• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.141-144
• /
• 1996

This study deals with the problem of the recognition of the preceding vehicles by image processing. The purpose of this study is the development of the equipment to prevent a collision with preceding vehicles during driving the vehicle. In order to decrease the processing time and increase reliability, at first, the traffic lane is extracted. It is determined by detecting road edges and calculating their tangent. After the traffic lane is gotten, the position of the vehicle is searched inside the lane. The features used to detect the vehicles in the algorithm are shadow of the vehicle, vertical edges, horizontal edges, and symmetrical segment. The preceding vehicles are extracted successfully by this method.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.6
• /
• pp.74-80
• /
• 2009

Path tracking of unmanned vehicle is a basis of autonomous driving and navigation. For the path tracking, it is very important to find the exact position of a vehicle. GPS is used to get the position of vehicle and a direction sensor and a velocity sensor is used to compensate the position error of GPS. To detect path lines in a road image, the bird's eye view transform is employed, which makes it easy to design a lateral control algorithm simply than from the perspective view of image. Because the driving speed of vehicle should be decreased at a curved lane and crossroads, so we suggest the speed control algorithm used GPS and image data. The control algorithm is simulated and experimented from the basis of expert driver's knowledge data. In the experiments, the results show that bird's eye view transform are good for the steering control and a speed control algorithm also shows a stability in real driving.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.6
• /
• pp.194-207
• /
• 2000

In this paper, we suggest a vision-based lane change control system, which can be applied on the straight road, without additional sensors such as a yaw rate sensor and a lateral accelerometer. In order to reduce the image processing time, we predict a reference line position during lane change using the lateral dynamics and the inverse perspective mapping. The sliding mode control algorithm with a boundary layer is adopted to overcome variations of parameters that significantly affects a vehicle`s lateral dynamics and to reduce chattering phenomenon. However, applying the sliding mode control to the system with a long sampling interval, the stability of a control system may seriously be affected by the sampling interval. Therefore, in this paper, a look ahead offset has been used instead of a lateral offset to reduce the effect of the long sampling interval due to the image processing time. The control algorithm is developed to follow the desired trajectory designed in advance. In the design of the desired trajectory, we take account of the constraints of lateral acceleration and lateral jerk for ride comfort. The performance of the suggested control system is evaluated in simulations as well as field tests.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.6
• /
• pp.594-600
• /
• 2012

Accurate localization is very important to stable navigation of a mobile robot. This paper deals with local localization of a mobile robot especially for outdoor environments. The GPS information is the easiest way to obtain the outdoor position information. However, the GPS accuracy can be severely affected by environmental conditions. To deal with this problem, the GPS and wheel odometry can be combined using an EKF (Extended Kalman Filter). However, this is not enough for safe navigation of a mobile robot in outdoor environments. This paper proposes a novel method using lane features from the road image. The pose data of a mobile robot can be corrected by analyzing the detected lane features. This can improve the accuracy of the localization process substantially.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.705-717
• /
• 2001

In this paper, we propose a rapid lane detection method to extract a preceding vehicle from sequential images captured by a single monocular CCD camera. We detect positions of lanes for an individual image within the limited area that would not be hidden and thereby compute the slopes of the detected lanes. Then we find a search area where vehicles would exist and extract the position of the preceding vehicle within the area with edge component by applying a structured method. To verify the effects of the proposed method, we capture the road images with a notebook PC and a CCD camera for PC and present the results such as processing time for lane detection, accuracy and vehicles detection against the images.

• Journal of Korea Multimedia Society
• /
• v.5 no.2
• /
• pp.176-190
• /
• 2002

According as vehicles increases, system such as Advanced Drivers Assistance System(ADAS ) to inform forward situation to driver is required. In this paper, we proposes method to detect forward vehicles and lane from sequential color images by basis process to inform forward situation to driver. We detect a front vehicle using that shadow area exists on part under vehicles and that road area occupies many parts even if road traffic is confused. We detect lane information using that lane part is white order by reverse characteristic of shadow area. This method shows good result in case road is confused or there is direction indication to road. HSV color space is selected for color modeling. This method uses saturation component and value component in HSV color model to detect vehicles and lane. It uses statistics features of HSV component and position to know whether detected vehicles area is vehicles such as vehicles previous frame. To verify the effects of the proposed method, we capture the road images with notebook and CCD camera for PC and Present the results such as processing time, accuracy and vehicles detection against the images.

