• 대한전기학회논문지:전력기술부문A
• /
• 제48권3호
• /
• pp.313-320
• /
• 1999

The Lane-Curvature Method(LCM) presented in this paper is a new local obstacle avoidance method for indoor mobile robots. The method combines Curvature-Velocith Method(CVM) with a new directional method called the Lane Method. The Lane Method divides the environment into lanes taking the information on obstacles and desired heading of the robot into account ; then it chooses the best lane to follow to optimize travel along a desired heading. A local heading is then calculated for entering and following the best lane, and CVM uses this heading to determine the optimal translational and rotational velocity space methods, LCM yields safe collision-free motion as well as smooth motion taking the dynamics of the robot Xavier, show the efficiency of the proposed method.

• Journal of Mechanical Science and Technology
• /
• 제17권11호
• /
• pp.1693-1703
• /
• 2003

This paper presents a new local obstacle avoidance method for indoor mobile robots. The method uses a new directional approach called the Lane Method. The Lane Method is combined with a velocity space method i.e., the Curvature-Velocity Method to form the Lane-Curvature Method (LCM). The Lane Method divides the work area into lanes, and then chooses the best lane to follow to optimize travel along a desired goal heading. A local heading is then calculated for entering and following the best lane, and CVM uses this local heading to determine the optimal translational and rotational velocities, considering some physical limitations and environmental constraint. By combining both the directional and velocity space methods, LCM yields safe collision-free motion as well as smooth motion taking the physical limitations of the robot motion into account.

• 한국자동차공학회논문집
• /
• 제11권1호
• /
• pp.193-200
• /
• 2003

This paper proposes a novel algorithm to recognize the curve of a structured road. The proposed algorithm uses an LCF (Lane Curve Function) obtained by the transformation of a parabolic function defined on world coordinate into image coordinate. Unlike other existing methods, the algorithm needs no transformation between world coordinate and image coordinate owing to the LCF. In order to search for an LCF describing the lane best, the differential comparison between the slope of an assumed LCF and the phase angle of edge pixels in the LROI (Lane Region Of Interest) constructed by the LCF is implemented. As finding the true LCF, the lane curve is determined. The proposed method is proved to be efficient through various kinds of images, providing the reliable curve direction and the valid curvature compared to the real road.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1999년도 제14차 학술회의논문집
• /
• pp.161-164
• /
• 1999

An effective approach to lane detection in driver assistance system (DAS) is proposed, based on the decomposition of lane markings. The properties of the decomposed lane markings are discussed, and analyses on lane curvature are given. The current lane on road is detected quickly, the neighboring lane regions are also extracted for lane planning of the vehicle, and the parameters of lane structure are accurately estimated.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.169-171
• /
• 2004

This paper propose a new detection method of curve lane using Catmull-Rom spline for recognition various shape of the curve lane. To improve the accracy of lane detection, binarization and thinning process are firstly performed on the input image. Next, features on the curve lane such as curvature and orientation are extracted, and the control points of Catmull-Rom spline are detected to recognize the curve lane. Finally, Computer simulation results are given using a natural test image to show the efficiency of the proposed scheme.

• 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.

• 제어로봇시스템학회논문지
• /
• 제21권2호
• /
• pp.121-129
• /
• 2015

This paper presents a multiple vehicle recognition algorithm based on radar and vision sensor fusion for lane change assistance. To determine whether the lane change is possible, it is necessary to recognize not only a primary vehicle which is located in-lane, but also other adjacent vehicles in the left and/or right lanes. With the given sensor configuration, two challenging problems are considered. One is that the guardrail detected by the front radar might be recognized as a left or right vehicle due to its genetic characteristics. This problem can be solved by a guardrail recognition algorithm based on motion and shape attributes. The other problem is that the recognition of rear vehicles in the left or right lanes might be wrong, especially on curved roads due to the low accuracy of the lateral position measured by rear radars, as well as due to a lack of knowledge of road curvature in the backward direction. In order to solve this problem, it is proposed that the road curvature measured by the front vision sensor is used to derive the road curvature toward the rear direction. Finally, the proposed algorithm for multiple vehicle recognition is validated via field test data on real roads.

