• International Journal of Automotive Technology
• /
• v.7 no.2
• /
• pp.227-235
• /
• 2006

In this paper a robust image processing method with modified Otsu algorithm to recognize the road lane for a real-time controlled autonomous vehicle is presented. The main objective of a proposed method is to drive an autonomous vehicle safely irrespective of road image qualities. For the steering of real-time controlled autonomous vehicle, a detection area is predefined by lane segment, with previously obtained frame data, and the edges are detected on the basis of a lane width. For stable as well as psudo-robust autonomous driving with "good", "shady" or even "bad" road profiles, the variable threshold with modified Otsu algorithm in the image histogram, is utilized to obtain a binary image from each frame. Also Hough transform is utilized to extract the lane segment. Whether the image is "good", "shady" or "bad", always robust and reliable edges are obtained from the algorithms applied in this paper in a real-time basis. For verifying the adaptability of the proposed algorithm, a miniature vehicle with a camera is constructed and tested with various road conditions. Also, various highway road images are analyzed with proposed algorithm to prove its usefulness.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.04a
• /
• pp.177-182
• /
• 2004

This study presents the application of aerial photographs and KOMPSAT-1 Electro-Optical Camera(EOC) imagery in detecting the change of an urban area that has been rapidly growing. For the study, we used multi-time images which were acquired by two different sensors. For all of the images, the coordinate reference system and scale were first made identical through the 1st and 2nd geometric corrections and then image resampling were carried out to spatial resolution of 7m to detect changes under the same conditions. The Image Differencing was employed as a change detection technique. It was confirmed to be able to detect the changes of terrestrial surface like building, structure and road features from aerial photos and KOMPSAT EOC images with single band. The changes could be detected to some extent with the images acquired from different kinds of sensors as well as the same kinds of sensors.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.11-13
• /
• 2008

This study proposes the method to use existing digital maps as one of the technologies to exclude individual differences that occur in the process of manually determining GCP for the geometric correction of KOMPSAT images and applying it to the images and to automate the generation of ortho-images. It is known that, in case high-resolution satellite images are corrected geometrically by using RPC, first order polynomials are generally applied as the correction formula in order to obtain good results. In this study, we matched the corresponding objects between 1:25,000 digital map and a KOMPSAT image to obtain the coefficients of the zero order polynomial and showed the differences in the pixel locations obtained through the matching. We performed proximity corrections using the Boolean operation between the point data of the surface linear objects and the point data of the edge objects of the image. The surface linear objects are road, water, building from topographic map.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.42 no.2
• /
• pp.1-9
• /
• 2014

This study is the renovation plan for BIFF(Busan International Film Festival) street themed movies, which is an internationally known film festival. The aim of this is the regional economic vitalization. The first step of the plan sets up position through the case study of the Theme Street. The theme for each road space is related with movies and realizes the unificative images for each road. Images between the Busan Cinema Center and BUSAN MARINA are introduction of the road and the subject of this road is greeting with movies. The history of movies are printed on the pavement, some sections are made with red blocks for recollecting the red carpet. The next section from the BUSAN MARINA to MARINE CITY is set up being close with movies. In this section, sculptures of filmmaking and theme benches are installed for indirect experiences. The theme from MARINE CITY to DONGBAEK ISLANDS is playing and enjoying with movies. It is made more fun with the installation of super graphic and trick art. The theme from DONGBAEK ISLANDS to HAEUNDAE is farewell with movies. It is expressed by music on pavement and musical fountain. The last section in the theme road from HAEUNDAE to MOONTAN ROAD shows the concept memories after farewell. It is a half way to Moonten Road. The Milky Way pavement and Milky Way square are made by installing the optical fibers.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.2
• /
• pp.95-111
• /
• 2021

As the population decreases in an aging society, the average age of drivers increases. Accordingly, the elderly at high risk of being in an accident need autonomous-driving vehicles. In order to secure driving safety on the road, several technologies to respond to various obstacles are required in those vehicles. Among them, technology is required to recognize static obstacles, such as poor road conditions, as well as dynamic obstacles, such as vehicles, bicycles, and people, that may be encountered while driving. In this study, we propose a deep neural network algorithm capable of simultaneously detecting these two types of obstacle. For this algorithm, we used 1,418 road images and produced annotation data that marks seven categories of dynamic obstacles and labels images to indicate road damage. As a result of training, dynamic obstacles were detected with an average accuracy of 46.22%, and road surface damage was detected with a mean intersection over union of 74.71%. In addition, the average elapsed time required to process a single image is 89ms, and this algorithm is suitable for personal mobility vehicles that are slower than ordinary vehicles. In the future, it is expected that driving safety with personal mobility vehicles will be improved by utilizing technology that detects road obstacles.

