DAL – A Deep Depth-aware Long-term Tracker
release_4lnrun5kirfy3ga4wo4m7cykqa
by
Yanlin Qian and Alan Lukežič and Matej Kristan and
Joni-Kristian Kämäräinen and Jiri Matas
2019
Abstract
The best RGBD trackers provide high accuracy but are slow to run. On the
other hand, the best RGB trackers are fast but clearly inferior on the RGBD
datasets. In this work, we propose a deep depth-aware long-term tracker that
achieves state-of-the-art RGBD tracking performance and is fast to run. We
reformulate deep discriminative correlation filter (DCF) to embed the depth
information into deep features. Moreover, the same depth-aware correlation
filter is used for target re-detection. Comprehensive evaluations show that the
proposed tracker achieves state-of-the-art performance on the Princeton RGBD,
STC, and the newly-released CDTB benchmarks and runs 20 fps.
In text/plain
format
Archived Files and Locations
application/pdf 7.3 MB
file_6bcd523kxvhy7aqfqbguf36gfy
|
arxiv.org (repository) web.archive.org (webarchive) |
1912.00660v1
access all versions, variants, and formats of this works (eg, pre-prints)