• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.511-513
• /
• 2001

지능형 교통 시스템(ITS)은 1) 도로의 상황 분석과 2) 위반 차량의 검지를 자동으로 수행하여 원활한 교통 제어를 제공하는 목적을 가지고 있다. 본 논문에서는 교차로에서 위반 차량을 검지하기 위하여 도로위의 차량 검지하고 차량의 진행 경로를 추적하는 기법으로 주간에는 배경 영상을 사용하지 않고 프레임간의 차를 이용하여 차량의 움직임 정보를 추출하고 야간에는 전조등을 검출하여 차량을 추적하는 기법으로 주간의 겨우 차량의 움직임만을 감지하므로 칼만 필터(Kalman Filter) 등에 의한 예측이 불가능하므로 현재 위치와 진행방향으로 움직임 정보를 추적하는 기법을 제안한다. 제안하는 기법은 주간 그림자의 영향과 야간의 난반사의 영향을 제거할 수 있고 입력 영상을 320x240으로 축소하여 초당 10프레임이상으로 처리하므로 정확한 차량의 움직임을 추적할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.740-743
• /
• 2010

본 논문에서는 컴퓨터 비젼에서 특징점 추적을 이용한 끼어들기 위반차량 검지 방법을 제안한다. 제안된 끼어들기 위반차량 검지 시스템의 전체적인 알고리즘은 영상 변환 및 전처리, 특징 추출, 추적대상 차량의 특징점 등록 및 추적, 끼어들기 위반차량 검지 등의 단계로 구성된다. 특히 형태학적 기울기 영상에서 특징점을 추출하므로 써 주간 및 야간 영상에 대해 동일한 알고리즘을 적용하여 그림자, 기상 조건, 차량 전조등 및 조명 등에 강인한 실시간성이 가능한 영상 검지 시스템을 구성 한다. 제안한 시스템을 끼어들기 금지구간에서 주간, 야간, 비 오는 날 야간에 취득한 영상을 사용하여 실험한 결과 정인식률 99.49%와 오류율 0.51%를 보였으며, 실시간처리에 문제가 없는 초당 91.34프레임의 빠른 처리속도를 나타냈다.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2006.05a
• /
• pp.131-136
• /
• 2006

전조등의 밝기 변동에 대한 운전자의 시인성 및 뇌파측정, 심리평가를 행하고 이를 바탕으로 전조등 밝기변화의 한계값과 운전자의 안전성을 고려한 평가 알고리즘을 개발하였다. 전조등의 밝기 변화 한계치는 심리평가의 설문지 작성을 통한 주관적 평가를 바탕으로 밝기 변화, 눈 깜박임, 불쾌감 등에 대한 한계값을 제시하였다. 그리고 뇌파측정을 바탕으로 정신적, 시각적 스트레스에 대한 한계값을 제시하였으며, 운전자의 시인성 측정을 바탕으로 차량을 장애물의 위협 없이 안전하게 정지하기 위한 한계값을 제시하였다. 안전성 평가 알고리즘은 장애물을 인식하고 브레이크 페달을 밟기 시작하기 까지 최대한 허용할 수 있는 시간인, 여유 시간 이내에 전압변동을 완료하고 최초의 정상 전압으로 복귀하는 경우와 그렇지 않은 경우를 적용할 수 있는 2종류의 알고리즘을 개발하였다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.19 no.2
• /
• pp.92-97
• /
• 2011

Vehicle lightings are very important for safe driving during night time. Since the eye recovery time after an exposure to oncoming headlights would take after several seconds, the aiming point of vehicle head lamps have to pass safety requirements. Despite the fact that vehicle inclination is variable with vehicle load conditions, the head lamps aiming point is usually fixed at a constant position which is set by car manufacturer. Consequently, vehicle head lamps under varying load conditions often make people in the opposing vehicle uncomfortable, and even worse, can cause an accident. This paper presents an active vehicle lighting mechanism to automatically adjust its aiming point, or cut-off line, in order to compensate the change in vehicle inclination resulting from load variations. The effectiveness of the proposed method is demonstrated through a set of simulations and experiments with a real vehicle.

