• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.252-253
• /
• 2023

Container terminal automation might offer many potential benefits, such as increased productivity, reduced cost, and improved safety. Autonomous trucks can lead to more efficient container transport. A robust lane detection method is proposed using score-based generative modeling through stochastic differential equations for image-to-image translation. Image processing techniques are combined with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Genetic Algorithm (GA) to ensure lane positioning robustness. The proposed method is validated by a dataset collected from the port terminals under different environmental conditions and tested the robustness of the lane detection method with stochastic noise.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.7 no.4
• /
• pp.28-34
• /
• 1998

This paper presents a new method for local obstacle avoidance of indoor mobile robots. The method combines a directional approach called the lane method and a velocity space approach. The lane method divides working area into lanes and then chooses the best lane to follow for efficient and collision-free movement. Then, the heading direction to enter and follow the best lane is decided, and translational and rotational velocity considering physical limitations of a mobile robot are determined. Since this method combines both the directional and velocity space method, it shows collision-free motion as well as smooth motion taking the dynamic of the robot into account.

• Journal of Advanced Navigation Technology
• /
• v.11 no.4
• /
• pp.359-370
• /
• 2007

Lane tracking and obstacle avoidance are considered two of the key technologies on an unmanned ground vehicle system. In this paper, we propose a method of lane tracking and obstacle avoidance, which can be expressed as vehicle control, modeling, and sensor experiments. First, obstacle avoidance consists of two parts: a longitudinal control system for acceleration and deceleration and a lateral control system for steering control. Each system is used for unmanned ground vehicle control, which notes the vehicle's location, recognizes obstacles surrounding it, and makes a decision how fast to proceed according to circumstances. During the operation, the control strategy of the vehicle can detect obstacle and perform obstacle avoidance on the road, which involves vehicle velocity. Second, we explain a method of lane tracking by means of a vision system, which consists of two parts: First, vehicle control is included in the road model through lateral and longitudinal control. Second, the image processing method deals with the lane tracking method, the image processing algorithm, and the filtering method. Finally, in this paper, we propose a method for vehicle control, modeling, lane tracking, and obstacle avoidance, which are confirmed through vehicles tests.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.6
• /
• pp.619-623
• /
• 2008

A lane detection system is one of the major components of intelligent vehicle systems. Difficulties in lane detection mainly come from not only various weather conditions but also a variety of special environment. This paper describes a simple and stable method for the broken lane tracking in various environments. Probabilistic Hough Transform (PHT) and the Least-square method (LSM) are used to track and correct the lane orientation. For the efficiency of the proposed method, two regions of interest (ROIs) are placed in the lower part of each image, where lane marking areas usually appear with less intervention in our system view. By testing in both a set of static images and video sequences, the experiments showed that the proposed approach yielded robust and reliable results.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.11 no.1
• /
• 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.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.6
• /
• pp.649-656
• /
• 2014

In this paper, we address the problem of center lane detection algorithm for autonomous driving. Color information for center lane is gathered by analyzing a row line color distribution of road in front of a vehicle. The candidate pixels for center lane are extracted from the histogram of road colors. Morphological filtering and clustering process are applied to the candidate pixels to extract the exact center lane. We predict a expected area of center lane and search only the regions in subsequent frames, that reduces the time required for center lane detection.

• Journal of Advanced Navigation Technology
• /
• v.15 no.3
• /
• pp.432-440
• /
• 2011

This paper focus on lane recognition performance test using a road lane constraint with transport infrastructure information. The constraint is determined through the relation of the drive direction and vehicle position. The road lane constraint sets large limit for first and last lane. To analyze the performance of the proposed method, simulations are carried out. The results show that the lane recognition performance using a constraint is improved 40% at four-lane, 25% at six-lane, 15% at eight-lane.

• Journal of Korea Multimedia Society
• /
• v.3 no.5
• /
• pp.445-453
• /
• 2000

In this paper we propose the method which extracts lane using the grouped block snake algorithm. In the proposed algorithm, input image is divided into $8\times{8}$ blocks and then noise-included blocks are removed by a probability-based method. And also, we use hough transform to separate lane from the background image and suggest a grouped block snake method to detect road lane blocks. The proposed method reduces computational complexity and removes the noise in a more effective way compared to the pixel-based snake method.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.6
• /
• pp.49-58
• /
• 2014

This paper proposes a new assessment and reliability validation method of Lane Departure Assistance System based on DGPS-GIS by measuring lanes with camera vision. Assessment of lane departure is performed with yaw speed measurement and determination method for false alarm of ISO 17361 and performance validation is executed after generating departure warning boundary line by considering deviation error of LDAS using DGPS. Distance between the wheel and the lane is obtained through line abstraction using Hough transformation of the lane image with camera vision. Evaluation validation is obtained by comparing this value with the distance obtained with LDAS. The experimental result shows that the error of the extracted distance of the LDAS is within 5 cm. Also it proves performance of LDAS based on DGPS-GIS and assures effectiveness of the proposed validation method for system reliability using camera vision.

• The Journal of Korea Robotics Society
• /
• v.11 no.3
• /
• 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.