Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Observe-and-Explain: A New Approach for Multiple Hypotheses Tracking of Humans and Objects

Summary: Observe-and-Explain: A New Approach for Multiple Hypotheses Tracking of
Humans and Objects
M. S. Ryoo and J. K. Aggarwal
Computer & Vision Research Center / Department of ECE
The University of Texas at Austin
{mryoo, aggarwaljk}@mail.utexas.edu
This paper presents a novel approach for tracking hu-
mans and objects under severe occlusion. We intro-
duce a new paradigm for multiple hypotheses tracking,
observe-and-explain, as opposed to the previous paradigm
of hypothesize-and-test. Our approach efficiently enumer-
ates multiple possibilities of tracking by generating several
likely `explanations' after concatenating a sufficient amount
of observations. The computational advantages of our ap-
proach over the previous paradigm under severe occlusions
are presented. The tracking system is implemented and
tested using the i-Lids dataset, which consists of videos of
humans and objects moving in a London subway station.
The experimental results show that our new approach is


Source: Aggarwal, J. K. - Department of Electrical and Computer Engineering, University of Texas at Austin


Collections: Computer Technologies and Information Sciences; Engineering