Please use this identifier to cite or link to this item:
|Title:||Online multi-target tracking using recurrent neural networks|
|Citation:||Proceedings of 31st AAAI Conference on Artificial Intelligence and the 29th Innovative Applications of Artificial Intelligence Conference, 2017 / pp.4225-4232|
|Publisher:||ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE|
|Conference Name:||31st AAAI Conference on Artificial Intelligence (AAAI 2017) (04 Feb 2017 - 09 Feb 2017 : San Francisco)|
|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|
|Appears in Collections:||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.