Joint movement similarities for robust 3D action recognition using skeletal data

Pazhoumand-Dar, Hossein; Lam, Chiou-Peng; Mašek, Martin

doi:10.1016/j.jvcir.2015.03.002

Cited by 54 publications

(31 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to maintain the computational efficiency, our method uses only 45 (15× 3) features per frame. The same can be said for other works [9,36,37]. Besides, we have proved experimentally that our method offers a great flexibility that would allow users to provide some feedback on wrong classifications or even to add a new action category at runtime.…”

Section: Discussionsupporting

confidence: 62%

“…In [35], Wang and Wu dealt with variations in execution rate by combining an SVM-based classification algorithm with DTW. Alternatively to DTW, the longest common subsequence (LCSS) is used in [36] to make their action classifier invariant to temporal variations. In [37], the authors find a representation of the body joint trajectories that is robust against execution rate variations among subjects.…”

Section: Har In Depth Videomentioning

confidence: 99%

See 1 more Smart Citation

Flexible human action recognition in depth video sequences using masked joint trajectories

Tejero-de-Pablos

Nakashima

Yokoya

et al. 2016

J Image Video Proc.

View full text Add to dashboard Cite

Human action recognition applications are greatly benefited from the use of commodity depth sensors that are capable of skeleton tracking. Some of these applications (e.g., customizable gesture interfaces) require learning of new actions at runtime and may not count with many training instances. This paper presents a human action recognition method designed for flexibility, which allows taking users' feedback to improve recognition performance and to add a new action instance without computationally expensive optimization for training classifiers. Our nearest neighbor-based action classifier adopts dynamic time warping to handle variability in execution rate. In addition, it uses the confidence values associated to each tracked joint position to mask erroneous trajectories for robustness against noise. We evaluate the proposed method with various datasets with different frame rates, actors, and noise. The experimental results demonstrate its adequacy for learning of actions from depth sequences at runtime. We achieve an accuracy comparable to the state-of-the-art techniques on the challenging MSR-Action3D dataset.

show abstract

Section: Discussionsupporting

confidence: 62%

Section: Har In Depth Videomentioning

confidence: 99%

Flexible human action recognition in depth video sequences using masked joint trajectories

Tejero-de-Pablos

Nakashima

Yokoya

et al. 2016

J Image Video Proc.

View full text Add to dashboard Cite

show abstract

“…Ofli et al and Pazhoumand et al have computed the variance [19] and the entropy [21] of each joint to discriminate the most informative features characterizing the motion and used these criteria to recognize actions. The problem of such approaches is that they loose information about the temporality of the motion.…”

Section: Related Workmentioning

confidence: 99%

Automatic evaluation of sports motion: A generic computation of spatial and temporal errors

Morel

Achard

Kulpa

et al. 2017

Image and Vision Computing

View full text Add to dashboard Cite

In this paper, we propose an innovative automatic evaluation process for any sport motions. Based on a 2-level Dynamic Time Warping, the process allows the evaluation of both spatial and temporal errors of a novice motion based on an experts' motion database and without any prior knowledge on the sport. This new methodology is evaluated with regards to coaches' assessment on two different kinds of motions: tennis serves and karate tsuki.

show abstract

“…The motions are thus supposed to be similar and our objective is to quantify the errors between them and not to try to ignore these small differences. For the second case, some authors have computed the variance (Ofli et al, 2012) or the entropy (Pazhoumand-Dar et al, 2015) of each joint to discriminate the most informative features characterizing the motion. The problem of such approaches is that they lost some of the temporal information of the motion.…”

Section: Related Workmentioning

confidence: 99%

Automatic and Generic Evaluation of Spatial and Temporal Errors in Sport Motions

Morel

Kulpa

Sorel

et al. 2016

Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

View full text Add to dashboard Cite

Abstract:Automatically evaluating and quantifying the performance of a player is a complex task since the important motion features to analyze depend on the type of performed action. But above all, this complexity is due to the variability of morphologies and styles of both the experts who perform the reference motions and the novices. Only based on a database of experts' motions and no additional knowledge, we propose an innovative 2-level DTW (Dynamic Time Warping) approach to temporally and spatially align the motions and extract the imperfections of the novice's performance for each joints. In this study, we applied our method on tennis serve but since it is automatic and morphology-independent, it can be applied to any individual motor performance.

show abstract

Joint movement similarities for robust 3D action recognition using skeletal data

Cited by 54 publications

References 45 publications

Flexible human action recognition in depth video sequences using masked joint trajectories

Flexible human action recognition in depth video sequences using masked joint trajectories

Automatic evaluation of sports motion: A generic computation of spatial and temporal errors

Automatic and Generic Evaluation of Spatial and Temporal Errors in Sport Motions

Contact Info

Product

Resources

About