Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Continuous energy minimization for multitarget tracking
Author: Milan, A.
Roth, S.
Schindler, K.
Citation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014; 36(1):58-72
Publisher: Institute of Electrical and Electronics Engineers
Issue Date: 2014
ISSN: 0162-8828
Statement of
Anton Milan, Stefan Roth, and Konrad Schindler
Abstract: Many recent advances in multiple target tracking aim at finding a (nearly) optimal set of trajectories within a temporal window. To handle the large space of possible trajectory hypotheses, it is typically reduced to a finite set by some form of data-driven or regular discretization. In this work, we propose an alternative formulation of multitarget tracking as minimization of a continuous energy. Contrary to recent approaches, we focus on designing an energy that corresponds to a more complete representation of the problem, rather than one that is amenable to global optimization. Besides the image evidence, the energy function takes into account physical constraints, such as target dynamics, mutual exclusion, and track persistence. In addition, partial image evidence is handled with explicit occlusion reasoning, and different targets are disambiguated with an appearance model. To nevertheless find strong local minima of the proposed nonconvex energy, we construct a suitable optimization scheme that alternates between continuous conjugate gradient descent and discrete transdimensional jump moves. These moves, which are executed such that they always reduce the energy, allow the search to escape weak minima and explore a much larger portion of the search space of varying dimensionality. We demonstrate the validity of our approach with an extensive quantitative evaluation on several public data sets.
Keywords: Multiobject tracking; tracking-by-detection; visual surveillance; continuous optimization
Rights: © 2014 IEEE
DOI: 10.1109/TPAMI.2013.103
Appears in Collections:Aurora harvest 7
Computer Science publications

Files in This Item:
File Description SizeFormat 
  Restricted Access
Restricted Access2.05 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.