Key points are not available for this paper at this time.
Over the last decade, the Advanced Driver Assistance System (ADAS) concept has evolved significantly. ADAS involves several technologies such as automotive electronics, vehicle-to-vehicle (V2V) vehicle-to-infrastructure (V2I) communication, RADAR, LIDAR, computer vision, and machine learning. Of these, computer vision and machine learning based solutions have mainly been effective that have allowed real-time vehicle control, driver aided systems, etc. However, most of the existing works deal with the deployment of ADAS and autonomous driving functionality in countries with well-disciplined lane traffic. Nevertheless, these solutions and frameworks do not work in countries and cities with less-disciplined/chaotic traffic. This paper identifies the research gaps, reviews the state-of-the-art looking at the different functionalities of ADAS and its levels of autonomy. Importantly, it provides a detailed description of vision intelligence and computational intelligence for ADAS. The eye-gaze and head pose estimation in vision intelligence is detailed. Notably, the learning algorithms such as supervised, unsupervised, reinforcement learning and deep learning solutions for ADAS are considered and discussed. Significantly, this would enable developing a real-time recommendation system for system-assisted/autonomous vehicular environments with less-disciplined road traffic.
Nidamanuri et al. (Wed,) studied this question.