Comparison of rigid body motion trajectory descriptors for motion representation and recognition

This paper presents an overview and comparison of minimal and complete rigid body motion trajectory descriptors, usable in applications like motion recognition and programming by demonstration. Motion trajectory descriptors are able to deal with potentially unwanted variations acting on the motion trajectory such as changes in the execution time, the motion's starting position, or the viewpoint from which the motion is observed. A suitable rigid body motion trajectory descriptor retains only the trajectory information relevant to the application. This paper compares different trajectory descriptors for rigid body motion and validates their usefulness for dealing with motion variation in a motion recognition experiment. Furthermore, a new type of invariant trajectory descriptor is introduced based on the Frenet-Serret formulas.

[1]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[2]  Mubarak Shah,et al.  View-Invariant Representation and Recognition of Actions , 2002, International Journal of Computer Vision.

[3]  Aude Billard,et al.  On Learning, Representing, and Generalizing a Task in a Humanoid Robot , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Dan Schonfeld,et al.  View-invariant motion trajectory-based activity classification and recognition , 2006, Multimedia Systems.

[5]  Jun Sato,et al.  Space-time invariants for recognizing 3D motions from arbitrary viewpoints under perspective projection , 2004, Third International Conference on Image and Graphics (ICIG'04).

[6]  Shandong Wu,et al.  Motion trajectory reproduction from generalized signature description , 2010, Pattern Recognit..

[7]  Isaac Weiss,et al.  Geometric invariants and object recognition , 1993, International Journal of Computer 11263on.

[8]  Joris De Schutter,et al.  Invariant Description of Rigid Body Motion Trajectories , 2010 .

[9]  R. Paul.  Robot manipulators : mathematics, programming, and control : the computer control of robot manipulators , 1981 .

[10]  Shandong Wu,et al.  Flexible signature descriptions for adaptive motion trajectory representation, perception and recognition , 2009, Pattern Recognit..

[11]  A. Paulo Moreira,et al.  Stereo-based real-time 6-DoF work tool tracking for robot programing by demonstration , 2016 .

[12]  Youfu Li,et al.  Mixed Signature: An Invariant Descriptor for 3D Motion Trajectory Perception and Recognition , 2012 .

[13]  Matteo Saveriano,et al.  Invariant representation for user independent motion recognition , 2013, 2013 IEEE RO-MAN.

[14]  W. Kühnel.  Differential Geometry: Curves - Surfaces - Manifolds , 2002 .

[15]  Guillaume Doisy,et al.  Position-invariant, real-time gesture recognition based on dynamic time warping , 2013, 2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[16]  Joris De Schutter,et al.  Invariant representations to reduce the variability in recognition of rigid body motion trajectories , 2012, 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC).