Authors: Seon-Geol Kim; Kyeong-Hoon Jung; Kang Yi
Addresses: School of Electrical Engineering, Kookmin University, 77 Jeongneung-ro, Seongbuk-gu, Seoul, Korea ' School of Electrical Engineering, Kookmin University, 77 Jeongneung-ro, Seongbuk-gu, Seoul, Korea ' School of Computer Science and Electrical Engineering, Handong Global University, 558 Handong-ro Buk-gu, Pohang Gyeongbuk, Korea
Abstract: The blind spot monitoring (BSM) is one of the key functions of advanced driver assistance system (ADAS). In this paper, we propose vision-based blind spot detection and tracking algorithm which is applicable at night-time. The feature of highly bright blobs due to the headlights of behind vehicle is employed for the detection of vehicles in blind spot area, because the appearance-based approach that can be used at daytime is not any more appropriate. We calculate the motion vectors of detected blobs to find an approaching vehicle and make headlight grouping to estimate its position by use of the projection map. We can successfully generate an alarm signal by detection and tracking the overtaking vehicle in blind spot area at night-time.
Keywords: advanced driver assistance system; ADAS; blind spot monitoring; BSM; vehicle detection; projection map.
International Journal of Internet Technology and Secured Transactions, 2018 Vol.8 No.1, pp.15 - 24
Received: 17 Mar 2017
Accepted: 23 Jun 2017
Published online: 23 May 2018 *