• 한국정보통신학회논문지
• /
• 제16권12호
• /
• pp.2755-2761
• /
• 2012

본 논문에서는 Eccentricity를 이용한 차선 검출 알고리듬을 제안한다. 차선 검출 알고리듬은 자동차 운전자의 안정성을 증가시키는 차선 이탈 경보 시스템 등에 활용될 수 있다. 차선 검출율을 개선하기 위하여 그래프 이론에서 소개되는 Eccentricity를 정의하고, 이를 차선 검출 알고리듬에 이용하여 Eccentricity를 계산하였다. 직선도로인 경우 Eccentricity는 1이고 1차 함수로 구현이 가능하다. 그래서 시간 복잡도와 공간 복잡도를 개선하였고, 아울러 기존의 방법들보다 차선 검출율이 향상됨을 확인하였다.

• 대한교통학회지
• /
• 제1권1호
• /
• pp.56-63
• /
• 1983

Intersection control has dual-purposes; increasing capacity and reducing delay. The primary concern of efficient intersection control under oversaturated condition as in Korea is to increase capacity. Prevailing intersection operation technique permits thru traffic to utilize left turn lane, because the intersection without left turn pocket has left turn signal interval. In this situation, it seems not to be valid to calculate capacity, delay, and signal timings by conventional methods. By critical lane technique, capacity increases as cycle length increases. However, when thru traffic utilize LT lane, the capacity varies according to LT volume, LT interval as well as cycle length, which implies that specific cycle length and LT interval exist to maximize capacity for given LT volume. The study is designed is designed to calculate utilization factors of LT lane for thru traffic and capacities, and identify signal timings to yield maximum capacity. The experimental design involved has 3 variables; 1)LT volumes at each approach(20-300 vph), 2)cycle lengths (60-220 sec), and 3)LT intervals(2.6-42 sec) for one scenario of isolated intersection crossing two 6-lanes streets. For LT volume of 50-150 vph, capacity calculated by using the utilization factor is about 25% higher than that by critical lane method. The range of optimum cycle length to yield maximum capapcity for LT volume less than 120 vph is 140-180 sec, and increases as LT volume increases. The optimum LT interval to yield maximum capacity is longer than the intrval necessary to accommodate LT volume at saturation flow rate.

• 대한임베디드공학회논문지
• /
• 제11권3호
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.179-186
• /
• 2015

In this paper, a novel lateral control system is proposed for the purpose of improving lane keeping performance which is independent from GPS signals. Lane keeping is a key function for the realization of unmanned driving systems. In order to obtain this objective, a vision sensor based real-time lane detection scheme is developed. Furthermore, we employ a data fusion along with a real-time steering angle of the test vehicle to improve its lane keeping performance. The fused direction data can be obtained by an IMU sensor and vision sensor. The performance of the proposed system was verified by computer simulations along with field tests using MOHAVE, a commercial vehicle from Kia Motors of Korea.

• 로봇학회논문지
• /
• 제11권3호
• /
• pp.172-182
• /
• 2016

Lane-level vehicle positioning is an important task for enhancing the accuracy of in-vehicle navigation systems and the safety of autonomous vehicles. GPS (Global Positioning System) and DGPS (Differential GPS) are generally used in navigation service systems, which however only provide an accuracy level up to 2~3 m. In this paper, we propose a 3D vision based lane-level positioning technique which can provides accurate vehicle position. The proposed method determines the current driving lane of a vehicle by tracking the 3D position of traffic signs which stand at the side of the road. Using a stereo camera, the 3D tracking paths of traffic signs are computed and their projections to the 2D road plane are used to determine the distance from the vehicle to the signs. Several experiments are performed to analyze the feasibility of the proposed method in many real roads. According to the experimental results, the proposed method can achieve 90.9% accuracy in lane-level positioning.

• 한국자동차공학회논문집
• /
• 제17권3호
• /
• pp.54-61
• /
• 2009

Lane keeping assistant system (LKAS) could save thousands of lives each year by maintaining lane position and is regarded as a promising active safety system. The LKAS is expected to reduce the driver workload and to assist the driver during driving. This paper proposes a model based predictive controller for the LKAS which requires cooperative driving between the driver and the assistance system. A Hardware-In-the-Loop-Simulator (HILS) is constructed for its evaluation and includes Carsim, Matlab Simulink and a lane detection algorithm. The single camera is mounted with the HILS to acquire the monitor images and to detect the lane markers. The simulation is conducted to validate the LKAS control performance in various road scenario.

• 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.

• 전자공학회논문지
• /
• 제50권5호
• /
• pp.224-230
• /
• 2013

운전자 보조 시스템에서 차선 경계 검출은 매우 중요하다. 본 연구는 악조건인 환경에서 차선 경계를 검출하기 위한 강건한 방법을 제안한다. 첫 번째로 원래의 image에서 iVMD(improve Vertical Mean Distribution) Method를 이용하여 수평선을 검출하고, 수평선 하위영역 image를 결정하며, 두 번째로 Canny edge detector를 사용하여 하위 영역에서 차선 표시를 추출한다. 마지막으로, RANSAC algorithm을 이용하여 각각에 맞는 line model을 적용하기 전에, k-means clustering algorithm을 이용하여 오른쪽 왼쪽 차선을 분류 한다. 제안된 알고리즘은 변종조명, 갈라진 도로, 복잡한 차선 표시, 교통신호에 관하여 상당히 정확한 차선 검출 기능을 나타낸다. 실험결과는 제안된 방법이 악조건인 환경하에서 실시간으로 효율적인 요구 사항을 충족함을 보여준다.

• 제어로봇시스템학회논문지
• /
• 제21권7호
• /
• pp.621-626
• /
• 2015

This paper presents a camera calibration method in order to estimate the lane detection and inter-vehicle distance estimation system for an automotive safety driving system. In order to implement the lane detection and vision-based inter-vehicle distance estimation to the embedded navigations or black box systems, it is necessary to consider the computation time and algorithm complexity. The process of camera calibration estimates the horizon, the position of the car's hood and the lane width for extraction of region of interest (ROI) from input image sequences. The precision of the calibration method is very important to the lane detection and inter-vehicle distance estimation. The proposed calibration method consists of three main steps: 1) horizon area determination; 2) estimation of the car's hood area; and 3) estimation of initial lane width. Various experimental results show the effectiveness of the proposed method.

• 센서학회지
• /
• 제28권3호
• /
• pp.164-170
• /
• 2019

In this paper, a lane detection and tracking algorithm based on vision sensors and employing a robust filter for inner edge detection is proposed for developing a lane departure warning system (LDWS). The lateral offset value was precisely calculated by applying the proposed filter for inner edge detection in the region of interest. The proposed algorithm was subsequently compared with an existing algorithm having lateral offset-based warning alarm occurrence time, and an average error of approximately 15ms was observed. Tests were also conducted to verify whether a warning alarm is generated when a driver departs from a lane, and an average accuracy of approximately 94% was observed. Additionally, the proposed LDWS was implemented as an embedded system, mounted on a test vehicle, and was made to travel for approximately 100km for obtaining experimental results. Obtained results indicate that the average lane detection rates at day time and night time are approximately 97% and 96%, respectively. Furthermore, the processing time of the embedded system is found to be approximately 12fps.