Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/84207
Citations | ||
Scopus | Web of ScienceĀ® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Multi-target tracking by continuous energy minimization |
Author: | Milan, A. Schindler, K. |
Citation: | Proceedings of the 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 11) / pp.1265-1272 |
Publisher: | IEEE |
Publisher Place: | USA |
Issue Date: | 2011 |
ISBN: | 9781457703942 |
Conference Name: | IEEE Conference on Computer Vision and Pattern Recognition (24th : 2011 : Colorado Springs, CO, U.S.A.) |
Statement of Responsibility: | Anton Andriyenko, Konrad Schindler |
Abstract: | We propose to formulate multi-target tracking as minimization of a continuous energy function. Other than a number of recent approaches we focus on designing an energy function that represents the problem as faithfully as possible, rather than one that is amenable to elegant optimization. We then go on to construct a suitable optimization scheme to find strong local minima of the proposed energy. The scheme extends the conjugate gradient method with periodic trans-dimensional jumps. These moves allow the search to escape weak minima and explore a much larger portion of the variable-dimensional search space, while still always reducing the energy. To demonstrate the validity of this approach we present an extensive quantitative evaluation both on synthetic data and on six different real video sequences. In both cases we achieve a significant performance improvement over an extended Kalman filter baseline as well as an ILP-based state-of-the-art tracker. |
Rights: | Copyright status unknown |
DOI: | 10.1109/CVPR.2011.5995311 |
Published version: | http://dx.doi.org/10.1109/cvpr.2011.5995311 |
Appears in Collections: | Aurora harvest Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_84207.pdf Restricted Access | Restricted Access | 2.46 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.