This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
In a known environment, objects may be tracked in multiple views using a set of background models. Stereo-based models can be illumination-invariant, but often have undefined valu...
Trevor Darrell, David Demirdjian, Neal Checka, Ped...
I am a doctoral student under supervision of Dr. Vincent Lepetit (co-advisor) and Prof. Pascal Fua. My research interests include object tracking-by-detection, camera egomotion est...
Dr. Fatih Porikli is a senior principal research scientist and project manager at Mitsubishi Electric Research Labs (MERL), Cambridge, USA. He received his PhD specializing in vide...
In this paper, we address the problem of learning an
adaptive appearance model for object tracking. In particular,
a class of tracking techniques called “tracking by detectionâ...