Citation

Greer R, Gopalkrishnan A, Deo N, Rangesh A, Trivedi MM. 27th International Technical Conference on the Enhanced Safety of Vehicles (ESV); April 3-6, 2023; Abstract #: 23-0333, pp. 11p. Washington, DC USA: US National Highway Traffic Safety Administration, 2023 open access.

Affiliation

Laboratory for Intelligent & Safe Automobiles University of California San Diego

Copyright

(Copyright © 2023 open access, US National Highway Traffic Safety Administration)

Abstract

27th International Technical Conference on the Enhanced Safety of Vehicles (ESV): Enhanced and Equitable Vehicle Safety for All: Toward the Next 50 Years

https://www-esv.nhtsa.dot.gov/Proceedings/27/27ESV-000333.pdf

Detecting road traffic signs and accurately determining how they can affect the driver's future actions is a critical task for safe autonomous driving systems. However, various traffic signs in a driving scene have an unequal impact on the driver's decisions, making detecting the salient traffic signs a more important task. Our research addresses this issue, constructing a traffic sign detection model which emphasizes performance on salient signs, or signs that influence the decisions of a driver. We define a traffic sign salience property and use it to construct the LAVA Salient Signs Dataset, the first traffic sign dataset that includes an annotated salience property. Next, we use a custom salience loss function, Salience-Sensitive Focal Loss, to train a Deformable DETR object detection model in order to emphasize stronger performance on salient signs. Results show that a model trained with Salience-Sensitive Focal Loss outperforms a model trained without, with regards to recall of both salient signs and all signs combined. Further, the performance margin on salient signs compared to all signs is largest for the model trained with Salience-Sensitive Focal Loss.