Vision-Based Blind Spot Monitoring Using Rear-View Camera and Its Real-Time Implementation in an Embedded System

Kyeong Hoon Jung,Kang Yi 한국정보과학회 2018 Journal of Computing Science and Engineering Vol.12 No.3

Blind spot monitoring (BSM) is one of the essential functions of Advanced Driver Assistance Systems (ADAS). In this paper, we propose a vision-based monitoring algorithm to detect vehicles in a blind-spot area using a rear-view camera. Instead of moving around the whole image to search for a vehicle, we use well-defined detection windows with fixed position and size. And we used histogram of oriented gradients (HOG) and the support vector machine (SVM) to detect a vehicle in each detection window. When a vehicle is detected, we compute the motion vector of the vehicle to determine if it approaches the ego vehicle or not. The alarm signal is finally generated based on history of events. To evaluate performance of the BSM algorithm, we captured various kinds of sequences by using a rear-view camera. Experimental results reveal precision higher than 98% and recall higher than 99%. We also develop high-speed methods to improve processing speed while keeping performance degradation as minimal as possible. Implementation of this fast algorithm on a commercial embedded device validated real-time characteristics of the proposed BSM algorithm.

지능형센서를 이용한 차량 측면충돌방지시스템 개발

윤민섭(Minseob Yoon),김현수(Hyunsoo Kim),제우성(Wooseong Che),부광석(Kwangseok Boo),김흥섭(Heungseob Kim) 한국자동차공학회 2011 한국자동차공학회 부문종합 학술대회 Vol.2011 No.5

The latest vehicle yields a superior safety and reduction of driving burden by monitoring the driving state of vehicle and its environment with various sensors. To detect other vehicles and objects of the rear left and right-side blind spot area of driver, provide the information about a existence of objects inside the blind spot, and give a signal to avoid collision, this study proposes the intelligent outside rear-view mirror system. This task has substantially complicated several factors. For example, the size, geometry and features of the various vehicles which might enter the monitored zone is varied widely and therefore present various reflective characteristics. This study proposes the optimal specification and configuration of optical system and IR array sensor of blind spot detection system, and shows the results of the performance evaluation of developed system.

SILS 환경에서의 측면 충돌 방지시스템 개발

윤민섭(Minseob Yoon),김현수(Hyunsoo Kim),부광석(Kwangseok Boo),김흥섭(Heungseob Kim) 한국자동차공학회 2011 한국자동차공학회 학술대회 및 전시회 Vol.2011 No.11

Recently the automotive industry to predict the risk factors with the sensor to the driver in an accident be avoided by delivering systems that are now underway to study through a combination of various sensors and car, and that during the course of study as part of the study vehicle"s blind-spot detection system is actively underway. Intelligent sensors developed in this study of 15˚ ~ 45˚ vehicle blind spot region is recognized by the infrared sensor. In order to increase the sensitivity of the sensor to receive infrared signals mixed with the carrier frequency and the center frequency of the signal consists of a mixed-frequency sensitivity and improved features. SILS environment was built according to international ISO standards based on specifications and configuration of presented BSDS. The environment of the road was built using PreScan and Matlab / simulink was configured using the control logic. In order to verify the applicability of the developed BSDS system, BSDS systems receive information of vehicle distance, steering angle, speed such as actual driving conditions. The applicability of the system presented safe conditions and accident situations by a visual representation and data.

차량 측후방 충돌방지를 위한 사각지대 감지시스템 개발

최정광(Jungkwang Choi),윤문영(Moonyoung Yoon),정재업(Jaeeop Jung),부광석(Kwangseok Boo),김흥섭(Heungseob Kim) 대한기계학회 2012 대한기계학회 춘추학술대회 Vol.2012 No.11

Recently the automotive industry to predict the risk factors with the sensor to the driver in an accident be avoided by delivering systems that are now underway to study through a combination of various sensors and car, and that during the course of study as part of the study vehicle’s blind-spot detection system is actively underway. Intelligent sensors developed in this study of 15°~45° vehicle blind spot region is recognized by the infrared sensor. In order to increase the sensitivity of the sensor to receive infrared signals mixed with the carrier frequency and the center frequency of the signal consists of a mixed-frequency sensitivity and improved features. SILS environment was built according to international ISO standards based on specifications and configuration of presented BSDS. The environment of the road was built using PreScan and Matlab / simulink was configured using the control logic. In order to verify the applicability of the developed BSDS system, BSDS systems receive information of vehicle distance, steering angle, speed such as actual driving conditions. The applicability of the system presented safe conditions and accident situations by a visual representation and data.

