Tracking multiple humans in crowded environment

Published 13 November 2004

Tao Zhao, R. Nevatia

DOI10.1109/cvpr.2004.1315192

Citations338

TL;DR

A method that can track humans in crowded environments, with significant and persistent occlusion by making use of human shape models in addition to camera models, the assumption that humans walk on a plane and acquired appearance models is presented.

Abstract

Tracking of humans in dynamic scenes has been an important topic of research. Most techniques, however, are limited to situations where humans appear isolated and occlusion is small. Typical methods rely on appearance models that must be acquired when the humans enter the scene and are not occluded. We present a method that can track humans in crowded environments, with significant and persistent occlusion by making use of human shape models in addition to camera models, the assumption that humans walk on a plane and acquired appearance models. Experimental results and a quantitative evaluation are included.

Keywords

Computer ScienceEngineering

IEEE Transactions on Pattern Analysis and Machine IntelligenceKernel-based object tracking

4,565 Citations2003Dorin Comaniciu, Visvanathan Ramesh +1 more

A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed, which employs a metric derived from the Bhattacharyya coefficient as similarity measure, and uses the mean shift procedure to perform the optimization.

IEEE Transactions on Pattern Analysis and Machine IntelligencePfinder: real-time tracking of the human body

4,147 Citations1997Christopher R. Wren, A. Azarbayejani +2 more

IEEE Transactions on Pattern Analysis and Machine IntelligenceW/sup 4/: real-time surveillance of people and their activities

2,514 Citations2000I. Haritaoglu, David Harwood +1 more

W/sup 4/ employs a combination of shape analysis and tracking to locate people and their parts and to create models of people's appearance so that they can be tracked through interactions such as occlusions.

Mean-shift blob tracking through scale space

798 Citations2003Robert T. Collins

Lindeberg's theory of feature scale selection based on local maxima of differential scale-space filters to the problem of selecting kernel scale for mean-shift blob tracking shows that a difference of Gaussian (DOG) mean- shift kernel enables efficient tracking of blobs through scale space.

BraMBLe: a Bayesian multiple-blob tracker

630 Citations2002Michael Isard, John MacCormick

A multi-blob likelihood function which assigns directly comparable likelihoods to hypotheses containing different numbers of objects and a Bayesian filter for tracking multiple objects when the number of objects present is unknown and varies over time are introduced.

Bayesian human segmentation in crowded situations

298 Citations2003Tao Zhao, R. Nevatia

This work poses the problem of segmenting individual humans in crowded situations from stationary video camera sequences as a "model-based segmentation" problem in which human shape models are used to interpret the foreground in a Bayesian framework using an efficient Markov chain Monte Carlo method.

Kinematic jump processes for monocular 3D human tracking

270 Citations2003Cristian Sminchisescu, Bill Triggs

This work uses simple kinematic reasoning to enumerate the tree of possible forwards/backwards flips, thus greatly speeding the search within each linked group of minima in the model-image matching cost function.

View PDF

Probabilistic framework for segmenting people under occlusion

172 Citations2002Ahmed Elgammal, L.S. Davis

This paper presents a general framework that uses maximum likelihood estimation to estimate the best arrangement for people in terms of 2D translation that yields a segmentation for the foreground region and conducts occlusion reasoning to recover relative depth information.

Segmentation and tracking of multiple humans in complex situations

107 Citations2005Tao Zhao, R. Nevatia +1 more

This work proposes a new method to recognize walking using a motion template and temporal integration, and shows that this approach works robustly in very challenging sequences.

Lecture notes in computer scienceA Sampling Algorithm for Tracking Multiple Objects

105 Citations2000Tao Hai, Harpreet Sawhney +1 more

A novel formulation and an associated CONDENSATION-like sampling algorithm that explicitly support counting, addition and deletion of objects are proposed and promising comparative results on both synthetic and real data are demonstrated.