@inbook{812d82a58e9043e88e35d02f82523eab,
title = "RoadText-1K: Text Detection Recognition Dataset for Driving Videos",
abstract = "Perceiving text is crucial to understand semantics of outdoor scenes and hence is a critical requirement to build intelligent systems for driver assistance and self-driving. Most of the existing datasets for text detection and recognition comprise still images and are mostly compiled keeping text in mind. This paper introduces a new RoadText-1K dataset for text in driving videos. The dataset is 20 times larger than the existing largest dataset for text in videos. Our dataset comprises 1000 video clips of driving without any bias towards text and with annotations for text bounding boxes and transcriptions in every frame. State of the art methods for text detection, recognition and tracking are evaluated on the new dataset and the results signify the challenges in unconstrained driving videos compared to existing datasets. This suggests that RoadText-1K is suited for research and development of reading systems, robust enough to be incorporated into more complex downstream tasks like driver assistance and self-driving. The dataset can be found at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtext-1k.",
author = "Sangeeth Reddy and Minesh Mathew and Lluis Gomez and Marcal Rusinol and Dimosthenis Karatzas and Jawahar, {C. V.}",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.",
year = "2020",
month = may,
doi = "10.1109/ICRA40945.2020.9196577",
language = "English",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "11074--11080",
booktitle = "2020 IEEE International Conference on Robotics and Automation, ICRA 2020",
}