• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.158-164
• /
• 2015

Lane detection is one of the key parts among autonomous vehicle technologies because lane keeping and path planning are based on lane detection. Camera is used for lane detection but there are severe limitations such as narrow field of view and effect of illumination. On the other hands, Lidar sensor has the merits of having large field of view and being little influenced by illumination because it uses intensity information. Existing researches that use methods such as Hough transform, histogram hardly handle multiple lanes in the co-occuring situation of lanes and road marking. In this paper, we propose a method based on RANSAC and regularization which provides a stable and precise detection result in the co-occuring situation of lanes and road marking in highway scenarios. This is performed by precise lane point extraction using circular model RANSAC and regularization aided least square fitting. Through quantitative evaluation, we verify that the proposed algorithm is capable of multi lane detection with high accuracy in real-time on our own acquired road data.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.11
• /
• pp.29-39
• /
• 2019

As mobile robot applications increase in real life, the need of low cost autonomous driving are gradually increasing. We propose a novel vision-based real-time lane detection and tracking system that supports autonomous driving of mobile robots in constrained tracks which are designed considering indoor driving conditions of mobile robots. Considering the processing of lanes with various shapes and the pre-adjustment of operation parameters, the system structure with multi-operation modes are designed. In parameter tuning mode, thresholds of the color filter is dynamically adjusted based on the geometric property of the lane thickness. And in the unstable input mode of curved tracks and the stable input mode of straight tracks, lane feature pixels are adaptively extracted based on the geometric and temporal characteristics of the lanes and the lane model is fitted using the least-squared method. The track centerline is calculated using lane models and the motion model is simplified and tracked by a linear Kalman filter. In the driving experiments, it was confirmed that even in low-performance robot configurations, real-time processing produces the accurate autonomous driving in the constrained track.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.5
• /
• pp.9-15
• /
• 2023

In this paper, we propose a method predicting the speed of each lane from the link speed using a neural network. We took three measures for configuring learning data to increase prediction accuracy. The first one is to expand the spatial range of the data source by including 14 links connected to the beginning and end points of the link. We also increased the time interval from 07:00 to 22:00 and included the data generation time in the feature data. Finally, we marked weekdays and holidays. Results of experiments showed that the speed error was reduced by 21.9% from 6.4 km/h to 5.0 km/h for straight lane, by 12.9% from 8.5 km/h to 7.4 km/h for right turns, and by 5.7% from 8.7 km/h to 8.2 km/h for left-turns. As a secondary result, we confirmed that the prediction accuracy of each lane was high for city roads when the traffic flow was congested. The feature of the proposed method is that it predicts traffic conditions for each lane improving the accuracy of prediction.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.5
• /
• pp.463-470
• /
• 2015

When a camera installed on a vehicle is used, estimation of the camera pose including tilt, roll, and pan angle with respect to the world coordinate system is important to associate camera coordinates with world coordinates. Previous approaches using huge calibration patterns have the disadvantage that the calibration patterns are costly to make and install. And, previous approaches exploiting multiple vanishing points detected in a single image are not suitable for automotive applications as a scene where multiple vanishing points can be captured by a front camera is hard to find in our daily environment. This paper proposes a camera pose estimation method. It collects multiple images of lane markings while changing the horizontal angle with respect to the markings. One vanishing point, the cross point of the left and right lane marking, is detected in each image, and vanishing line is estimated based on the detected vanishing points. Finally, camera pose is estimated from the vanishing line. The proposed method is based on the fact that planar motion does not change the vanishing line of the plane and the normal vector of the plane can be estimated by the vanishing line. Experiments with large and small tilt and roll angle show that the proposed method outputs accurate estimation results respectively. It is verified by checking the lane markings are up right in the bird's eye view image when the pan angle is compensated.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.147-153
• /
• 2020

Conventional lane detection algorithms have problems in that the detection rate is lowered in road environments having a large change in curvature and illumination. The probabilistic Hough transform method has low lane detection rate since it exploits edges and restrictive angles. On the other hand, the method using a sliding window can detect a curved lane as the lane is detected by dividing the image into windows. However, the detection rate of this method is affected by road slopes because it uses affine transformation. In order to detect lanes robustly and avoid obstacles, we propose driving assist system using semantic segmentation based on deep learning. The architecture for segmentation is SegNet based on VGG-16. The semantic image segmentation feature can be used to calculate safety space and predict collisions so that we control a vehicle using adaptive-MPC to avoid objects and keep lanes. Simulation results with CARLA show that the proposed algorithm detects lanes robustly and avoids unknown obstacles in front of vehicle.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.97-100
• /
• 1996

