• 제어로봇시스템학회논문지
• /
• 제17권5호
• /
• pp.490-498
• /
• 2011

In this paper, we present a two-stage vision-based approach to detect multi views of pedestrian in road scene images. The first stage is HG (Hypothesis Generation), in which potential pedestrian are hypothesized. During the hypothesis generation step, we use a vertical, horizontal edge map, and different colors between road background and pedestrian's clothes to determine the leg position of pedestrian, then a novel symmetry peaks processing is performed to define how many pedestrians is covered in one potential candidate region. Finally, the real candidate region where pedestrian exists will be constructed. The second stage is HV (Hypothesis Verification). In this stage, all hypotheses are verified by Support Vector Machine for classification, which is robust for multi views of pedestrian detection and recognition problems.

• 한국통신학회논문지
• /
• 제40권12호
• /
• pp.2343-2352
• /
• 2015

본 논문에서는 U-시차 지도(U-disparity map)와 정방향-역방향 에러 제거를 통하여 자동차 환경에서의 새로운 모션 필드 예측기법을 제안한다. 일반적으로 자동차에 장착된 카메라로 획득된 영상에서는 자동차의 움직임에 따라 모션 벡터가 발생하게 된다. 그러나 이러한 모션 벡터는 주변 환경에 영향을 받기 때문에 정확도가 떨어진다. 특히 도로면에서는 인접한 화소값이 유사하기 때문에 정확한 모션 벡터의 추출이 어렵다. 따라서 제안하는 기법에서는 U-시차 지도를 이용하여 도로면을 제거하고 나머지 부분에 대하여 옵티컬 플로우(optical flow)를 수행한다. 또한 모션 벡터의 정확도를 향상시키기 위해 정방향-역방향 에러 제거 방법을 활용한다. 최종적으로 획득한 모션 벡터에 RANSAC(RANdom SAmple Consensus)을 적용하여 차량의 움직임을 예측하고 모션 필드를 생성한다. 실험을 통해 제안하는 기법이 기존의 기법보다 성능이 우수한 것을 확인하였다.

• 대한교통학회지
• /
• 제33권3호
• /
• pp.284-293
• /
• 2015

본 연구의 목적은 도로상에 설치된 CCTV에서 수집되는 영상정보를 이용하여 노면 상태를 판단하는 것이다. 이를 위해 먼저 야간의 젖은 노면을 검지하는 기술을 검증하였다. 지금까지 도로상의 젖음 정보를 추출하는 기술은 편광(polarization) 특성을 활용하는 것이다. 그러나 태양광이 없는 야간 도로상황에서는 편광특성을 활용할 수 없다. 이에 본 연구에서는 CCTV 야간 영상의 특징을 활용하여 마른 노면과 젖은 노면을 판별하는 방법을 제안한다. 노면의 젖음 여부를 판단하는 판별 방법론으로 웨이블릿(wavelet) 패킷 변환을 활용한 질감분석 방법론 및 영상의 명도분포 특성을 반영하기 위한 HSI 색상 모형 기반 명도(intensity) 히스토그램 활용 방법론을 적용하였다. 현장장비에서 취득한 총 200장의 샘플영상을 활용하여 영상을 분석, SVM (Support Vector Machine) 분류기 기반 판별 초평면을 구성한 후, 검지 기법을 검증하기 위한 현장테스트를 수행하였으며 유의한 결과를 얻을 수 있었다. 본 연구결과는 교통류의 안전성 향상을 위한 효율적인 야간 노면상태 수집에 활용될 수 있을 것이다.

