Projects per year
Abstract
This letter presents SkeletonNet, a deep learning framework for skeleton-based 3-D action recognition. Given a skeleton sequence, the spatial structure of the skeleton joints in each frame and the temporal information between multiple frames are two important factors for action recognition. We first extract body-part-based features from each frame of the skeleton sequence. Compared to the original coordinates of the skeleton joints, the proposed features are translation, rotation, and scale invariant. To learn robust temporal information, instead of treating the features of all frames as a time series, we transform the features into images and feed them to the proposed deep learning network, which contains two parts: one to extract general features from the input images, while the other to generate a discriminative and compact representation for action recognition. The proposed method is tested on the SBU kinect interaction dataset, the CMU dataset, and the large-scale NTU RGB+D dataset and achieves state-of-the-art performance.
Original language | English |
---|---|
Article number | 7891014 |
Pages (from-to) | 731-735 |
Number of pages | 5 |
Journal | IEEE Signal Processing Letters |
Volume | 24 |
Issue number | 6 |
DOIs | |
Publication status | Published - Jun 2017 |
Fingerprint
Dive into the research topics of 'SkeletonNet: Mining Deep Part Features for 3-D Action Recognition'. Together they form a unique fingerprint.-
Advanced Computer Vision Techniques for Marine Ecology
Bennamoun, M. (Investigator 01), Boussaid, F. (Investigator 02), Kendrick, G. (Investigator 03) & Fisher, R. (Investigator 04)
ARC Australian Research Council
1/01/15 → 31/12/21
Project: Research
-
Advanced 3D Computer Vision Algorithms for 'Find and Grasp' Future Robots
Bennamoun, M. (Investigator 01)
ARC Australian Research Council
1/01/15 → 31/12/20
Project: Research
-
Revocable 2D/3D Shape Based Multimodal Hand Biometrics for Personal Identification & Verification
Sohel, F. (Investigator 01)
ARC Australian Research Council
1/01/12 → 29/06/17
Project: Research