• 대한전자공학회논문지SP
• /
• 제47권6호
• /
• pp.97-106
• /
• 2010

본 논문에서는 곡선 템플릿 정합 방법을 이용한 곡률 검출 및 차선 검출 알고리즘을 제안한다. 본 논문에서는 영상의 원근감을 제거하기 위하여 입력 영상을 탑뷰(top view) 영상으로 변환한다. 생성된 탑뷰 영상을 이용하여 에지 영상을 생성하는데 검출의 정확도를 높이기 위해 차선 검출에 적합한 에지 검출 방법을 제안한다. 검출된 에지 영상을 이용하여 먼저 직선 차선을 검출한 후 본 논문에서 제안한 곡선 템플릿 정합 방법을 이용하여 가장 적합한 곡선 차선을 결정하여 곡률을 검출한다. 제안된 곡선 템플릿 정합 방법은 법선의 방정식과 원의 방정식만을 이용한 단순한 계산만으로 곡선 차선을 검출하기 때문에 알고리즘이 단순하고 검출 시간이 매우 짧다. 또한 본 논문에서는 이전 프레임에서 검출된 차선 정보를 이용하여 현재 프레임의 차선 정보를 보정하고 보완함으로써 보다 안정적인 차선 검출이 가능하였다. 제안된 알고리즘은 고속도로나 비교적 복잡한 시내 도로, 야간 시 고속도로 등에서 얻은 다양한 환경에서의 영상을 이용하여 실험하였다. 제안된 알고리즘은 초당 70 frame 가량의 영상 처리가 가능하였고 95% 이상의 차선 검출율과 90% 가량의 곡률 검출율을 얻을 수 있었다.

• 한국자동차공학회논문집
• /
• 제7권5호
• /
• pp.178-185
• /
• 1999

Recently, Collision Warning System is developed to improve vehicle safety. This system chiefly uses radar. But the detected vehicle from radar must be decide whether it is the vehicle in the same lane of my vehicle or not. Therefore, Vision System is needed to detect traffic lane. As a preparative step, this study presents the development of algorithm to recognize traffic lane curve direction. That is, the Neural Network that can recognize traffic lane curve direction is constructed by using the information of short distance, middle distance, and decline of traffic lane. For this procedure, the relation between used information and traffic lane curve direction must be analyzed. As the result of application to sampled 2,000 frames, the rate of success is over 90%.t text here.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제26권11호
• /
• pp.1350-1358
• /
• 1999

이 논문에서는 유전밴드 영상신호에 포함되어 있는 지형적 특징을 이용하여 밝기의 변화가 일정하지 않은 유전밴드를 인식하는 방법을 연구하였다. 유전밴드는 동일인을 식별하는데 있어서 지문보다 높은 신뢰성을 가지고 있으므로, 유전밴드 영상에서 유전밴드의 유무와 위치를 자동적으로 검출하는 것은 매우 중요하다. 레인내의 밝기의 변화가 일정한 유전밴드는 미분연산자에 의해 검출할 수 있지만, 밝기의 변화가 일정하지 않은 레인내의 유전밴드는 일반적인 인식방법에 의해서는 검출하기 어렵다. 따라서 유전밴드 영상으로부터 지형적 특징을 추출하고, 이것으로부터 계산한 곡률(curvature)의 크기에 의해 유전밴드를 인식함으로써 레인의 밝기가 변화하는 경우에도 효과적으로 인식하였다.Abstract This paper presents recognition of DNA band using the topographical features of DNA band images. The DNA band provides a more reliable way of identification than fingerprints. Recognition based on differentiation operators can easily detect the DNA band if the brightness of lane in the image is almost uniform. When the brightness of the lane changes gradually, the DNA bands are hard to be recognized. Using the curvature magnitude of the lane computed from topographic features extracted from DNA images, the DNA bands are efficiently recognized in the lane whose brightness changes.