Kazumi Renge

Evidence-based automated traffic hazard zone mapping using wearable sensors

Recently, underestimating traffic condition risk is considered one of the biggest reasons for traffic accidents. In this paper, we proposed evidence-based automatic hazard zone mapping method using wearable sensors. Here, we measure drivers behavior using three-axis gyro sensors. Analyzing the measured motion data, proposed method can label characteristic motion that is observed at hazard zone. We gathered motion data sets form two types of driver, i.e., an instructor of driving school and an ordinary driver, then, tried to generate traffic hazard zone map focused on difference of the motions. Through the experiment in public road, we confirmed our method allows to extract hazard zone.

Development of a Wide-View Visual Presentation System and Estimating Human Primary Visual Cortical Magnification by Using FMRI For Traffic Safety

In this study, the authors examine basic human visual characteristics of retinotopic mapping using functional Magnetic Resonance Imaging (fMRI). A wide-view visual stimulus presentation system is developed and used for identifying the human primary visual cortex. The results are then applied to understanding the relationship between peripheral vision and traffic safety. The authors conclude that due to the limited cortical area that is used in processing visual information from the peripheral visual field, drivers are unable to recognize dangerous information from both sides of peripheral vision.