How Much of Driving Is Preattentive?

Driving a car in an urban setting is an extremely difficult problem, incorporating a large number of complex visual tasks; however, this problem is solved daily by most adults with little apparent effort. This paper proposes a novel vision-based approach to autonomous driving that can predict and even anticipate a driver´s behavior in real time, using preattentive vision only. Experiments on three large datasets totaling over 200 000 frames show that our preattentive model can (1) detect a wide range of driving-critical context such as crossroads, city center, and road type; however, more surprisingly, it can (2) detect the driver´s actions (over 80% of braking and turning actions) and (3) estimate the driver´s steering angle accurately. Additionally, our model is consistent with human data: First, the best steering prediction is obtained for a perception to action delay consistent with psychological experiments. Importantly, this prediction can be made before the driver´s action. Second, the regions of the visual field used by the computational model strongly correlate with the driver´s gaze locations, significantly outperforming many saliency measures and comparable to state-of-the-art approaches.