Fast Adaptive Reparametrization (FAR) With Application to Human Action Recognition

In this letter, a fast approach for curve reparametrization, called Fast Adaptive Reparamterization (FAR), is introduced. Instead of computing an optimal matching between two curves such as Dynamic Time Warping (DTW) and elastic distance-based approaches, our method is applied to each curve independently, leading to linear computational complexity. It is based on a simple replacement of the curve parameter by a variable invariant under specific variations of reparametrization. The choice of this variable is heuristically made according to the application of interest. In addition to being fast, the proposed reparametrization can be applied not only to curves observed in Euclidean spaces but also to feature curves living in Riemannian spaces. To validate our approach, we apply it to the scenario of human action recognition using curves living in the Riemannian product Special Euclidean space $\mathbb {SE}(3)^n$. The obtained results on three benchmarks for human action recognition (MSRAction3D, Florence3D, and UTKinect) show that our approach competes with state-of-the-art methods in terms of accuracy and computational cost.

[1]  Anuj Srivastava,et al.  Statistical analysis of trajectories on Riemannian manifolds: Bird migration, hurricane tracking and video surveillance , 2014, 1405.0803.

[2]  B. Hall.  Lie Groups, Lie Algebras, and Representations: An Elementary Introduction , 2004 .

[3]  Charles C. Tappert,et al.  Cursive Script Recognition by Elastic Matching , 1982, IBM J. Res. Dev..

[4]  D. Kendall.  A Survey of the Statistical Theory of Shape , 1989 .

[5]  Jake K. Aggarwal,et al.  View invariant human action recognition using histograms of 3D joints , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[6]  Rama Chellappa,et al.  Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Rama Chellappa,et al.  Silhouette-based gesture and action recognition via modeling trajectories on Riemannian shape manifolds , 2011, Comput. Vis. Image Underst..

[8]  Girum G. Demisse,et al.  Deformation Based Curved Shape Representation , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Faouzi Ghorbel,et al.  Fourier-based geometric shape prior for snakes , 2008, Pattern Recognit. Lett..

[10]  Stéphane Lecoeuche,et al.  A fast and accurate motion descriptor for human action recognition applications , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[11]  P. Thomas Fletcher,et al.  Principal geodesic analysis for the study of nonlinear statistics of shape , 2004, IEEE Transactions on Medical Imaging.

[12]  Junwei Wang,et al.  Shape matching and classification using height functions , 2012, Pattern Recognit. Lett..

[13]  Djamila Aouada,et al.  Squigraphs for Fine and Compact Modeling of 3-D Shapes , 2010, IEEE Transactions on Image Processing.

[14]  Bjorn Ottersten,et al.  A View-invariant Framework for Fast Skeleton-based Action Recognition using a Single RGB Camera , 2019, VISIGRAPP.

[15]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Yoh'ichi Tohkura,et al.  A weighted cepstral distance measure for speech recognition , 1987, IEEE Trans. Acoust. Speech Signal Process..

[17]  Wanqing Li,et al.  Action recognition based on a bag of 3D points , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[18]  Richard M. Murray,et al.  A Mathematical Introduction to Robotic Manipulation , 1994 .

[19]  Vijay Kumar,et al.  Two methods for interpolating rigid body motions , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[20]  Abd El Rahman Shabayek,et al.  Home self-training: Visual feedback for assisting physical activity for stroke survivors , 2019, Comput. Methods Programs Biomed..

[21]  Stéphane Lecoeuche,et al.  Kinematic Spline Curves: A temporal invariant descriptor for fast action recognition , 2018, Image Vis. Comput..

[22]  Anuj Srivastava,et al.  Shape Analysis of Elastic Curves in Euclidean Spaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Rushil Anirudh,et al.  Elastic Functional Coding of Riemannian Trajectories , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Björn E. Ottersten,et al.  Localized Trajectories for 2D and 3D Action Recognition † , 2019, Sensors.

[25]  Stéphane Lecoeuche,et al.  An extension of kernel learning methods using a modified Log-Euclidean distance for fast and accurate skeleton-based Human Action Recognition , 2018, Comput. Vis. Image Underst..

[26]  Laurent Younes,et al.  Computable Elastic Distances Between Shapes , 1998, SIAM J. Appl. Math..

[27]  Björn E. Ottersten,et al.  Deformation-Based Abnormal Motion Detection using 3D Skeletons , 2018, 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA).

[28]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[29]  Nikos Paragios,et al.  Shape Priors for Level Set Representations , 2002, ECCV.

[30]  Alberto Del Bimbo,et al.  Recognizing Actions from Depth Cameras as Weakly Aligned Multi-part Bag-of-Poses , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[31]  Björn E. Ottersten,et al.  Similarity Metric for Curved Shapes in Euclidean Space , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).