12. Driver adaptive prediction for pedestrian detectability using in-vehicle camera images
Ryunosuke Tanishige, Daisuke Deguchi, Keisuke Doman, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Naoki Nitanda · 2017
In recent years, advances in pedestrian detection technology have resulted in the development of driving assistance systems that notify the driver of the presence of pedestrians. However, warning of the presence of all pedestrians would con-fuse the driver. Therefore, the driver should only be notified of the less detectable pedestrians to avoid confusion. To achieve this, it is necessary to develop a method to predict the driver’s perception performance of pedestrian detectability. This paper proposes a method that predicts pedestrian detectability considering the difference between individual drivers. The proposed method constructs a predictor specific to each driver, in order to predict pedestrian detectability precisely. To obtain the ground truth of pedestrian detectability, an experiment was conducted with human subjects using images from an in-vehicle camera including pedestrians. From the comparison between the output of the proposed method and the actual detectability, we confirmed that the proposed method significantly reduces prediction error in comparison with existing methods.