A method for estimating roadway billboard salience

TL;DR

This paper evaluates neural network models for detecting roadside billboards and uses saliency extraction methods to estimate their importance in driver perspective images, aiming to understand their potential distraction impact.

Contribution

It introduces a combined approach using YOLOv5, Faster R-CNN, and saliency methods UniSal and SpectralResidual to assess billboard significance in driving images.

Findings

YOLOv5 and Faster R-CNN effectively detect roadside billboards.

Saliency methods can identify the importance of billboards in driver images.

Database of eye-tracking data supports saliency model evaluation.

Abstract

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.