In this paper, we describe an algorithm which estimate road following direction using the vanishing point property and obstacle detection. This method of detecting the lane markers in a set of continuous lane highway images using linear approximation is presented. This algorithm is designed for accurate and robust extraction of this data as well as high processing speed. Also, this algorithm reckon distance and chase about an obstacle. It include four algorithms which are lane prediction, lane extraction, road following parameter estimation and obstacle detection algorithm. High accuracy was proven by quantitative evaluation using simulated images. Both robustness and the practicality of real time video rate processing were then confirmed through experiment using VTR real road images.

• Journal of Korean Society of Transportation
• /
• v.7 no.2
• /
• pp.89-111
• /
• 1989

This study concentrates on a basic investigation research related to some of parameters to be used for the analysis of capacity and the level of service for signalized intersections. The parameters to be studied are ideal saturation flow rate, large vehicle's passenger car equivalent(PCE) ane the lane utilization factors of through and left turn vehicles. The field data were collected at six intersections in Seoul using video cameras so as to reflect conditions in urban areas. In this study discharge headway based on a rear bumper of each vehicle was used and all the parameters were estimated using a regression technique. The findings of this research are as follows : 1. The saturation headway and saturation flow rate on a single lane with the lane width of 3.1m are 1.652 seconds and 2,180 pcphgpl. It was found that the frist 5 vehicles in the queue experience some start-up lost time. 2. It was confirmed that the new method adopted for the estimate of large vehicle's PCE gives larger PCE values than those derived from the method commonly used. 3. For the estimate of lane utilization factors of through and left turn vehicles, a relationship was established and the corresponding formulas were developed.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.139-146
• /
• 2021

Ahead of the commercialization of autonomous vehicles, it's application should be considered into the current transportation infrastructure. Under limited traffic circumstances, effective set of lane change rules alone could bring benefits to the autonomous driving system. In this study, a cooperative movement (local platooning) plan with limited vehicles associated as pocket driving, aiming at effective movement between vehicles in urban environment was proposed. Under congested roadway condition, the gaussian gap between vehicles was introduced to secure gap acceptance for safe lane change maneuver. Proposed lane change method showed 86.6% delay reduction along with traffic volume improvement. This result could be considered as a crucial factor in designing a next-generation roadway infrastructure with autonomous driving.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.257-257
• /
• 2000

The objective of this research is to monitor and control the vehicle motion in order to remove out the existing safety risk based upon the human-machine cooperative vehicle control. A predictive control method is proposed to control the steering wheel of the vehicle to keep the lane. Desired angle of the steering wheel to control the vehicle motion could be calculated based upon vehicle dynamics, current and estimated pose of the vehicle every sample steps. 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, where not only the state variables, but also the corresponding uncertainties were propagated in forward and backward direction in such a way to satisfy the given constraint condition, maintain consistency, reduce the uncertainties, and guarantee robustness. A series of experiments was conducted to evaluate the control performance, in which a car Like robot was utilized to quit unwanted safety problem. As the results, the robot was keeping very well a given lane with arbitrary shape at moderate speed.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.4
• /
• pp.16-24
• /
• 2012

This paper proposes a method utilizing Differential Global Position System (DGPS) with Real-Time Kinematic (RTK) and pre-built Geo-graphic Information System (GIS) to detect lane departure of a vehicle. The position of a vehicle measured by DGPS with RTK has 18 cm-level accuracy. The preconditioned GIS data giving accurate position information of the traffic lanes is used to set up coordinate system and to enable fast calculation of the relative position of the vehicle within the traffic lanes. This relative position can be used for safe driving by preventing the vehicle from departing lane carelessly. The proposed system can be a key component in functions such as vehicle guidance, driver alert and assistance, and the smart highway that eventually enables autonomous driving supporting system. Experimental results show the ability of the system to meet the accuracy and robustness to detect lane departure of a vehicle at high speed.