Sangeeth Reddy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sangeeth Reddy has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
C. V. Jawahar
1 shared publication- C. V. Jawahar
IIIT Hyderabad
1 shared publication - Dimosthenis Karatzas
Computer Vision Center
1 shared publication Dimosthenis Karatzas.
1 shared publication- George Tom
IIIT Hyderabad
1 shared publication - Lluis Gomez
Universitat Autónoma de Barcelona
1 shared publication
Latest Publications
- 18 May 2022
- Published by Springer Nature
- p. 756-770
Read While You Drive - Multilingual Text Tracking on the Road
- 18 May 2022
- Published by Springer Nature
- p. 756-770
Read While You Drive - Multilingual Text Tracking on the Road
- Open Access
RoadText-1K: Text Detection & Recognition Dataset for Driving Videos
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
Open AccessRoadText-1K: Text Detection & Recognition Dataset for Driving Videos
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