Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - HOPC
T2 - Histogram of oriented principal components of 3D pointclouds for action recognition
AU - Rahmani, Hossein
AU - Mahmood, Arif
AU - Huynh, Du Q.
AU - Mian, Ajmal
PY - 2014
Y1 - 2014
N2 - Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint. In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations. Our technique consists of a novel descriptor and keypoint detection algorithm. The proposed descriptor is extracted at a point by encoding the Histogram of Oriented Principal Components (HOPC) within an adaptive spatio-temporal support volume around that point. Based on this descriptor, we present a novel method to detect Spatio-Temporal Key-Points (STKPs) in 3D pointcloud sequences. Experimental results show that the proposed descriptor and STKP detector outperform state-of-the-art algorithms on three benchmark human activity datasets. We also introduce a new multiview public dataset and show the robustness of our proposed method to viewpoint variations.
AB - Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint. In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations. Our technique consists of a novel descriptor and keypoint detection algorithm. The proposed descriptor is extracted at a point by encoding the Histogram of Oriented Principal Components (HOPC) within an adaptive spatio-temporal support volume around that point. Based on this descriptor, we present a novel method to detect Spatio-Temporal Key-Points (STKPs) in 3D pointcloud sequences. Experimental results show that the proposed descriptor and STKP detector outperform state-of-the-art algorithms on three benchmark human activity datasets. We also introduce a new multiview public dataset and show the robustness of our proposed method to viewpoint variations.
U2 - 10.1007/978-3-319-10605-2_48
DO - 10.1007/978-3-319-10605-2_48
M3 - Conference contribution/Paper
SN - 9783319106045
SP - 742
EP - 757
BT - Computer Vision – ECCV 2014.
A2 - Fleet, D.
A2 - Pajdla, T.
A2 - Schiele, B.
A2 - Tuytelaars, T.
PB - Springer
CY - Cham
ER -