• Journal of Auto-vehicle Safety Association
• /
• v.10 no.4
• /
• pp.33-39
• /
• 2018

Recently, the automobile industry has developed ADAS (Advanced Driver Assistance System) to prevent traffic accidents and reduce driver's driving burden. Among the ADAS, the LKAS (Lane Keeping Assistance System) is a support system for the convenience and safety of the driver, and the main function is to maintain the driving lane of the vehicle. LKAS is a system that uses radar sensor and camera sensor to collect information about the position of the vehicle in the lane and to support keeping the lane through control if necessary. In many countries, LKAS has already been commercialized and the convenience and safety of drivers have been improved. The international LKAS evaluation test procedure is being developed and discussed by standardization committees such as the ISO (International Organization for Standardization) and the Euro NCAP (New Car Assessment Program). In Korean, the LKAS test method is specified in the KNCAP (Korean New Car Assessment Program), but the evaluation method is not defined. Therefore, the LKAS test procedure that meets international standards and is suitable for domestic road environment is necessary. In this paper, development of LKAS test evaluation scenarios that meets international standards and considering domestic road environment, and the formula that can evaluate the result value after control as the relative distance of lane and the front wheel are suggested. And a comparative analysis was conducted to verify the validity of the suggested scenario and formula. The test evaluation was conducted using the vehicle equipped with the LKAS.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.6
• /
• pp.786-792
• /
• 2010

This paper presents a real-time lane detection method which can accurately find the lane-mark boundaries in complex road environment. Unlike many existing methods that pay much attention on the post-processing stage to fit lane-mark position among a great deal of outliers, the proposed method aims at removing those outliers as much as possible at feature extraction stage, so that the searching space at post-processing stage can be greatly reduced. To achieve this goal, a grid-based morphology operation is firstly used to generate the regions of interest (ROI) dynamically, in which a directional edge-linking algorithm with directional edge-gap closing is proposed to link edge-pixels into edge-links which lie in the valid directions, these directional edge-links are then grouped into pairs by checking the valid lane-mark width at certain height of the image. Finally, lane-mark colors are checked inside edge-link pairs in the YUV color space, and lane-mark types are estimated employing a Bayesian probability model. Experimental results show that the proposed method is effective in identifying lane-mark edges among heavy clutter edges in complex road environment, and the whole algorithm can achieve an accuracy rate around 92% at an average speed of 10ms/frame at the image size of $320{\times}240$.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.8
• /
• pp.2942-2950
• /
• 2010

Car black box helps to investigate the cause of accident by recording time, position and videos as well as shock information. In addition, the car black box need a function to support safe driving for preventing accident. The representative driving support function is a lane departure warning. In order to implement the function, it is necessary to carry out the image processing to detect the lane first. The image processing algorithm requires computational burden to handle so much data and complicated structure of algorithm. This paper describes the efficient image processing algorithm with relatively low amount of computation for car black box embedded platform to detect lanes from the real-time lane image.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.2
• /
• pp.235-240
• /
• 2015

Active Safety system is requested on the market of the medium and heavy duty commercial vehicle over 4.5ton beside the market of passenger car with advancement of the digital equipment proportionally. Unlike the passenger car, the mounting position of camera in case of the medium and heavy duty commercial vehicle is relatively high, it is disadvantaged conditions for lane recognition in contradiction to passenger car. In this work, we show the method of lane recognition through the Sobel edge, based on the spatial domain processing, Hough transform and color conversion correction. Also we suggest the low error method of front vehicles recognition in order to reduce the detection error through Haar-like, Adaboost, SVM and Template matching, etc., which are the object recognition methods by frontal camera vision. It is verified that the reliability over 98% on lane recognition is obtained through the vehicle test.