• 제어로봇시스템학회논문지
• /
• 제21권2호
• /
• pp.130-136
• /
• 2015

In this paper, we propose a robust curved lane marking detection method. Several lane detection methods have been proposed, however most of them have considered only straight lanes. Compared to the number of straight lane detection researches, less number of curved-lane detection researches has been investigated. This paper proposes a new curved lane detection and tracking method which is robust to various illumination conditions. First, the proposed methods detect straight lanes using a robust road feature image. Using the geometric relation between a vehicle camera and the road plane, several circle models are generated, which are later projected as curved lane models on the camera images. On the top of the detected straight lanes, the curved lane models are superimposed to match with the road feature image. Then, each curve model is voted based on the distribution of road features. Finally, the curve model with highest votes is selected as the true curve model. The performance and efficiency of the proposed algorithm are shown in experimental results.

• 한국도로학회논문집
• /
• 제16권1호
• /
• pp.41-48
• /
• 2014

PURPOSES : The lane width of the domestic highway is 3.5 ~ 3.6m and it has been designed nationwide. However, the distribution of the average vehicle widths, rearview mirror widths and lateral wheel paths by region appear different. Then, lane spare widths may differ by region followingly. Thus, the flexible design of freeway lane widths is required. METHODS : The methodologies of this paper are as follows. First, vehicle widths rearview mirror widths lateral wheel paths of vehicles driven four national expressways were measured. Second, lane spare widths by vehicle widths were calculated. Third, lane spare widths reflecting rearview mirror widths were calculated by using interval estimation. Additionally, lane spare widths reflecting vehicles lateral wheel paths were calculated. RESULTS : The results of this paper are as follows. First, lane spare widths by vehicle widths ranges 0.83 to 0.95m. Second, lane spare widths reflecting rearview mirror widths ranges 0.518 to 0.747m at the confidence interval 95%. Third, lane spare widths reflecting vehicles' lateral wheel paths ranges -0.022 to 0.322m at the curved sections and the confidence interval 95%. CONCLUSIONS : It may be concluded that the present lane spare widths are relatively narrow at the curved section. Thus, there is a need to consider expanded lane widths at the curved sections. Additionally, there is a need to consider flexible design of lane widths by various conditions.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.34-36
• /
• 2009

This paper proposes an effective lane detection algorithm using hugh transform and lane model. The proposed lane detection algorithm includes two major components, i.e., lane marks segmentation and an exact lane extraction using a novel postprocessing technique. The first step is to segment lane marks from background images using HSV color model. Then, a novel postprocessing is used to detect an exact lane using Hugh transform and lane models(linear and curved lane models). The postprocessing consists of three parts, i.e, thinning process, Hugh Transform and filtering process. We divide input image into three regions of interests(ROIs). Based on lane curve function(LCF), we can detect an exact lane from various extracted lane lines. The lane models(linear and curved lane mode]) are used in order to judge whether each lane segment is fit or not in each ROIs. Experimental results show that the proposed scheme is very effective in lane detection.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.107.2-107
• /
• 2002

The objective of this study is to propose a lane changing and keeping method on a curved road for an automatic guidance of a vehicle. It is well known that the speed control of a vehicle in a curved road is essential in terms of vehicle stability and passenger safety because centrifugal force makes a vehicle to be on out of lane. And it is also natural to avoid the collision with other cars or obstructions with keeping the stability and drivability. The vehicle pose and the road curvature were calculated by geometrically fusing sensor data from camera image, tachometer and steering wheel encoder though the Perception Net in which not only the state variables, but also the corresponding uncer...

• 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.

• 한국도로학회논문집
• /
• 제13권2호
• /
• pp.57-65
• /
• 2011

본 연구에서는 도시부도로의 곡선구간에서 주행차량의 횡방향 이격량을 분석하여 차량 주행에 필요한 최소 소요차로폭을 산정하였으며 본 연구결과와 선행연구에서 제시된 직선구간에서의 최소 소요차로폭을 비교 분석하였다. 이를 바탕으로 도로의 선형과 차종에 따라 곡선구간에서의 최소 소요차로폭을 제시하였다. 조사대상 곡선구간 도로의 차로폭은 2.79m~3.40m이다. 주행차량의 횡방향 이격량의 분포 및 조사대상 차량의 85%를 기준으로 누적분포를 분석하였다. 분석결과 곡선구간에서의 최소 소요차로폭이 소형차량의 경우 2.31m~2.58m, 대형차량의 경우 2.80m~3.27m로 산정되었다. 본 연구결과는 녹색교통 도입을 위한 공간, 도로공사 중, 소형차 전용도로의 건설 등에 활용될 수 있을 것이다. 또한 설계자의 목적에 따라 유연한 차로폭 설계기준의 적용에 필요한 기초적인 연구로 활용될 수 있을 것으로 기대된다.

