

TY - JOUR

T1 - Histogram of oriented principal components for cross-view action recognition

AU - Rahmani, Hossein

AU - Mahmood, Arif

AU - Huynh, Du

AU - Mian, Ajmal

PY - 2016/12/1

Y1 - 2016/12/1

N2 - Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which are viewpoint dependent. In contrast, we directly process pointclouds for cross-view action recognition from unknown and unseen views. We propose the Histogram of Oriented Principal Components (HOPC) descriptor that is robust to noise, viewpoint, scale and action speed variations. At a 3D point, HOPC is computed by projecting the three scaled eigenvectors of the pointcloud within its local spatio-temporal support volume onto the vertices of a regular dodecahedron. HOPC is also used for the detection of Spatio-Temporal Keypoints (STK) in 3D pointcloud sequences so that view-invariant STK descriptors (or Local HOPC descriptors) at these key locations only are used for action recognition. We also propose a global descriptor computed from the normalized spatio-temporal distribution of STKs in 4-D, which we refer to as STK-D. We have evaluated the performance of our proposed descriptors against nine existing techniques on two cross-view and three single-view human action recognition datasets. The Experimental results show that our techniques provide significant improvement over state-of-the-art methods.

AB - Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which are viewpoint dependent. In contrast, we directly process pointclouds for cross-view action recognition from unknown and unseen views. We propose the Histogram of Oriented Principal Components (HOPC) descriptor that is robust to noise, viewpoint, scale and action speed variations. At a 3D point, HOPC is computed by projecting the three scaled eigenvectors of the pointcloud within its local spatio-temporal support volume onto the vertices of a regular dodecahedron. HOPC is also used for the detection of Spatio-Temporal Keypoints (STK) in 3D pointcloud sequences so that view-invariant STK descriptors (or Local HOPC descriptors) at these key locations only are used for action recognition. We also propose a global descriptor computed from the normalized spatio-temporal distribution of STKs in 4-D, which we refer to as STK-D. We have evaluated the performance of our proposed descriptors against nine existing techniques on two cross-view and three single-view human action recognition datasets. The Experimental results show that our techniques provide significant improvement over state-of-the-art methods.

KW - Spatio-temporal keypoint

KW - pointcloud

KW - view invariance

U2 - 10.1109/TPAMI.2016.2533389

DO - 10.1109/TPAMI.2016.2533389

M3 - Journal article

VL - 38

SP - 2430

EP - 2443

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 12

ER -