New Prediction Method of Running Out by Pressure Sensor for Pedestrian-Vehicular Collision Avoidance Support System

We have developed Pedestrian-Vehicular Collision Avoidance Support System (P-VCASS) in order to protect pedestrians from traffic accidents and its effectiveness has been verified. P-VCASS is a system that takes into account pedestrian's moving situations. It gives warning to drivers of neighboring vehicles in advance if there is a possibility of collision between vehicles and pedestrians. There are pedestrians to move around. They are dangerous for vehicle drivers because they have high probability of running out into the road suddenly. Hence, we need to take into account the presence of them. In this paper, we propose a new prediction method to adapt to running out into the road by using pressure sensor attached to sole of a pedestrian. We show the validity of the proposed system by experiments using a vehicle and a pedestrian terminal in the intersection. As a result, we show that a driver of vehicle is able to detect dangerous pedestrians quickly and accurately.

[1]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

[2]  Hui Fang,et al.  Design of a wireless assisted pedestrian dead reckoning system - the NavMote experience , 2005, IEEE Transactions on Instrumentation and Measurement.

[3]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[4]  Mansour Alsulaiman,et al.  Motion periodicity based pedestrian detection and particle filter based pedestrian tracking using stereo vision camera , 2012, 2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP).

[5]  Sasi Inguva,et al.  Padati: A Robust Pedestrian Dead Reckoning System on Smartphones , 2012, 2012 IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications.

[6]  Ryohta Yamaguchi,et al.  A New Collision Judgment Algorithm for Pedestrian-Vehicular Collision Avoidance Support System (P-VCASS) in Advanced ITS , 2010, 2010 Sixth International Conference on Networking and Services.

[7]  Masao Nakagawa,et al.  An anti-car collision system using GPS and 5.8 GHz inter-vehicle communication at an off-sight intersection , 2000, Vehicular Technology Conference Fall 2000. IEEE VTS Fall VTC2000. 52nd Vehicular Technology Conference (Cat. No.00CH37152).

[8]  Ryohta Yamaguchi,et al.  Pedestrian Oriented Vehicular Collision Avoidance Support System: P-VCASS , 2010, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[9]  Yuanjie Wang,et al.  A new pedestrian detection algorithm used for Advanced Driver-Assistance System with one cheap camera , 2013, Proceedings 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC).

[10]  Fawzi Nashashibi,et al.  Fast Pedestrian Detection in Dense Environment with a Laser Scanner and a Camera , 2009, VTC Spring 2009 - IEEE 69th Vehicular Technology Conference.

[11]  Tomotaka Wada,et al.  A New Activity Estimation Method of Pedestrians with Coordination between Intersections in P-VCASS , 2012, 2012 41st International Conference on Parallel Processing Workshops.

[12]  Alistair Armitage,et al.  An embedded real-time pedestrian detection system using an infrared camera , 2009 .

[13]  X.B. Cao,et al.  Extended Kalman filter based pedestrian localization for collision avoidance , 2009, 2009 International Conference on Mechatronics and Automation.

[14]  Shunsuke Kamijo,et al.  On-board wireless sensor for collision avoidance: Vehicle and pedestrian detection at intersection , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[15]  Wu-chi Feng,et al.  GPS-based message broadcasting for inter-vehicle communication , 2000, Proceedings 2000 International Conference on Parallel Processing.

[16]  Takeo Kato,et al.  An obstacle detection method by fusion of radar and motion stereo , 2002, SICE 2003 Annual Conference (IEEE Cat. No.03TH8734).