• Journal of the Korean Society for Railway
• /
• v.19 no.1
• /
• pp.46-53
• /
• 2016

LED light sources have been known to have a long life and good energy efficiency compared to traditional light sources. Recently, headlamps using LED light sources have ensured the forward visibility and safe operation of high-speed rolling stock. However, assessing the lifespan of LED headlamps based on real test data is not easy because it depends on the multiple stress factors such as a fixed driving current, junction temperature, vibration and so on. Generally, LED headlamps have failed before their advertised life span mainly due to temperature. Thus, the performance assessment of a temperature control unit should be done before a life cycle test of LED headlamps. This study attempted to develop a prototype temperature control module for a lifecycle test system using a commercial LED headlight and verified the system through experiments.

• Journal of Korea Multimedia Society
• /
• v.13 no.7
• /
• pp.983-990
• /
• 2010

The image processing technique is very sensitive to the variation of external environment, so it tends to lose a lot of accuracy when the external environment changes rapidly. In this paper, we propose a vehicle detecting and tracking system for crime prevention suitable for an external environments with various changes using the image processing technique. Because the vehicle camera detector for crime prevention extracts and tracks the vehicle within one lane, it is important to classify a characteristic region rather than the contour of a vehicle. The proposed system detects the entrance of the vehicle using optical flow and tracks the vehicle by classifying the headlights, the bonnet, the front-window and the roof area of the vehicle. Experimental results show that the proposed method is robust to the environmental changes such as type, speed and time of a vehicle.

• Journal of the Korean Society for Railway
• /
• v.18 no.2
• /
• pp.111-116
• /
• 2015

LED luminaires as a lighting system have attracted much research attention due to their high efficiency and long lifetimes. However, disappointing outcomes have been noted in terms of performance levels and lifetimes as compared to desired system requirements in practice due to certain electrical and thermal characteristics of LEDs. LM-80 and TM-21 established by IESNA are the best known standards for lifetime test procedures and estimation techniques. However, they only handle LED light sources without guaranteeing the LED luminaire in a reliability test. They also operate for more than 6,000 hours and undergo various stresses, such as the operating current and temperature. Therefore, a lifetime standard for LED luminaires has not yet been established. This paper proposes a conceptual design of a lifetime test system for LED headlamps depending on the operating environment. Eventually, this method can assist with evaluations of the validity of lifetime standard tests of LED headlamps.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.10
• /
• pp.13-21
• /
• 2007

Based on the measurement results, a limit value for the change of the brightness of the headlamp, and an estimation algorithm considering the driver's safety was developed. Limitation values concerning being uncomfortable, blinking, and brightness change were indicated based on a subjective estimation of the psychological estimation. Also a safety estimation algorithm and a limitation value for stopping safely without the threat of obstacles to the vehicle were indicated by the perception measurement.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.282-294
• /
• 2017

In this paper, we propose a novel intelligent headlight control (IHC) system which is durable to various road lights and camera movement caused by vehicle driving. For detecting candidate light blobs, the region of interest (ROI) is decided as front ROI (FROI) and back ROI (BROI) by considering the camera geometry based on perspective range estimation model. Then, light blobs such as headlights, taillights of vehicles, reflection light as well as the surrounding road lighting are segmented using two different adaptive thresholding. From the number of segmented blobs, taillights are first detected using the redness checking and random forest classifier based on Haar-like feature. For the headlight and taillight classification, we use the random forest instead of popular support vector machine or convolutional neural networks for supporting fast learning and testing in real-life applications. Pairing is performed by using the predefined geometric rules, such as vertical coordinate similarity and association check between blobs. The proposed algorithm was successfully applied to various driving sequences in night-time, and the results show that the performance of the proposed algorithms is better than that of recent related works.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.783-785
• /
• 2015

Automotive Semiconductor revenue grew 3.9% in 2013 to $26.7 billion, driven by strength in LED lighting, ASSPs and analog ICs. Renesas Electronics held onto the No.1 spot despite a revenue decline, while Freescale Semiconductor, NXP, Texas Instruments and Robert Bosch made strong gains. Global Semiconductor manufacturers are paying attention to the Korean auto market, which reflects the reality of the local auto industry. The local industry has a long way go in the automotive semiconductor sector, even though it has grown to become the six-largest in the world. The reason for global semiconductors companies' interest in the local market lies in the fact that are the use of semiconductors in cars is on the rise, since smart and eco-friendly cars are becoming popular.