5G/LTE based protection of vulnerable road users: Detection of crossing a curb

Unfortunately, every year many vulnerable road users (VRUs), such as pedestrians or bicyclists are killed or seriously injured in traffic accidents. Several research groups are working on different solutions including radar or laser based approaches to reduce the number of traffic accidents VRUs are involved. The approach presented in this paper is based on wireless communications such as WLAN and 5G/LTE and a "context filter". The "context filter" identifies vulnerable road users in potentially dangerous situations based on several contexts (VRU position, movement direction, accelerations). An identified dangerous situation is communicated between the VRU and the cars using wireless communication such as ad hoc or cellular systems. As one specifically interesting context for identifying dangerous situations this paper investigates on detecting pedestrians stepping onto the road. We examine smartphone sensor data and several reasoning classifiers to investigate whether "stepping onto the road" by detecting a pedestrian "crossing a curb" is possible. To the best of our knowledge detecting pedestrians crossing a curb by using smartphone sensors, has not been investigated so far.