• 한국정밀공학회지
• /
• 제26권12호
• /
• pp.131-137
• /
• 2009

Recent technological advances made a vehicle more intelligent to increase safety and comfort. An intelligent vehicle provides drivers with safety warning information through audible sounds, visual displays, and tactile devices. However, elderly drivers have been known to decrease the physical and cognitive abilities such as muscular strength, hearing, eyesight, short term memory, and spatial perception. Therefore, possible age-related deficits should be considered to design an effective warning system. This paper aims to evaluate the impact of advancing age on response performance on audible safety warnings which are widely used for alerting driving hazards. In order to understand the effect of age-related hearing loss and movement slowing, three sound characteristics (frequency, intensity, and period) and three age groups (younger, middle, and older) are considered. Data was drawn from 38 drivers who drove a simulated rural road in a driving simulator. Experimental results show that age influences driver's response performance. In conclusion, the appropriate range of a warning sound is suggested.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 추계학술발표대회
• /
• pp.891-894
• /
• 2017

Lane detection algorithms became a key factor of advance driver assistance system (ADAS), since the rapidly increasing of high-technology in vehicles. However, one common problem of these algorithms is their performance's instability under various illumination conditions. We recognize a feasible complementation between image processing and color science to address the problem of lane marks detection on the road with different lighting conditions. We proposed a novel lane detection algorithm using the attributes of a uniform color space such as $CIEL^*C^*h$ with the implementation of image processing techniques, that lead to positive results. We applied at the final stage Clustering to make more accurate our lane mark estimation. The experimental results show the effectiveness of our method with detection rate of 91.80%. Moreover, the algorithm performs satisfactory with changes in illumination due to our process with lightness ($L^*$) and the color's property on $CIEL^*C^*h$.

• ETRI Journal
• /
• 제41권6호
• /
• pp.731-738
• /
• 2019

We proposed a novel electromagnetic band-gap (EBG) cell-embedded antenna structure for reducing the interference that radiates at the antenna edge in wireless access in vehicular environment (WAVE) communication systems for vehicle-to-everything communications. To suppress the radiation of surface waves from the ground plane and vehicle, EBG cells were inserted between micropatch arrays. A simulation was also performed to determine the optimum EBG cell structure located above the ground plane in a conformal linear microstrip patch array antenna. The characteristics such as return loss, peak gain, and radiation patterns obtained using the fabricated EBG cell-embedded antenna were superior to those obtained without the EBG cells. A return loss of 35.14 dB, peak gain of 10.15 dBi at 80°, and improvement of 2.037 dB max at the field of view in the radiation beam patterns were obtained using the proposed WAVE antenna.

• 제어로봇시스템학회논문지
• /
• 제22권1호
• /
• pp.1-7
• /
• 2016

ADAS (Advanced Driver Assistance Systems) requires not only real-time robust lane detection, both straight and curved, but also predicting upcoming steering direction by detecting the curvature of lanes. In this paper, a curvature lane detection algorithm is proposed to enhance the accuracy and detection rate based on using inverse perspective images and Gaussian Mixture Model (GMM) to segment the lanes from the background under various illumination condition. To increase the speed and accuracy of the lane detection, this paper used template matching, RANSAC and proposed post processing method. Through experiments, it is validated that the proposed algorithm can detect both straight and curved lanes as well as predicting the upcoming direction with 92.95% of detection accuracy and 50fps speed.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.237-250
• /
• 2015

This paper describes a hardware-oriented algorithm and its conceptual implementation in a real-time speed limit traffic sign detection system on an automotive-oriented field-programmable gate array (FPGA). It solves the training and color dependence problems found in other research, which saw reduced recognition accuracy under unlearned conditions when color has changed. The algorithm is applicable to various platforms, such as color or grayscale cameras, high-resolution (4K) or low-resolution (VGA) cameras, and high-end or low-end FPGAs. It is also robust under various conditions, such as daytime, night time, and on rainy nights, and is adaptable to various countries' speed limit traffic sign systems. The speed limit traffic sign candidates on each grayscale video frame are detected through two simple computational stages using global luminosity and local pixel direction. Pipeline implementation using results-sharing on overlap, application of a RAM-based shift register, and optimization of scan window sizes results in a small but high-performance implementation. The proposed system matches the processing speed requirement for a 60 fps system. The speed limit traffic sign recognition system achieves better than 98% accuracy in detection and recognition, even under difficult conditions such as rainy nights, and is implementable on the low-end, low-cost Xilinx Zynq automotive Z7020 FPGA.

