Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/116855
Type: Conference paper
Title: Online multi-target tracking using recurrent neural networks
Author: Milan, A.
Rezatofighi, H.
Dick, A.
Reid, I.
Schindler, K.
Citation: Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence, 2017, pp.4225-4232
Publisher: ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE
Issue Date: 2017
Series/Report no.: AAAI Conference on Artificial Intelligence
ISSN: 2159-5399
2374-3468
Conference Name: 31st AAAI Conference on Artificial Intelligence (AAAI 2017) (4 Feb 2017 - 9 Feb 2017 : San Francisco)
Statement of
Responsibility: 
Anton Milan, S. Hamid Rezatofighi, Anthony Dick, Ian Reid, Konrad Schindler
Abstract: We present a novel approach to online multi-target tracking based on recurrent neural networks (RNNs). Tracking multiple objects in real-world scenes involves many challenges, including a) an a-priori unknown and time-varying number of targets, b) a continuous state estimation of all present targets, and c) a discrete combinatorial problem of data association. Most previous methods involve complex models that require tedious tuning of parameters. Here, we propose for the first time, an end-to-end learning approach for online multi-target tracking. Existing deep learning methods are not designed for the above challenges and cannot be trivially applied to the task. Our solution addresses all of the above points in a principled way. Experiments on both synthetic and real data show promising results obtained at ~300 Hz on a standard CPU, and pave the way towards future research in this direction.
Rights: Copyright © 2017, Association for the Advancement of Artificial Intelligence
Grant ID: http://purl.org/au-research/grants/arc/LP130100154
http://purl.org/au-research/grants/arc/FL130100102
http://purl.org/au-research/grants/arc/CE140100016
Published version: https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14184
Appears in Collections:Aurora harvest 3
Australian Institute for Machine Learning publications
Computer Science publications

Files in This Item:
There are no files associated with this item.


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