Recognition of Driver Turn Behavior Based on Video Analysis
2012 ◽
Vol 433-440
◽
pp. 6230-6234
◽
Keyword(s):
In view of the shortcoming of driver state detection system which may take turn behavior as driver distraction, a new method to recognize turn behavior was proposed based on video images analysis. The driver hands position in different driving behavior were analyzed and we found that the position of driver’s hands changed more violent when in turning than in other driving behavior. So we may use standard deviation of driver hands position to recognize driver turn behavior. In order to improve the hands locating speed the Particle Filtering was used to track the driver hands. And experiments resulted that the recognition algorithm can identify the driver's turn behavior.