A method for estimating roadway billboard salience
This work addresses the issue of driver distraction from outdoor advertising, which is incremental as it applies existing detection and saliency methods to a new domain-specific dataset.
The study tackled the problem of detecting and assessing the salience of roadside billboards in driver-view images to understand their potential distraction, finding that YOLOv5 and Faster R-CNN were effective for detection, and UniSal and SpectralResidual methods were used for saliency extraction, with evaluation based on a database of eye tracking sessions.
Roadside billboards and other forms of outdoor advertising play a crucial role in marketing initiatives; however, they can also distract drivers, potentially contributing to accidents. This study delves into the significance of roadside advertising in images captured from a driver's perspective. Firstly, it evaluates the effectiveness of neural networks in detecting advertising along roads, focusing on the YOLOv5 and Faster R-CNN models. Secondly, the study addresses the determination of billboard significance using methods for saliency extraction. The UniSal and SpectralResidual methods were employed to create saliency maps for each image. The study establishes a database of eye tracking sessions captured during city highway driving to assess the saliency models.