%0 Conference Proceedings
%T Read While You Drive-Multilingual Text Tracking on the Road
%A Sergi Garcia Bordils
%A George Tom
%A Sangeeth Reddy
%A Minesh Mathew
%A Marçal Rusiñol
%A C.V. Jawahar
%A Dimosthenis Karatzas
%B 15th IAPR International workshop on document analysis systems
%D 2022
%V 13237
%@ 978-3-031-06554-5
%F Sergi Garcia Bordils2022
%O DAG; 600.155; 611.022; 611.004
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3783), last updated on Mon, 24 Apr 2023 11:55:40 +0200
%X Visual data obtained during driving scenarios usually contain large amounts of text that conveys semantic information necessary to analyse the urban environment and is integral to the traffic control plan. Yet, research on autonomous driving or driver assistance systems typically ignores this information. To advance research in this direction, we present RoadText-3K, a large driving video dataset with fully annotated text. RoadText-3K is three times bigger than its predecessor and contains data from varied geographical locations, unconstrained driving conditions and multiple languages and scripts. We offer a comprehensive analysis of tracking by detection and detection by tracking methods exploring the limits of state-of-the-art text detection. Finally, we propose a new end-to-end trainable tracking model that yields state-of-the-art results on this challenging dataset. Our experiments demonstrate the complexity and variability of RoadText-3K and establish a new, realistic benchmark for scene text tracking in the wild.
%U https://link.springer.com/chapter/10.1007/978-3-031-06555-2_51
%U http://refbase.cvc.uab.es/files/GTR2022.pdf
%U http://dx.doi.org/10.1007/978-3-031-06555-2_51
%P 756–770