• Journal of Korean Society for Geospatial Information Science
• /
• 제16권1호
• /
• pp.49-55
• /
• 2008

The face extraction is very important to provide the images of the roads and road sides without the problem of privacy. For face extraction form roadside images, we detected the skin color area by using HSI and YCrCb color models. Efficient skin color detection was achieved by using these two models. We used a connectivity and intensity difference for grouping, skin color regions further we applied shape conditions (rate, area, number and oval condition) and determined face candidate regions. We applied thresholds to region, and determined the region as the face if black part was over 5% of the whole regions. As the result of the experiment 28 faces has been extracted among 38 faces had problem of privacy. The reasons which the face was not extracted were the effect of shadow of the face, and the background objects. Also objects with the color similar to the face were falsely extracted. For improvement, we need to adjust the threshold.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2009년도 춘계학술발표대회
• /
• pp.82-85
• /
• 2009

본 논문에서는 실제 도로환경의 속도 표지판 영역 추출 및 인식 방법을 제안한다. 화소의 색상정보를 이용하여 속도 표지판 영역을 추출하고 추출된 속도 표지판 영역 안에서 숫자 영역만 다시 추출한다. 표지판의 경사여부를 판단하여 시계방향, 반시계방향으로 각각 표지판을 회전시켜 기울기를 보정한 후 인식을 행함으로써 인식률을 제고한다. 도로환경의 동영상을 대상으로 인식을 행한 결과 일반적인 속도표지판 뿐 아니라 기울어진 환경에서도 매우 강건한 인식 결과를 보인다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• 제47권6호
• /
• pp.86-96
• /
• 2010

In this paper, we propose stereo vision-based obstacle detection and vehicle verification methods using U-disparity map and bird's-eye view mapping. First, we extract a road feature using maximum frequent values in each row and column. And we extract obstacle areas on the road using the extracted road feature. To extract obstacle areas exactly we utilize U-disparity map. We can extract obstacle areas exactly on the U-disparity map using threshold value which consists of disparity value and camera parameter. But there are still multiple obstacles in the extracted obstacle areas. Thus, we perform another processing, namely segmentation. We convert the extracted obstacle areas into a bird's-eye view using camera modeling and parameters. We can segment obstacle areas on the bird's-eye view robustly because obstacles are represented on it according to ranges. Finally, we verify the obstacles whether those are vehicles or not using various vehicle features, namely road contacting, constant horizontal length, aspect ratio and texture information. We conduct experiments to prove the performance of our proposed algorithms in real traffic situations.

• Journal of Cadastre & Land InformatiX
• /
• 제44권1호
• /
• pp.127-138
• /
• 2014

It can be effective to extract and apply the updated information from the newly updated map data for updating road data of topographic map. In this study, update target data and update reference data are overlaid and the update objects are explored using network matching technique. And the network objects are classified into five matching and update cases and the update processes for each case are applied to the test data. For this study, road centerline data of digital topographic map is used as an update target data and road data of Korean Address Information System is used as an update reference data. The buffer-based network matching method is applied to the two data and the matching and update cases are classified after calculating the overlaid ratio of length. The newly updated road centerline data of digital topographic map is generated from the application of update process for each case. As a result, the update information can be extracted from the different map dataset and applied to the road network data updating.

• 한국지형공간정보학회:학술대회논문집
• /
• 한국지형공간정보학회 2004년도 추계학술발표대회 논문집
• /
• pp.25-31
• /
• 2004

To obtain the 3-D coordinates of the urban roads from aerial images, the accurate matching technique in road areas is required. In this paper, we suggest the relational matching method that is performed by comparison of relationships of road pavement markings after they are extracted from aerial images using geometric properties and spatial relationships of the pavement markings. Relational matching requires not only high level description of features but also the solution for inexact matching problems. In addition, it needs a lot of tests for the reliable final result. In this research, we described features as calculating geometric properties of the pavement markings, suggested the solution for inextact matching problems, and performed tests to decide whether the result is acceptable or not, which use the property that road areas are flat. In order to evaluate the accuracy of matching, we made a visual evaluation and compared the result of this technique with those measured by analytical photogrammetry.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• 제34권1호
• /
• pp.11-19
• /
• 2016

Recently, global companies are developing the automobile technologies, converged with state-of-the-art IT technologies for the commercialization of autonomous vehicles. These autonomous vehicles are required the accurate lane information to enhance its reliability by controlling the vehicles safely. Hence, the study planned to examine possibilities of applying UAV photogrammetry of high-resolution images, obtained from the low altitudes. The high-resolution DSM and the ortho-images were generated from the GSD 7cm-level digital images that were obtained and based on the generated data, when the positions information of the roads including the lanes were extracted. In fact, the RMSE of verifying the extracted data was shown to be about 15cm. Through the results from the study, it could be concluded that the low alititude UAV photogrammetry can be applied for generating and updating a high-accuracy map of road areas.