• 대한임베디드공학회논문지
• /
• 제10권5호
• /
• pp.325-333
• /
• 2015

Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.

• 전기전자학회논문지
• /
• 제19권2호
• /
• pp.148-154
• /
• 2015

차량 전장시스템은 매 순간마다 정확한 인식을 통하여 사용자에게 정확한 경보를 전달해야 한다. 따라서 차량 영상 인식 알고리즘을 적용하기 위하여 빠른 전처리 시스템이 필요하다. 본 논문은 운전자 보조 시스템의 영상 처리를 목적으로 histogram equalization과 편차를 이용한 bilateral Filter를 사용하여 blur 영상을 보정하는 방법에 대해서 제안하였다. 제안한 시스템은 영상 스케일, 평활화, 노이즈 필터, 윤곽선 추출 순으로 총 5단계로 구성되며, bilateral filter의 과 값을 운전자 보조 시스템에서 나타나는 도로의 주행 현상에 적합하게 추출하여 10픽셀 이하의 blur를 기존의 방법들보다 빠르게 처리하였다. 실험 결과는 MATLAB을 사용하여 소요시간 및 PSNR을 구하였으며 기존의 방법과 비교하여 본 논문의 결과가 처리속도가 빠름을 입증하였다.

• 한국컴퓨터정보학회논문지
• /
• 제20권2호
• /
• pp.55-62
• /
• 2015

본 논문에서는 디지털 운행기록장치를 활용하여 자동차 운전자에 대한 실시간 위험운전행동 분석 및 경고를 통한 운전습관 개선과 안전운전 지원이 가능한 방법을 제안한다. 대부분의 교통사고와 에코 드라이빙은 자동차 운전자의 운전습관과 밀접한 관련이 있으며 이러한 운전습관을 자동화된 방법으로 실시간 분석 및 경고로 잘못된 운전습관을 개선시킬 필요가 있다. 제안 방법에 대한 구현 및 실험을 통하여 본 논문에서 제안하는 방법으로 운전자의 위험운전행동에 대한 실시간 분석 및 경고를 해줌으로써 운전습관 개선 유도와 안전운전을 지원하여 에코 드라이빙에 실제로 도움이 될 수 있음을 증명하였다.

• 한국정보통신학회논문지
• /
• 제18권9호
• /
• pp.2189-2196
• /
• 2014

본 논문에서는 자동차용 컴퓨터 비전 알고리즘을 고속으로 처리하기 위해 VLIW 보조프로세서를 설계하였다. VLIW 보조프로세서는 8단 파이프라인 구조로 1개의 사이클에 4개의 명령을 처리할 수 있으며, 보행자 인식을 위한 36개의 정수 및 부동 소수점 명령어 집합을 갖고 있다. 프로세서는 45nm CMOS 공정에서 최대 동작 속도는 300-MHz이며 약 210,900 게이트로 구성되며 예상 연산 성능은 1.2 GOPS 이다. VPE와 8개의 VLIW 코어로 구성된 비전 프로세서 시스템은 25~29 FPS의 보행자 검출 성능을 가진다. VLIW 보조 프로세서는 높은 검출 속도와 호스트 프로세서와 느슨한 결합 특성으로 다양한 비전 분야에 응용 가능하다.

• 한국자동차공학회논문집
• /
• 제24권5호
• /
• pp.495-503
• /
• 2016

Regulation for the testing and operation of autonomous vehicles on public roadways has been recently developed all over the world. For example, the licensing standards and the evaluation technology for autonomous vehicles have been proposed in California, Nevada and EU. But specific safety evaluation scenarios for autonomous vehicles have not been proposed yet. This paper presents safety evaluation scenarios for extraordinary service permission of autonomous vehicles on highways. A total of five scenarios are selected in consideration of safety priority and real traffic situation. These scenarios are developed based on existing ADAS evaluation and simulation of autonomous vehicle algorithm. Also, Safety evaluation factors are developed based on ISO requirements, other papers and the current traffic regulations. These scenarios are investigated via computer simulation.