ExTraVis: Exploration of Traffic Incidents Using a Visual Interactive System

Abstract

The impact of road traffic incidents (e.g., road accidents, vehicle breakdowns) have become progressively worse over the years, being a major cause of many adverse issues such as serious injury, economic loss, and lifelong disabilities. Thus, it is essential to acknowledge these issues and proactively construct appropriate solutions to mitigate the impact of these issues in the future. This study outlines the history of traffic incident research and covers several solutions such as machine learning, mathematical modeling, and visualization system to traffic incident analysis. In this paper, we design a unique visualization system, ExTraVis, for incident data exploration and analysis that can be used to help traffic management controllers, aid to make decisions, and help them to understand how past incidents affected and where incidents may occur. The key features of this system are visual exploration and analysis to overcome the problems linked with road traffic incidents and to encourage future work and improvements. Additionally, we gather various custom queries for free text search feature. We find that people ask questions and our system provide 90% correct visual insights. Finally, we demonstrate the effectiveness and robustness of ExTraVis by comparing with three different incident visualization dashboards and a user study.