• Geomechanics and Engineering
• /
• v.33 no.2
• /
• pp.203-209
• /
• 2023

One major advantage of ground penetrating radar (GPR) over other field test methods is its ability to obtain subsurface images of roads in an efficient and non-intrusive manner. Not only can the strata of pavement structure be retrieved from the GPR scan images, but also various irregularities, such as cracks and internal cavities. This article introduces a deep learning-based approach, focusing on detecting subsurface cracks by recognizing their distinctive hyperbolic signatures in the GPR scan images. Given the limited road sections that contain target features, two data augmentation methods, i.e., feature insertion and generation, are implemented, resulting in 9,174 GPR scan images. One of the most popular real-time object detection models, You Only Learn One Representation (YOLOR), is trained for detecting the target features for two types of subsurface cracks: bottom cracks and full cracks from the GPR scan images. The former represents partial cracks initiated from the bottom of the asphalt layer or base layers, while the latter includes extended cracks that penetrate these layers. Our experiments show the test average precisions of 0.769, 0.803 and 0.735 for all cracks, bottom cracks, and full cracks, respectively. This demonstrates the practicality of deep learning-based methods in detecting subsurface cracks from GPR scan images.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.1
• /
• pp.17-21
• /
• 2011

This paper presents a real- time detection of on-road succeeding vehicles based on low level edge features and a boosted cascade of Haar-like features. At first, the candidate vehicle location in an image is found by low level horizontal edge and symmetry characteristic of vehicle. Then a boosted cascade of the Haar-like features is applied to the initial hypothesized vehicle location to extract the refined vehicle location. The initial hypothesis generation using simple edge features speeds up the whole detection process and the application of a trained cascade on the hypothesized location increases the accuracy of the detection process. Experimental results on real world road scenario with processing speed of up to 27 frames per second for $720{\times}480$ pixel images are presented.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.249-257
• /
• 2017

This paper proposes a method to segment urban scenes semantically based on location prior information. Since major scene elements in urban environments such as roads, buildings, and vehicles are often located at specific locations, using the location prior information of these elements can improve the segmentation performance. The location priors are defined in special 2D coordinates, referred to as road-normal coordinates, which are perpendicular to the orientation of the road. With the help of depth information to each element, all the possible pixels in the image are projected into these coordinates and the learned prior information is applied to those pixels. The proposed location prior can be modeled by defining a unary potential of a conditional random field (CRF) as a sum of two sub-potentials: an appearance feature-based potential and a location potential. The proposed method was validated using publicly available KITTI dataset, which has urban images and corresponding 3D depth measurements.

• Journal of Sensor Science and Technology
• /
• v.27 no.2
• /
• pp.137-141
• /
• 2018

Detecting the ego-lane of a vehicle (the lane on which the vehicle is currently running) is one of the basic techniques for a smart car. Vision sensing is a widely-used method for the ego-lane detection. Existing studies usually find road lane lines by detecting edge pixels in the image from a vehicle camera, and then connecting the edge pixels using Hough Transform. However, this approach takes rather long processing time, and too many straight lines are often detected resulting in false detections in various road conditions. In this paper, we find the lane lines by scanning only a limited number of horizontal lines within a small image region of interest. The horizontal image line scan replaces the edge detection process of existing methods. Automatic thresholding and spatiotemporal filtering procedures are also proposed in order to make our method reliable. In the experiments using real road images of different conditions, the proposed method resulted in high success rate.

• The Journal of Korea Robotics Society
• /
• v.12 no.2
• /
• pp.217-227
• /
• 2017

Crosswalk detection is an important part of the Pedestrian Protection System in autonomous vehicles. Different methods of crosswalk detection have been introduced so far using crosswalk edge features, the distance between crosswalk blocks, laser scanning, Hough Transformation, and Fourier Transformation. However, most of these methods failed to detect crosswalks accurately, when they are damaged, faded away or partly occluded. Furthermore, these methods face difficulties when applying on real road environment where there are lot of vehicles. In this paper, we solve this problem by first using a region based binarization technique and x-axis histogram to detect the candidate crosswalk areas. Then, we apply Support Vector Machine (SVM) based classification method to decide whether the candidate areas contain a crosswalk or not. Experiment results prove that our method can detect crosswalks in different environment conditions with higher recognition rate even they are faded away or partly occluded.