Continuous energy minimization for multitarget tracking

Files

RA_hdl_90016.pdf (2 MB)
  (Restricted Access)

Date

2014

Authors

Milan, A.
Roth, S.
Schindler, K.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Journal article

Citation

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014; 36(1):58-72

Statement of Responsibility

Anton Milan, Stefan Roth, and Konrad Schindler

Conference Name

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.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2014 IEEE

License

Grant ID

Call number

Persistent link to this record