AutoBiVision - A Novel Vision-Based Bicycle Warning System

Abstract

This article presents the concept of a novel visionbased bicycle warning system (AutoBiVision). AutoBiVision system warns the driver of the approaching bicycles without offering redundant or disturbing information, which means when the driver is focusing on one specific area, the system will focus on the other areas that the driver is not paying attention to. To this end both the driver and cyclists require to be monitored, which means two camera systems are needed: The inner camera system captures the interior of the vehicle while the outer camera system captures the bicycle lane as well as the cyclists. With the purpose of intelligently detecting and tracking the bicyclist in wider ranges, two rotatable cameras, which are components of the outer camera system, are mounted on the top of the left and right back mirrors of the vehicle, respectively. The angle control of the rotatable cameras depends on the results of bicycle tracking and bicycle lane detection. In this contribution, the main structure of the system and the initial results of a series of novel methods of bicycle lane detection, are presented. A patent is pending.  Index Terms-bicycle warning system; bicycle lane detection; rotatable cameras Jie Zhao was born in Shandong, PR China on May 4, 1989. He obtained the B.Eng degree in School of Information and Science, Shandong University, in Jinan in 2012, majoring in communication engineering. In 2011 he worked as an INTERN at Hisense Group in Qingdao, China. He published several papers in the field of vision-based driver monitoring. From 2012 he became a M.Sc. degree candidate at the University of Bremen, Bremen, Germany, majoring in information and automation engineering. His paper "Robust Profile Face Detection and Rotation Angle Estimation of the Driver's Head in a Novel Dazzling Avoidance System" proposes a novel way to estimate the yaw rotating angle of the driver's head, which was published by IEEE on the 2015 IEEE Intelligent Vehicles Symposium in Seoul, Korea. His previous research focused on wireless communication and currently his research field is computer vision and robotics. Mr. Zhao is a student member of IEEE. He obtained the "Full-Mark Master Project" award at University of Bremen in 2015.