• Science of Emotion and Sensibility
• /
• 제2권2호
• /
• pp.75-82
• /
• 1999

지금까지 인간 감성의 측정은 대부분 제한된 실험실에서 실시되었다. 보다 자연스러운 동적인 환경에서 인간의 감성을 자율신경계의 반응을 통해 추출하고자 본 연구를 수행하였다. 쾌 또는 불쾌한 도로의 시각 환경이 긍정 및 부정 시각으로 제시되었고, 아스팔트, 시멘트, 비포장 도로 등의 도로 굴곡 변화가 또 다른 쾌/불쾌 관련 감성 자극으로 제시되었다. 건강한 5명의 피험자는 실험을 위해 차량 내부에서 도로의 시각 환경을 관찰하게 하였고, 세 가지 굴곡이 다른 도로를 주행하면서 굴곡 변화에 따른 감성을 느끼게 하였다. 심박 변화율, 피부 저항, 피부온도 등의 생리 신호를 측정하였고 주관적 평가와 비교 분석하였다. 피험자가 긍정 시각 장면에 비해 부정 시각 장면을 보았을 때 또한 도로 굴곡의 변화가 클수록 평균 R-R 간격과 피부온도의 감소율은 컸고 피부 전도도는 증가하였다. 본 연구로부터 동적 환경에서 긍정 감성 자극에 비해 부정 감성 자극이 주어 졌을 때 교감 신경계의 활성화가 보다 증가함을 관찰할 수 있었다.

• Science of Emotion and Sensibility
• /
• 제2권1호
• /
• pp.61-68
• /
• 1999

본 연구의 목적은 운전 상황과 도로 상황에 따른 자율신경계의 반응을 측정하는 것이다. 지금까지의 생리 신호는 대부분 제한된 실험실에서 측정되었고, 이 결과들은 자연스러운 상황에 측정된 데이터와는 차이가 있을 것이다. 그러므로 보다 동적인 환경에서 인간의 감성을 추출하고자 본 연구를 수행하였다. 건강한 5명의 피험자로부터 심박 변화율, 피부 저항, 피부온도 등의 생리 신호를 측정하였다. 먼저, 정차, 정속 주행, 급출발, 급제동의 운전 상황 변화에 따른 자율신경계의 반응을 측정하였고, 둘째로, 직선 도로와 굴곡이 심한 도로에서 정속 주행을 하면서 생리 신호를 측정하여 도로상황 변화에 따른 자율신경계의 반응을 측정하였다. 정차 및 정속 주행에 비해 급출발, 급제동일 때, 직선도로에 비해 굴곡이 심한 도로에서 주행을 할 때 평균 R-R 간격은 감소하였고, 전력 스펙트럼의 (LF+MF)/HF비는 증가하였고, 피부온도는 감소하였고, 피부저항은 증가하였다. 본 연구로부터, 정차 및 정속 주행에 비해 급출발, 급제동일 때 그리고 직선도로에 비해 굴곡이 심한 도로에서 주행을 할 때 교감신경계의 활성화비가 증가한다는 일치된 경향을 관찰할 수 있었다. 앞으로 피실험자수를 늘려 보다 정확한 통계적 분석을 하고자 한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제18권8호
• /
• pp.355-360
• /
• 2017

Recently, with the development of autonomous vehicle technology, the importance of precise road maps is increasing. A precise road map is a digital map with lane information, regulations, safety information, and various road facilities. Conventional precise road maps have been tested and developed based on the mobile mapping system (MMS). But they have not been activated due to high introduction costs. However, in the case of unmanned aerial vehicles (UAVs), the application field is continuously increasing. This study tries to extract information through classification of high-resolution UAV images for autonomous driving. Autonomous vehicle test roads were selected as study sites, and high-resolution orthoimages were produced using UAVs. In addition, the utilization of high-resolution orthoimages has been proposed by effectively extracting data for precise road map construction, such as road lines, guards, and machines through image classification. If additional experimentation and verification are performed, the field of UAV image use will be expanded, providing the data to automobile manufacturers and related public and private organizations, and venture companies will contribute to the development of domestic autonomous vehicle technology.

• The Journal of the Korea Contents Association
• /
• 제19권1호
• /
• pp.125-131
• /
• 2019

A vanishing point is a point on an image to which parallel lines projected from a real space gather. A vanishing point in a road space provides important spatial information. It is possible to improve the position of an extracted lane or generate a depth map image using a vanishing point in the road space. In this paper, we propose a method of detecting vanishing points on images taken from a vehicle's point of view using Deep Neural Network (DNN) and Histogram of Oriented Gradient (HoG). The proposed algorithm is divided into a HoG feature extraction step, in which the edge direction is extracted by dividing an image into blocks, a DNN learning step, and a test step. In the learning stage, learning is performed using 2,300 road images taken from a vehicle's point of views. In the test phase, the efficiency of the proposed algorithm using the Normalized Euclidean Distance (NormDist) method is measured.