Continuous Car Driving intention recognition with syntactic pattern approach

Abstract

Intelligent driver assistance systems are becoming a necessity in every future cars with the increased of injuries and fatalities from road accidents. The implementation of a wide array of sensors in a car could be utilised to detect driver's intention to improve safety. This paper present an analysis of car driver's behaviour pattern recognition in lane changes and turns behaviour using context-free grammar in syntactic recognition approach. The driving data which consists of the driver's eye gaze; the car's speed, steering wheel angle, and signal indication; are represented in symbolic form thus forming sentences which represent a specific behaviour. Grammars are formulated based on the sentences trained from training data. The grammars are then evaluated by parsing the testing data. The results shows that driving behaviours are correctly detected at 90% recognition rate from less than 0.5 seconds after a driving maneuver behaviour commenced.