• 제어로봇시스템학회논문지
• /
• 제20권12호
• /
• pp.1259-1266
• /
• 2014

Road signs provide important safety information about road and traffic conditions to drivers. Road signs include not only common traffic signs but also warning information regarding unexpected obstacles and road constructions. Therefore, accurate detection and identification of road signs is one of the most important research topics related to safe driving. In this paper, we propose a 3-D vision technique to automatically detect and track road signs in a video sequence which is acquired from a stereo vision camera mounted on a vehicle. First, color information is used to initially detect the sign candidates. Second, the SVM (Support Vector Machine) is employed to determine true signs from the candidates. Once a road sign is detected in a video frame, it is continuously tracked from the next frame until it is disappeared. The 2-D position of a detected sign in the next frame is predicted by the 3-D motion of the vehicle. Here, the 3-D vehicle motion is acquired by using the 3-D pose information of the detected sign. Finally, the predicted 2-D position is corrected by template-matching of the scaled template of the detected sign within a window area around the predicted position. Experimental results show that the proposed method can detect and track many types of road signs successfully. Tracking comparisons with two different methods are shown.

• 경영과정보연구
• /
• 제4권
• /
• pp.257-284
• /
• 2000

According as the drivers increase who have their cars, the comprehensive studies on the automobile for the traffic safety have been raised as the important problems. Visual Recognition System for radio-controled driving is a part of the sensor processor of Unmanned Autonomous Vehicle System. When a driver drives his car on an unknown highway or general road, it produces a model from the successively inputted road traffic information. The suggested Recognition System of the Road Traffic Safety Information Board is to recognize and distinguish automatically a Road Traffic Safety Information Board as one of road traffic information. The whole processes of Recognition System of the Road Traffic Safety Information Board suggested in this study are as follows. We took the photographs of Road Traffic Safety Information Board with a digital camera in order to get an image and normalize bitmap image file with a size of $200{\times}200$ byte with Photo Shop 5.0. The existing True Color is made up the color data of sixteen million kinds. We changed it with 256 Color, because it has large capacity, and spend much time on calculating. We have practiced works of 30 times with erosion and dilation algorithm to remove unnecessary images. We drawing out original image with the Region Splitting Technique as a kind of segmentation. We made three kinds of grouping(Attention Information Board, Prohibit Information Board, and Introduction Information Board) by RYB( Red, Yellow, Blue) color segmentation. We minimized the image size of board, direction, and the influence of rounding. We also minimized the Influence according to position. and the brightness of light and darkness with Eigen Vector and Eigen Value. The data sampling this feature value appeared after building the learning Code Book Database. The suggested Recognition System of the Road Traffic Safety Information Board firstly distinguished three kinds of groups in the database of learning Code Book, and suggested in order to recognize after comparing and judging the board want to recognize within the same group with Nearest Neighborhood Decision Making.

• 제어로봇시스템학회논문지
• /
• 제16권4호
• /
• pp.361-367
• /
• 2010

This paper reports the development of a mobile robot for patrol using a single laser range finder. A Laser range finder is useful for outdoor environment regardless of illumination change or various weather conditions. In this paper we combined the motion control of the mobile robot and the algorithm for detecting the outdoor environment. For obstacle avoidance, we adopted the Vector Field Histogram algorithm. A laser range finder is mounted on the mobile robot and looking down the road with a small tilt angle. We propose an algorithm for detecting the surface of the road. The outdoor patrol robot platform is equipped with a DGPS system, a gyro-compass sensor, and a laser range finder. The proposed obstacle avoidance and road detection algorithms were experimentally tested in success.

• 한국멀티미디어학회논문지
• /
• 제19권6호
• /
• pp.1003-1013
• /
• 2016

This paper proposes a framework of superpixel-based vehicle detection method using plane normal vector in disparity space. We utilize two common factors for detecting vehicles: Hypothesis Generation (HG) and Hypothesis Verification (HV). At the stage of HG, we set the regions of interest (ROI) by estimating the lane, and track them to reduce computational cost of the overall processes. The image is then divided into compact superpixels, each of which is viewed as a plane composed of the normal vector in disparity space. After that, the representative normal vector is computed at a superpixel-level, which alleviates the well-known problems of conventional color-based and depth-based approaches. Based on the assumption that the central-bottom of the input image is always on the navigable region, the road and obstacle candidates are simultaneously extracted by the plane normal vectors obtained from K-means algorithm. At the stage of HV, the separated obstacle candidates are verified by employing HOG and SVM as for a feature and classifying function, respectively. To achieve this, we trained SVM classifier by HOG features of KITTI training dataset. The experimental results demonstrate that the proposed vehicle detection system outperforms the conventional HOG-based methods qualitatively and quantitatively.