적외선 어레이센서를 이용한 차량 사각지대감지 시스템

윤문영(Moonyoung Yoon),김세훈(Sehun Kim),손민혁(Minhyuk Son),윤득선(Duksun Yun),김화식(Hwasik Kim),허원무(Wonmoo Hur),김흥섭(Heungseob Kim) 한국자동차공학회 2008 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-

The latest vehicle yields a superior safety and reduction of driving burden by monitoring the driving state of vehicle and its environment with various sensors. To detect other vehicles and objects of the rear left and right-side blind spot area of driver. provide the information about a existence of objects inside the blind spot, and give a signal to avoid collision, this study proposes the intelligent outside rear-view mirror system. This task has substantially complicated several factors. For example, the size, geometry and features of the various vehicles which might enter the monitored zone is varied widely and therefore present various reflective characteristics. This study proposes the optical system and optimal configuration of IR array sensor, controller design to detect and judge a presence of other vehicles and shows the results of the performance evaluation of developed system.

초음파센서를 이용한 BSD 경고시스템 개발 및 평가

김종민(Jongmin Kim),송문형(Moonhyung Song),김창일(Changil Kim),이광수(Gwangsu Lee),김문식(Moonsik Kim) 한국자동차공학회 2017 한국자동차공학회 부문종합 학술대회 Vol.2017 No.5

Recently, most automakers have been working on the development of advanced driver assistance systems with an emphasis on driver safety. Conventional BSD is a blind zone warning system, and most of them use radar equipment for obstacle detection. However, BSD systems using radar equipment are still difficult to popularize in terms of price. Therefore, there is a need to reduce costs by developing a multi-function using a popularized driver-assisted system sensor. In this paper, we propose an ultrasonic BSD warning system which has a blind zone warning function by using ultrasonic sensor for parking assist system.

BSD 시스템의 성능한계에 관한 연구

정승권(Seungkwon Jung) 한국자동차공학회 2011 한국자동차공학회 학술대회 및 전시회 Vol.2011 No.11

Recently driver assist system has a tendency to use the technology of sensors for pre-safety. Blind Spot Detection(BSD) system is one of that. BSD system uses two radar sensors installed in rear bumper. It warns a driver when a vehicle is closing to blind spot zone. But it has the performance limitation in some cases such as close overtaking with lane change the ego lane of subject vehicle to the next lane. A vehicle collision can happen because of the warning delay time in BSD system. The performance limitation in BSD system is found out by vehicle test in this paper and the way to improvement is presented.

적외선 어레이센서를 이용한 차량 사각지대감지 시스템

윤문영(Moonyoung Yoon),손민혁(Minhyuk Son),윤득선(Duksun Yun),허원무(Wonmoo Hur),김화식(Hwasik Kim),김흥섭(Heungseob Kim) 한국자동차공학회 2007 한국자동차공학회 지부 학술대회 논문집 Vol.- No.-

The latest vehicle yields a superior safety and reduction of driving burden by monitoring the driving state of vehicle and its environment with various sensors. To detect other vehicles and objects of the rear left and right-side blind spot of driver, provide the information about a existence of objects inside the blind spot, and give a signal to avoid collision, this study proposes the intelligent outside rear-view mirror(IOSRVM) system. This task has substantially complicated several factors. For example, the size, geometry and features of the various vehicles which might enter the monitored zone is varied widely and therefore present various reflective characteristics. This study proposes the optical system and optimal configuration of IR array sensor, controller design to detect and judge a presence of other vehicles and shows the results of the performance evaluation of developed system.

