Physically Plausible 3D Scene Tracking: The Single Actor Hypothesis

Abstract

In several hand-object(s)

DART: Dense Articulated Real-Time Tracking

“…While many of these existing techniques achieve excellent results in their application domain, such as hand/object tracking [24,19,26], human pose tracking [29,31,11,12,35], or deformable object tracking [28], none of them have been demonstrated to work in several domains. In contrast, our DART framework relies on a highly efficient representation and optimization to operate under very general conditions, thereby enabling it to track a wide variety of objects.…”

“…For example, many articulated model tracking approaches in this category utilize some form of silhouette information, necessitating the use of indicator functions which are discontinuous and therefore not globally differentiable. Such methods thus often rely on inference techniques which are less thoroughly studied and perhaps less theoretically justified, such as particle swarm optimization (PSO) as employed by Oikonomidis et al [24], Kyriazis and Argyros [19].…”

“…Recently introduced depth cameras along with highly parallel algorithms optimized for modern GPUs have enabled new algorithms for tracking complex 3D objects in real time. Examples include KinectFusion and related efforts for 3D mapping [23,16,34], human body pose tracking [29,35,15], articulated hand tracking [24,19,26]. These approaches were developed for specific application domains and have not been demonstrated or tested on multiple tracking applications.…”

Real-Time Tracking of Single and Multiple Objects from Depth-Colour Imagery Using 3D Signed Distance Functions

“…Oikonomidis (2012) tracks two interacting hands with Kinect input, introducing a penalty term measuring the inter-penetration of fingers to invalidate impossible articulated poses. Both Oikonomidis et al (2011b) and Kyriazis and Argyros (2013) track a hand and moving object simultaneously, and invalid configurations similarly penalized. In both cases the measure used is the minimum magnitude of 3D translation required to eliminate intersection of the two objects, a measure computed using the Open Dynamic Engine library (Smith 2006).…”

“…In each the objective function involves rendering the model at some hypothesised pose into the observation domain and evaluating the differences between the generated and the observed visual cues; but in each the cost is deemed too non-convex, or its partial derivatives too expensive or awkward to compute, for gradientbased methods to succeed. Particle Swarm Optimization was used by Oikonomidis et al (2011a) to track an articulated hand, and by Kyriazis and Argyros (2013) to follow the interaction between a hand and an object. Both achieve real-time performance by exploiting the power of GPUs, but the level of accuracy that can be achieved by PSO is not thoroughly understood either empirically or theoretically.…”