Home > Research > Publications & Outputs > Real Time Action Recognition Using Histograms o...

Research

Links

Text available via DOI:

View graph of relations

Real Time Action Recognition Using Histograms of Depth Gradients and Random Decision Forests

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Real Time Action Recognition Using Histograms of Depth Gradients and Random Decision Forests. / Rahmani, Hossein; Mahmood, Arif; Huynh, Du Q. et al.
IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2014. p. 626-633.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Rahmani, H, Mahmood, A, Huynh, DQ & Mian, A 2014, Real Time Action Recognition Using Histograms of Depth Gradients and Random Decision Forests. in IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, pp. 626-633. https://doi.org/10.1109/WACV.2014.6836044

APA

Rahmani, H., Mahmood, A., Huynh, D. Q., & Mian, A. (2014). Real Time Action Recognition Using Histograms of Depth Gradients and Random Decision Forests. In IEEE Winter Conference on Applications of Computer Vision (WACV) (pp. 626-633). IEEE. https://doi.org/10.1109/WACV.2014.6836044

Vancouver

Rahmani H, Mahmood A, Huynh DQ, Mian A. Real Time Action Recognition Using Histograms of Depth Gradients and Random Decision Forests. In IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE. 2014. p. 626-633 doi: 10.1109/WACV.2014.6836044

Author

Rahmani, Hossein ; Mahmood, Arif ; Huynh, Du Q. et al. / Real Time Action Recognition Using Histograms of Depth Gradients and Random Decision Forests. IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2014. pp. 626-633

Bibtex

@inproceedings{4abc55f4e6174127b93aff1a4ad706e8,
title = "Real Time Action Recognition Using Histograms of Depth Gradients and Random Decision Forests",
abstract = "We propose an algorithm which combines the discriminative information from depth images as well as from 3D joint positions to achieve high action recognition accuracy. To avoid the suppression of subtle discriminative information and also to handle local occlusions, we compute a vector of many independent local features. Each feature encodes spatiotemporal variations of depth and depth gradients at a specific space-time location in the action volume. Moreover, we encode the dominant skeleton movements by computing a local 3D joint position difference histogram. For each joint, we compute a 3D space-time motion volume which we use as an importance indicator and incorporate in the feature vector for improved action discrimination. To retain only the discriminant features, we train a random decision forest (RDF). The proposed algorithm is evaluated on three standard datasets and compared with nine state-of-the-art algorithms. Experimental results show that, on the average, the proposed algorithm outperform all other algorithms in accuracy and have a processing speed of over 112 frames/second.",
author = "Hossein Rahmani and Arif Mahmood and Huynh, {Du Q.} and Ajmal Mian",
year = "2014",
doi = "10.1109/WACV.2014.6836044",
language = "English",
pages = "626--633",
booktitle = "IEEE Winter Conference on Applications of Computer Vision (WACV)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Real Time Action Recognition Using Histograms of Depth Gradients and Random Decision Forests

AU - Rahmani, Hossein

AU - Mahmood, Arif

AU - Huynh, Du Q.

AU - Mian, Ajmal

PY - 2014

Y1 - 2014

N2 - We propose an algorithm which combines the discriminative information from depth images as well as from 3D joint positions to achieve high action recognition accuracy. To avoid the suppression of subtle discriminative information and also to handle local occlusions, we compute a vector of many independent local features. Each feature encodes spatiotemporal variations of depth and depth gradients at a specific space-time location in the action volume. Moreover, we encode the dominant skeleton movements by computing a local 3D joint position difference histogram. For each joint, we compute a 3D space-time motion volume which we use as an importance indicator and incorporate in the feature vector for improved action discrimination. To retain only the discriminant features, we train a random decision forest (RDF). The proposed algorithm is evaluated on three standard datasets and compared with nine state-of-the-art algorithms. Experimental results show that, on the average, the proposed algorithm outperform all other algorithms in accuracy and have a processing speed of over 112 frames/second.

AB - We propose an algorithm which combines the discriminative information from depth images as well as from 3D joint positions to achieve high action recognition accuracy. To avoid the suppression of subtle discriminative information and also to handle local occlusions, we compute a vector of many independent local features. Each feature encodes spatiotemporal variations of depth and depth gradients at a specific space-time location in the action volume. Moreover, we encode the dominant skeleton movements by computing a local 3D joint position difference histogram. For each joint, we compute a 3D space-time motion volume which we use as an importance indicator and incorporate in the feature vector for improved action discrimination. To retain only the discriminant features, we train a random decision forest (RDF). The proposed algorithm is evaluated on three standard datasets and compared with nine state-of-the-art algorithms. Experimental results show that, on the average, the proposed algorithm outperform all other algorithms in accuracy and have a processing speed of over 112 frames/second.

U2 - 10.1109/WACV.2014.6836044

DO - 10.1109/WACV.2014.6836044

M3 - Conference contribution/Paper

SP - 626

EP - 633

BT - IEEE Winter Conference on Applications of Computer Vision (WACV)

PB - IEEE

ER -