CADAS: A multimodal advanced driver assistance system for normal urban streets based on road context understanding

Abstract

Comprehensive situational awareness is paramount to the effectiveness of higher-level functions of the advanced driver assistance systems (ADAS) used in daily urban traffic, in which, the host vehicle have to interact with other cars. This paper addresses a multimodal advanced driver assistance system, which we call CADAS (Contextual ADAS), designed for expanding the usability of current ADAS functions, including LKA, ACC, and PCS, to normal urban streets, particularly for non-marking roads. In the proposed system, the relational contexts between the host vehicle, the road and other vehicles are employed for both the low level object detection improvement and the high level scene understanding and decision making. Experimental results in various typical but challenging scenarios show the effectiveness of the proposed system.