Defining Traffic Scenarios for the Visually Impaired

Abstract

For the development of a transfer concept of camera-based object detections from Advanced Driver Assistance Systems to the assistance of the visually impaired, we define relevant traffic scenarios and vision use cases by means of problem-centered interviews with four experts and ten members of the target group. We identify the six traffic scenarios: general orientation, navigating to an address, crossing a road, obstacle avoidance, boarding a bus, and at the train station clustered into the three categories: Orientation, Pedestrian, and Public Transport. Based on the data, we describe each traffic scenario and derive a summarizing table adapted from software engineering resulting in a collection of vision use cases. The ones that are also of interest in Advanced Driver Assistance Systems - Bicycle, Crosswalk, Traffic Sign, Traffic Light (State), Driving Vehicle, Obstacle, and Lane Detection - build the foundation of our future work. Furthermore, we present social insights that we gained from the interviews and discuss the indications we gather by considering the importance of the identified use cases for each interviewed member of the target group.