Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 38, Issue 1, Pages 1-13Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2015.2439257
Keywords
Action recognition; Riemannian geometry; manifold trajectories; depth sensors; skeletal data
Funding
- Institut Mines-Telecom
- MAGNUM project (BPI)
- NSF [DMS 1208959, 1217515]
- Fulbright scholar grant
- MAGNUM project (Region Nord-Pas de Calais)
- Direct For Computer & Info Scie & Enginr [1217515] Funding Source: National Science Foundation
- Division of Computing and Communication Foundations [1320267, 1319658] Funding Source: National Science Foundation
Ask authors/readers for more resources
We study the problem of classifying actions of human subjects using depth movies generated by Kinect or other depth sensors. Representing human body as dynamical skeletons, we study the evolution of their (skeletons') shapes as trajectories on Kendall's shape manifold. The action data is typically corrupted by large variability in execution rates within and across subjects and, thus, causing major problems in statistical analyses. To address that issue, we adopt a recently-developed framework of Su et al. [1], [2] to this problem domain. Here, the variable execution rates correspond to re-parameterizations of trajectories, and one uses a parameterization-invariant metric for aligning, comparing, averaging, and modeling trajectories. This is based on a combination of transported square-root vector fields (TSRVFs) of trajectories and the standard Euclidean norm, that allows computational efficiency. We develop a comprehensive suite of computational tools for this application domain: smoothing and denoising skeleton trajectories using median filtering, up-and down-sampling actions in time domain, simultaneous temporal-registration of multiple actions, and extracting invertible Euclidean representations of actions. Due to invertibility these Euclidean representations allow both discriminative and generative models for statistical analysis. For instance, they can be used in a SVM-based classification of original actions, as demonstrated here using MSR Action-3D, MSR Daily Activity and 3D Action Pairs datasets. Using only the skeletal information, we achieve state-of-the-art classification results on these datasets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available