• Spatial Information Research
• /
• 제14권1호
• /
• pp.1-13
• /
• 2006

한국건설기술연구원에서는 기존의 도로현황을 더욱 빠르고 정확하게 파악하기 위해 전국의 일반국도에 대해 매 10m 간격으로 2매의 고해상도의 칼라 영상을 취득하고 이를 도로관리통합시스템에 제공하는 사업을 수행하고 있다. 현재는 경기, 강원, 충청지역의 일반국도 영상을 도로관리통합시스템에서 제공하고 있으며 2006년 상반기까지 전국으로 확대할 계획이다. 본 논문에서는 취득한 위치자료와 영상자료를 일대일로 매칭하거나 노선별로 취득한 자료를 국도유지건설사무소별로 재구성하는 것과 같이 도로영상수집차량을 이용하여 수집한 영상을 데이터베이스화하는 전 과정에 대해 기술하였다.

• 한국산학기술학회논문지
• /
• 제12권12호
• /
• pp.5856-5864
• /
• 2011

본 논문은 도로상에 설치한 고정 카메라로부터 획득된 비디오 영상으로부터 이동물체를 검출하는 방법을 제안한다. 제안된 방법은 배경과 입력 비디오 프레임에서 가우시안 피라미드를 사용한 배경 차영상 기법에 기반하며, 입력 비디오 프레임과 배경영상의 오정합으로 발생하는 오검출을 줄이는데 화소기반 방법에 비해 효과적이다. 차영상에서 임계값을 효과적으로 결정하기위하여 각 프레임에서 Otsu의 방법으로 계산된 임계값에 스칼라 칼만필터를 적용하여 필터링하였다. 실험 결과 도로 비디오 영상에서 움직이는 물체를 효과적으로 검출함을 보였다.

• 융합신호처리학회논문지
• /
• 제10권3호
• /
• pp.164-169
• /
• 2009

본 논문에서는 고해상도 위성영상에 대해서 분할된 후보영역의 텍스처 정보를 기반으로 BP 신경회로망을 이용한 도로영역검출방법을 제안한다. 먼저, N.Otsu가 제안한 히스토그램 기반의 이진화와 열림연산을 수행하여 배경영역으로부터 일차적으로 도로영역인 전경부분을 분할한다. 그리고 전경부분의 색상 히스토그램을 이용하여 주요색상을 추출한 후 ${\pm}25$ 범위 이내에 있는 영역을 도로영역 후보를 검출한다. 마지막으로, 분할된 후보 도로영역에 대해서 동시발생행렬을 이용하여 텍스처 정보를 추출한 후 BP 신경회로망을 이용하여 최종적인 도로영역을 검출한다. 제안한 방법은 도로영역이 일정한 밝기값과 형태를 가진다는 사실에 착안한 것으로, 실험에서 다양한 위성영상들을 대상으로 평균 90% 이상의 검출율을 보여 그 유효함을 보였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권1호
• /
• pp.85-96
• /
• 2023

The number of traffic accidents caused by wet or icy road surface conditions is on the rise every year. Car crashes in such bad road conditions can increase fatalities and serious injuries. Historical data (from the year 2016 to the year 2020) on weather-related traffic accidents show that the fatality rates are fairly high in Korea. This requires accurate prediction and identification of hazardous road conditions. In this study, a forecasting model is developed to predict the chances of traffic accidents that can occur on roads affected by weather and road surface conditions. Multiple deep learning algorithms taking into account AlexNet and 2D-CNN are employed. Data on orthophoto images, automatic weather systems, automated synoptic observing systems, and road surfaces are used for training and testing purposes. The orthophotos images are pre-processed before using them as input data for the modeling process. The procedure involves image segmentation techniques as well as the Z-Curve index. Results indicate that there is an acceptable performance of prediction such as 65% for dry, 46% for moist, and 33% for wet road conditions. The overall accuracy of the model is 53%. The findings of the study may contribute to developing comprehensive measures for enhancing road safety.

• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.112-121
• /
• 2016

ADAS(Advanced Driver Assistance Systems) and street furniture information collecting car like as MMS(Mobile Mapping System), they require object location estimation method for recognizing spatial information of object in road images. But, the case of conventional methods, these methods require additional hardware module for gathering spatial information of object and have high computational complexity. In this paper, for a coordinate of road sign in single camera image, a position estimation scheme of object in road images is proposed using the relationship between the pixel and object size in real world. In this scheme, coordinate value and direction are used to get coordinate value of a road sign in images after estimating the equation related on pixel and real size of road sign. By experiments with test video set, it is confirmed that proposed method has high accuracy for mapping estimated object coordinate into commercial map. Therefore, proposed method can be used for MMS in commercial region.