• 한국정보전자통신기술학회논문지
• /
• 제10권4호
• /
• pp.304-310
• /
• 2017

본 논문은 자율주행자동차가 곡선 주행 차로를 따라 주행 경로를 인지하고 경로 제어가 가능하도록 하기 위한 IPM 기반의 차선 검출기 구조에 대해 제안하고 RTL (Register Transfer Level) 기반의 회로 구현 결과에 대해 설명한다. 제안한 회로 구조는 곡률이 심한 차선에 대해 높은 정확도를 보장하기 위해 역투영 정합 영상을 Near/Far 영역으로 구분하여 허프 변환과 차선의 후보 영역 검출 연산을 적용한다. 자율주행자동차의 경우 다양한 알고리즘을 탑재해야 하므로 임베디드 시스템에서 차선 인식기의 시스템 자원 사용량을 줄이기 위해 차선 인식에 사용하는 영상 데이터 및 각종 파라미터 데이터에 대해 메모리 접근 회수를 최소화하는 방법을 제안하였다. 제안한 회로는 Xilinx Zynq XC7Z020에서 LUT 16%, FF 5.9%, BRAM 29%의 FPGA 자원 점유율을 보였으며 100MHz 클럭에서 Full-HD ($1920{\times}1080$) 영상을 초당 42장 처리 가능한 성능을 갖고 약 96% 차선 인식률을 보인다.

• 한국ITS학회 논문지
• /
• 제15권4호
• /
• pp.81-90
• /
• 2016

자율주행 차량은 변화하는 도로환경에 스스로 대응 가능하여야 하여, 인간 운전자 수준의 도로환경 인지성능을 확보하여야 한다. 자율주행 차량의 센서 중 영상센서는 주행방향 결정 및 차로이탈 방지 등 조향제어 수행을 위하여 차선인식 기능을 수행한다. 현재 제시된 영상센서의 차선인식 성능기준은 ADAS(Advanced Driver Assistance System)과 관련된 '운전자 보조' 관점의 성능기준으로서, 자율주행 차량의 '주체적 인지'를 위한 성능조건과 상이할 것으로 판단된다. 본 연구에서는 자율주행 시 차선인식이 비정상적으로 지속되어, 직선구간에서 곡선구간으로 진입하는 차량이 조향실패에 따라 차로를 이탈하는 상황을 가정하였다. 차량 이동궤적을 기반하여 차로이탈 상황을 모형화하고, 차로이탈 허용 수준에 따른 자율주행 차량 영상센서 성능수준을 제시하였다. 분석 결과 승용차 조건에서 차선인식 기능이 1초 이상 연속적인 오작동을 일으킨다면 차로이탈에 의한 위험한 상황에 놓일 수 있으며, 자율주행 차량을 위하여 현재 ADAS 영상센서 성능평가 방법에서의 차로이탈조건보다 심각한 차로이탈상황을 고려한 영상센서 성능평가 방안이 필요할 것으로 판단된다.

• International Journal of Automotive Technology
• /
• 제5권2호
• /
• pp.69-76
• /
• 2004

This paper evaluates the effectiveness of four-wheel-steering system from the viewpoint of lane-keeping control theory. In this paper, the lane-keeping control system is designed on the basis of the four-wheel-steering automobiles whose desired steering response is realized with the application of model matching control. Two types of desired steering responses are presented in this paper. One is zero-sideslip response, the other one is steering response which realizes zero-phase-delay of lateral acceleration. Using simplified linear two degree-of-freedom bicycle model, simulation study and theoretical analysis are conducted to evaluate the lane-keeping control performance of active four-wheel-steering automobiles which have different desired steering responses. Finally, the evaluation is conducted on straight and curved roadway tracking maneuvers.

• 반도체디스플레이기술학회지
• /
• 제15권1호
• /
• pp.27-32
• /
• 2016

A new lane detection algorithm is proposed for the analysis of DNA fingerprints from a polymerase chain reaction (PCR) gel electrophoresis image. Although several research results have been previously reported, it is still challenging to extract lanes precisely from images having abrupt background brightness difference and bent lanes. We propose an edge based algorithm for calculating the average lane width and lane cycle. Our method adopts sub-pixel algorithm for extracting rising-edges and falling edges precisely and estimates the lane width and cycle by using k-means clustering algorithm. To handle the curved lanes, we partition the gel image into small portions, and track the lane centers in each partitioned image. 32 gel images including 534 lanes are used to evaluate the performance of our method. Experimental results show that our method is robust to images having background difference and bent lanes without any preprocessing.