• International Journal of Automotive Technology
• /
• 제6권1호
• /
• pp.53-63
• /
• 2005

We propose a fuzzy neural network (FNN) theory capable of deciding the quality of a road image prior to extracting lane-related information. The accuracy of lane-related information obtained by image processing depends on the quality of the raw images, which can be classified as good or bad according to how visible the lane marks on the images are. Enhancing the accuracy of the information by an image-processing algorithm is limited due to noise corruption which makes image processing difficult. The FNN, on the other hand, decides whether road images are good or bad with respect to the degree of noise corruption. A cumulative distribution function (CDF), a function of edge histogram, is utilized to extract input parameters from the FNN according to the fact that the shape of the CDF is deeply correlated to the road image quality. A suitability analysis shows that this deep correlation exists between the parameters and the image quality. The input pattern vector of the FNN consists of nine parameters in which eight parameters are from the CDF and one is from the intensity distribution of raw images. Experimental results showed that the proposed FNN system was quite successful. We carried out simulations with real images taken in various lighting and weather conditions, and obtained successful decision-making about $99\%$ of the time.

• 제어로봇시스템학회논문지
• /
• 제8권6호
• /
• pp.468-476
• /
• 2002

The confidence of information from image processing depends on the original image quality. Enhancing the confidence by an algorithm has an essential limitation. Especially, road images are exposed to lots of noisy sources, which makes image processing difficult. We, in this paper, propose a FNN (fuzzy-neural network) capable oi deciding the quality of a road image prior to extracting lane-related information. According to the decision by the FNN, road images are classified into good or bad to extract lane-related information. A CDF (cumulative distribution function), a function of edge histogram, is utilized to construct input parameters of the FNN, it is based on the fact that the shape of the CDF and the image quality has large correlation. Input pattern vector to the FNN consists of ten parameters in which nine parameters are from the CDF and the other one is from intensity distribution of raw image. Correlation analysis shows that each parameter represents the image quality well. According to the experimental results, the proposed FNN system was quite successful. We carried out simulations with real images taken by various lighting and weather conditions and achieved about 99% successful decision-making.

• 대한원격탐사학회지
• /
• 제22권2호
• /
• pp.123-129
• /
• 2006

고해상도 컬러항공영상은 공간정보생성을 위한 지형의 상세한 정량적 및 정성적 정보를 제공해준다. 하지만 도심지역에서 빌딩 또는 숲에 의한 그림자의 발생으로 인하여 지물 추출 및 분류시 부정확한 결과를 초래 시킬 수 있다. 현재까지 그림자 효과에 대한 여러 연구가 이뤄졌으나 도심지에서 그림자의 발생으로 야기된 분광정보 왜곡의 문제점을 해결하여 도로추출에 대한 연구가 매우 부족한 실정이다 본 연구에서는 컬러항공사진과 LIDAR(LIght Detection and Ranging) 고도 자료를 이용하여 아스팔트 도로 경계선을 추출하는 기법을 제안하였다. 구체적으로 그림자 영향의 제거를 통한 아스팔트 도로 경계선의 추출과정은 다음과 같다. 첫 번째, 항공사진에서 그림자 영역을 LIDAR자료부터 생성된 DSM(Digital Surface Model)과 태양각으로부터 추출하였다. 그 후 도로영역추출기법, 경계선 검출기법을 통하여 도로의 경계를 추출하였으며 이 자료를 벡터화하므로서 GIS벡터의 선분 자료로 생성하였다. 본 연구의 실험결과 제안된 방법은 그림자의 영향을 소거하여 원활한 아스팔트 도로의 경계를 추출하는데 있어서 효과적임을 알 수 있었다.