Vision-based Driver Assistance Systems: Survey, Taxonomy and Advances

TL;DR

This paper surveys vision-based driver assistance systems, proposes a taxonomy, and introduces an abstract model to guide development towards autonomous driving.

Contribution

It provides a comprehensive taxonomy and a formal abstract model for developing vision-based driver assistance systems, facilitating progress towards autonomous vehicles.

Findings

Established a consistent terminology for the field.

Proposed a formal abstract model for system development.

Reviewed recent advances in vision-based ADAS.

Abstract

Vision-based driver assistance systems is one of the rapidly growing research areas of ITS, due to various factors such as the increased level of safety requirements in automotive, computational power in embedded systems, and desire to get closer to autonomous driving. It is a cross disciplinary area encompassing specialised fields like computer vision, machine learning, robotic navigation, embedded systems, automotive electronics and safety critical software. In this paper, we survey the list of vision based advanced driver assistance systems with a consistent terminology and propose a taxonomy. We also propose an abstract model in an attempt to formalize a top-down view of application development to scale towards autonomous driving system.