Human Motion Tracking with a Kinematic Parameterization of Extremal Contours

Abstract

This paper addresses the problem of human motion tracking from multiple image sequences. The human body is described by five articulated mechanical chains and human body-parts are described by volumetric primitives with curved surfaces. If such a surface is observed with a camera, an extremal contour appears in the image whenever the surface turns smoothly away from the viewer. We describe a method that recovers human motion through a kinematic parameterization of these extremal contours. The method exploits the fact that the observed image motion of these contours is a function of both the rigid displacement of the surface and of the relative position and orientation between the viewer and the curved surface. First, we describe a parameterization of an extremal-contour point velocity for the case of developable surfaces. Second, we use the zeroreference kinematic representation and we derive an explicit formula that links extremal contour velocities to the angular velocities associated with the kinematic model. Third, we show how the chamfer-distance may be used to measure the discrepancy between predicted extremal contours and observed image contours; moreover we show how the chamfer distance can be used as a differentiable multi-valued function and how the tracker based on this distance can be cast into a continuous non-linear optimization framework. Fourth, we describe implementation issues associated with a practical human-body tracker that may use an arbitrary number of cameras. One great methodological and practical advantage of our method is that it relies neither on model-toimage, nor on image-to-image point matches. In practice we D. Knossow · R. Ronfard · R. Horaud ( ) INRIA Rhône-Alpes, 655, avenue de l'Europe, 38330 Montbonnot Saint-Martin, France e-mail: radu.horaud@inrialpes.fr model people with 5 kinematic chains, 19 volumetric primitives, and 54 degrees of freedom; We observe silhouettes in images gathered with several synchronized and calibrated cameras. The tracker has been successfully applied to several complex motions gathered at 30 frames/second.

Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief Propagation

“…These approaches typically rely on a kinematic tree (Marr and Nishihara 1978;Nevatia and Binford 1973) representation of the body in 2D (Ju et al 1996), 2.5D (Cham and Rehg 1999;Wang and Rehg 2006), or 3D (Bregler and Malik 1998;Cheung et al 2003;Choo and Fleet 2001;Corazza et al 2006;Deutscher and Reid 2005;Gall et al 2007Gall et al , 2010Gavrila and Davis 1996;Hogg 1983;Horaud et al 2008;John et al 2009;Kakadiaris and Metaxas 1996;Kehl et al 2005;Knossow et al 2008;Rosenhahn et al 2008;Sidenbladh et al 2000;Sminchisescu and Triggs 2003;Wachter and Nagel 1999). While generative models employed for human pose and motion estimation are typically very weak (i.e.…”

Three Dimensional Monocular Human Motion Analysis in End-Effector Space

“…Specifically, we will validate our method on the ground truth data set of Knossow et.al. [21] and compare with their method, which should allow us to quantitatively evaluate the accuracy of our approach.…”

Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes

“…Comparatively, while a representative trajectory may be equivalent to the corresponding region of a human head, hand, or foot for instance, it may also possibly correspond to an area that involves a whole person, or multiple people, where the constitutive particles experience close-grained motion. Hence, a representative trajectory in crowds is inherently different from the traditionally tracked trajectory of an object in sparse scenes, where normally a body part or a person as a whole [16,17] are tracked.…”