Attractor-Shape for Dynamical Analysis of Human Movement: Applications in Stroke Rehabilitation and Action Recognition

Venkataraman, Vinay; Turaga, Pavan; Lehrer, Nicole; Baran, Michael; Rikakis, Thanassis; Wolf, Steven L.

doi:10.1109/cvprw.2013.82

Cited by 19 publications

(23 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For completeness, we compared our algorithm with the state-of-the-art methods [20,12,16] which were described in Section 1.…”

Section: Datasetmentioning

confidence: 99%

“…These instructions can be in the form of a video of an agent performing an action, a text describing the kinematic details of an action or an instructor/person in interaction. Instances of this problem in the literature are evaluation of karate performance [2], of dancer's performance [9], quality assessment of reach and grasp movements of stroke survivors [20], and the gaming/entertainment industry. In this work, we aim in particular to assess the quality of physical exercises for therapeutic purposes.…”

Section: Introductionmentioning

confidence: 99%

“…This method uses quaternionic correlation to estimate the time-shift between two dancing sequences. Finally, Venkataraman et al [20] also proposed a correlation-based approach to quantify the movements of stroke survivors. They differently model the movements of a human from a dynamical system perspective and reconstruct a phase space to infer geometrical and topological information from observations by means of attractor.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Graph-based analysis of physical exercise actions

Çeliktutan

Akgül

Wolf

et al. 2013

Proceedings of the 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Healthcare

View full text Add to dashboard Cite

In this paper, we develop a graph-based method to align two dynamic skeleton sequences, and apply it to both action recognition tasks as well as to the objective quantification of the goodness of the action performance. The automated measurement of "action quality" has potential to be used to monitor action imitations, for example, during a physical therapy. We seek matches between a query sequence and model sequences selected with graph mining. The best matches are obtained through minimizing an energy function that jointly measures space and time domain deformations. This measure has been used for recognizing actions, for separating acceptable and unacceptable action performances, or as a continuous quantification of the action performance goodness. Experimental evaluation demonstrates the improved results of our scheme vis-à-vis its nearest competitors. Furthermore, a plausible relationship has been obtained between action perturbation, given by the joint noise variances, and quality measure, given by matching energies averaged over a sequence.

show abstract

“…For completeness, we compared our algorithm with the state-of-the-art methods [20,12,16] which were described in Section 1.…”

Section: Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Graph-based analysis of physical exercise actions

Çeliktutan

Akgül

Wolf

et al. 2013

Proceedings of the 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Healthcare

View full text Add to dashboard Cite

show abstract

“…2). A recent study has shown that a single marker-based system (marker on the wrist) can achieve comparable performance levels of movement quality assessment to a heavy marker-based system [17]. …”

Section: Introductionmentioning

confidence: 99%

Component-Level Tuning of Kinematic Features From Composite Therapist Impressions of Movement Quality

Venkataraman

Turaga

Baran

et al. 2016

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a general framework for tuning component-level kinematic features using therapists’ overall impressions of movement quality, in the context of a Home-based Adaptive Mixed Reality Rehabilitation (HAMRR) system. We propose a linear combination of non-linear kinematic features to model wrist movement, and propose an approach to learn feature thresholds and weights using high-level labels of overall movement quality provided by a therapist. The kinematic features are chosen such that they correlate with the quality of wrist movements to clinical assessment scores. Further, the proposed features are designed to be reliably extracted from an inexpensive and portable motion capture system using a single reflective marker on the wrist. Using a dataset collected from ten stroke survivors, we demonstrate that the framework can be reliably used for movement quality assessment in HAMRR systems. The system is currently being deployed for large-scale evaluations, and will represent an increasingly important application area of motion capture and activity analysis.

show abstract

“…A diverse set of applications have benefited from dynamics based metrics such as -human action recognition [4,37], bio-mechanics [23], dynamics of crowds [3], and dynamic scene recognition [22]. It has also been shown that such properties can help in fine grained classification between similar kinds of human movement [30]. Exploiting the dynamics is relatively easy when the concerned feature space is Euclidean, but the last few years have seen an increased interest in modeling features that lie on non Euclidean spaces such as Riemannian manifolds.…”

Section: Introductionmentioning

confidence: 99%

A Generalized Lyapunov Feature for Dynamical Systems on Riemannian Manifolds

Venkataraman

Turaga

2015

Procedings of the Proceedings of the 1st International Workshop on DIFFerential Geometry in Computer Vision for Analysis of Sha

Self Cite

View full text Add to dashboard Cite

Dynamic phenomena such as human activities, dynamic scenes, and moving crowds are commonly observed through visual sensors, resulting in feature trajectories sampled in time. Such phenomena can be accurately modeled by taking the temporal variations and changes into account. For problems where the trajectories are sufficiently different, elastic metrics can provide distances that are invariant to speed, but for more complex problems such as fine grained activity classification, one needs to exploit higher order dynamical properties. For features in the Euclidean space, applications such as crowd monitoring, dynamic scene recognition and human movement quality analysis have found a lot of success this way. In this paper we propose the largest Riemannian Lyapunov exponent (L-RLE), which is the first generalization of the largest Lyapunov exponent to Riemannian manifolds. The largest Lyapunov exponent is a classic measure to quantify the amount of chaos within signals in the Euclidean space, and allows us to exploit higher order dynamics for various applications. We show the effectiveness of the L-RLE on two manifolds -the Grassmann and the SO(3) lie group. By modeling human actions as dynamic processes evolving on Riemannian manifolds, we show that L-RLE can measure the amount of chaos within each action accurately. We show that our measure is a good generalization of largest Euclidean Lyapunov exponent (L-ELE), and is less susceptible to arbitrary distortions.

show abstract

Attractor-Shape for Dynamical Analysis of Human Movement: Applications in Stroke Rehabilitation and Action Recognition

Cited by 19 publications

References 27 publications

Graph-based analysis of physical exercise actions

Graph-based analysis of physical exercise actions

Component-Level Tuning of Kinematic Features From Composite Therapist Impressions of Movement Quality

A Generalized Lyapunov Feature for Dynamical Systems on Riemannian Manifolds

Contact Info

Product

Resources

About