Search: id:"swepub:oai:DiVA.org:liu-153489" >
Synthetic Data Gene...
-
Zhang, LichaoUniv Autonoma Barcelona, Spain
(author)
Synthetic Data Generation for End-to-End Thermal Infrared Tracking
- Article/chapterEnglish2019
Publisher, publication year, extent ...
-
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC,2019
-
printrdacarrier
Numbers
-
LIBRIS-ID:oai:DiVA.org:liu-153489
-
https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-153489URI
-
https://doi.org/10.1109/TIP.2018.2879249DOI
Supplementary language notes
-
Language:English
-
Summary in:English
Part of subdatabase
Classification
-
Subject category:ref swepub-contenttype
-
Subject category:art swepub-publicationtype
Notes
-
Funding Agencies|CIIISTERA Project M2CR of the Spanish Ministry [PCIN-2015-251, TIN2016-79717-R]; ACCIO Agency; CERCA Programme/Generalitat de Catalunya; CENIIT [18.14]; VR Starting Grant [2016-05543]
-
The usage of both off-the-shelf and end-to-end trained deep networks have significantly improved the performance of visual tracking on RGB videos. However, the lack of large labeled datasets hampers the usage of convolutional neural networks for tracking in thermal infrared (TIR) images. Therefore, most state-of-the-art methods on tracking for TIR data are still based on handcrafted features. To address this problem, we propose to use image-to-image translation models. These models allow us to translate the abundantly available labeled RGB data to synthetic TIR data. We explore both the usage of paired and unpaired image translation models for this purpose. These methods provide us with a large labeled dataset of synthetic TIR sequences, on which we can train end-to-end optimal features for tracking. To the best of our knowledge, we are the first to train end-to-end features for TIR tracking. We perform extensive experiments on the VOT-TIR2017 dataset. We show that a network trained on a large dataset of synthetic TIR data obtains better performance than one trained on the available real TIR data. Combining both data sources leads to further improvement. In addition, when we combine the network with motion features, we outperform the state of the art with a relative gain of over 10%, clearly showing the efficiency of using synthetic data to train end-to-end TIR trackers.
Subject headings and genre
Added entries (persons, corporate bodies, meetings, titles ...)
-
Gonzalez-Garcia, AbelUniv Autonoma Barcelona, Spain
(author)
-
van de Weijer, JoostUniv Autonoma Barcelona, Spain
(author)
-
Danelljan, MartinLinköpings universitet,Datorseende,Tekniska fakulteten(Swepub:liu)marda26
(author)
-
Khan, FahadLinköpings universitet,Datorseende,Tekniska fakulteten,Incept Inst Artificial Intelligence, U Arab Emirates(Swepub:liu)fahkh30
(author)
-
Univ Autonoma Barcelona, SpainDatorseende
(creator_code:org_t)
Related titles
-
In:IEEE Transactions on Image Processing: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC28:4, s. 1837-18501057-71491941-0042
Internet link
Find in a library
To the university's database