In-vehicle 통합 운전자지원시스템 효과평가 방법론 개발 및 적용

정은비,오철,정소영 대한교통학회 2014 대한교통학회지 Vol.32 No.4

Recently, advanced sensors and communication technologies have been widely applied to advanced safetyvehicles for reducing traffic accidents and injury severity. To apply the advanced safety vehicle technologies, it isimportant to quantify safety benefits, which is a fundamental for justifying application. This study proposed amethodology for quantifying the effectiveness of the Advanced Driver Assistant System (ADAS) with the AnalyticHierarchy Process (AHP). When the proposed methodology is applied to 2008-2010 Gyeonggi-province crash data,ADAS would reduce about 10.18% of crashes. In addition, Adaptive Cruise Control, Automatic EmergencyBraking System, Lane Departure Warning System and Blind Spot Detection System are expected to reduce about10.43%, 10.17%, 9.96%, and 10.18%, respectively. The outcomes of this study might support decision making fordeveloping not only vehicular technologies but also relevant safety policies. 교통사고 및 사고로 인한 사상자수 감소를 위해 기존의 자동차에 각종 센서나 통신기술 등의 첨단기술을 융합한첨단안전자동차에 대한 연구가 활발히 진행 중에 있다. 이러한 첨단안전자동차의 시장진입 및 관련 기술도입을 위해서는 첨단안전자동차 기술의 효과분석을 통한 도입 타당성 평가가 필요하다. 본 연구에서는 계층화분석법(AHP:Analytic Hierarchy Process)을 이용하여 첨단안전자동차 기술 중 사고예방의 기능을 가지는 첨단운전자지원시스템의효과추정 방법론을 제시하였다. 제시한 효과추정 방법론을 이용하여 적응형순항제어장치(ACC: Adaptive CruiseControl), 자동비상제동장치(AEBS: Automatic Emergency Braking System), 차로이탈경고장치(LDWS: LaneDeparture Warning System), 사각지역감시장치(BSDS: Blind Spot Detection System)의 네 가지 시스템을 통합하여평가하였다. 분석결과, 운전자지원시스템의 효과는 약 10.18%의 사고감소 효과가 있는 것으로 나타났으며, 적응형순항제어장치는 10.43%, 자동비상제동장치는 10.17%, 차로이탈경고장치는 9.96%, 사각지역감시장치는 10.14%의 사고감소 효과가 있을 것으로 추정되었다. 본 연구의 결과는 추후 첨단안전자동차 시스템 도입시 도입타당성을 제시하는데 기초자료로써 활용이 가능할 것으로 기대된다.

ISRSS: INTEGRATED SIDE/REAR SAFETY SYSTEM

Jung, H.G.,Cho, Y.H.,Kim, J. 한국자동차공학회 2010 International journal of automotive technology Vol.11 No.4

As driver assistant systems (DAS) and active safety vehicles (ASV) with various functions become popular, it is not uncommon for multiple systems to be installed on a vehicle. If each function uses its own sensors and processing unit, it will make installation difficult and raise the cost of the vehicle. As a countermeasure, research integrating multiple functions into a single system has been pursued and is expected to make installation easier, decrease power consumption, and reduce vehicle pricing. This paper proposes a novel side/rear safety system using only one scanning laser radar, which is installed in the rear corner of the driver's side. Our proposed system, ISRSS (integrated side/rear safety system), integrates and implements four system functions: BSD (blind spot detection), RCWS (rear collision warning system), semi-automatic perpendicular parking, and semi-automatic parallel parking. BSD and RCWS, which operate while the vehicle is running, share a common signal processing result. The target position designation for perpendicular parking and parallel parking situations is based on the same signal processing. Furthermore, as system functions during running and those during automatic parking operate in exclusive situations, they can share common sensors and processing units efficiently. BSD and RCWS system functions were proved with 13025 and 2319 frames, respectively. The target position designation for perpendicular and parallel parking situations was evaluated with 112 and 52 situations and shows a success rate of 98.2% and 92.3%, respectively.