• 시스템엔지니어링학술지
• /
• 제1권2호
• /
• pp.26-33
• /
• 2005

In this paper, an algorithm is presented to recognize road based on unpaved test courses image. The road images obtained by a video camera undergoes a pre-processing that includes filtering, gray level slicing, masking and identification of unpaved test courses. After this pre-processing, a part of image is grouped into 27 sub-windows and fed into a three-layer feed-forward neural network. The neural network is trained to indicate the road direction. The proposed algorithm has been tested with the images different from the training images, and demonstrated its efficacy for recognizing unpaved road. Based on the test results, it can be said that the algorithm successfully combines the traditional image processing and the neural network principles towards a simpler and more efficient driver warning or assistance system.

• 한국ITS학회 논문지
• /
• 제13권2호
• /
• pp.27-33
• /
• 2014

This paper proposes a gradation image processing method for the development of a Road Sign Recognition Platform (RReP), which aims to facilitate the rapid and accurate management and surveying of approximately 160,000 road signs installed along the highways, national roadways, and local roads in the cities, districts (gun), and provinces (do) of Korea. RReP is based on GPS(Global Positioning System), IMU(Inertial Measurement Unit), INS(Inertial Navigation System), DMI(Distance Measurement Instrument), and lasers, and uses an imagery information collection/classification module to allow the automatic recognition of signs, the collection of shapes, pole locations, and sign-type data, and the creation of road sign registers, by extracting basic data related to the shape and sign content, and automated database design. Image division and merging, which were applied in this study, produce superior results compared with local binarization method in terms of speed. At the results, larger texts area were found in images, the accuracy of text recognition was improved when images had been gradated. Multi-threshold values of natural scene images are used to improve the extraction rate of texts and figures based on pattern recognition.

• Smart Structures and Systems
• /
• 제24권6호
• /
• pp.745-757
• /
• 2019

Road surface deteriorations such as potholes have caused motorists heavy monetary damages every year. However, effective road condition monitoring has been a continuing challenge to road owners. Depth cameras have a small field of view and can be easily affected by vehicle bouncing. Traditional image processing methods based on algorithms such as segmentation cannot adapt to varying environmental and camera scenarios. In recent years, novel object detection methods based on deep learning algorithms have produced good results in detecting typical objects, such as faces, vehicles, structures and more, even in scenarios with changing object distances, camera angles, lighting conditions, etc. Therefore, in this study, a Deep Learning Pothole Detector (DLPD) based on the deep region-based convolutional neural network is proposed for autonomous detection of potholes from images. About 900 images with potholes and road surface conditions are collected and divided into training and testing data. Parameters of the network in the DLPD are calibrated based on sensitivity tests. Then, the calibrated DLPD is trained by the training data and applied to the 215 testing images to evaluate its performance. It is demonstrated that potholes can be automatically detected with high average precision over 93%. Potholes can be differentiated from manholes by training and applying a manhole-pothole classifier which is constructed using the convolutional neural network layers in DLPD. Repeated detection of the same potholes can be prevented through feature matching of the newly detected pothole with previously detected potholes within a small region.

• 한국인공지능학회지
• /
• 제11권3호
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• 대한공간정보학회지
• /
• 제12권4호
• /
• pp.61-68
• /
• 2004

본 연구에서는 도로 노면표지를 이용하여 도심지에서 3차원 도로정보를 자동으로 취득하기 위한 기술을 제안하였다. 제안된 방법은 다음의 주요 3단계로 구성되어 있다. 첫 단계는 두 장의 항공사진에 나타난 도로 노면표지를 추출하는 것이고, 두 번째는 추출된 노면표지 중 동일한 표지를 매칭하는 것이다. 마지막 단계는 항공사진의 외부표정요소를 이용하여 노면표지의 3차원 위치좌표를 얻는 것이다. 마지막 단계는 공선조건식을 사용하여 수행될 수 있기 때문에, 본 연구에서는 처음 두 단계에 연구의 초점을 맞추었다. 차로 경계선을 추출하기 위해 노면표지의 형상 정보와 공간 관계를 이용하였고, 템플릿 매칭을 추가적으로 사용하여 방향표시를 추출하였다. 그리고 도로의 3차원 위치정보를 취득하기 위해 도로 노면표지에 적합한 관계형 매칭(relational matching)기법을 사용하였다. 추출정확도는 시각적인 평가를 통해 수행하였고, 위치정확도는 수치사진 측량시스템을 통해 얻은 참고자료와 비교를 통해 수행하였다.