• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.3
• /
• pp.11-19
• /
• 2008

Background subtraction, which separates moving objects in video sequences, is an essential technology for object recognition and tracking. However, background subtraction methods are often confused by shadow regions and this misclassification of shadow regions disturbs further processes to perceive the shapes or exact positions of moving objects. This paper proposes a method for shadow elimination which is based on shadow modeling by color information and Bayesian classification framework. Also, because of dynamic update of modeling parametres, the proposed method is able to correspond adaptively to illumination changes. Experimental results proved that the proposed method can eliminate shadow regions effectively even for circumstances with varying lighting condition.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.622-624
• /
• 2001

영상기반 렌더링(image-based rendering) 기법은 전통적인 컴퓨터 그래픽 기법과는 다르게 장면 생성 시 복잡한 3차원 정보들을 2차원 영상들의 조합으로 표현하여 렌더링 하는 방법이다. 그 중에서 원통맵을 이용한 렌더링은 파노라마 영상을 이요해 관찰자에게 보다 빠르게 실시간으로 장면을 렌더링하여 보여준다. 이러한 영상기반 렌더링에서도 ㅅㄹ제감을 보다 더 높이기 위해서는 빛과 빛에 의해 생기는 그림자, 하이라이트의 역할이 매우 중요하다. 하지만 파노라마 영상의 경우 미리 촬영된 영상들을 사용하므로 실시간으로 동적인 광원의 변화와 그로인한 그림자와 하이라이트 부분을 표현하기 위해서는 변화된 영상들을 재촬영하여 새로운 파노라마 영상을 제작해야 한다. 본 논문에서는 OpenGL을 이용하여 실내 공간을 표현한 원통 영상 기반 환경 맵에서 광원의 위치변화에 의해 가상 하이라이트 (virtual highlight)의 움직임을 파노라마 이미지의 재 촬영 없이 몇 가지 기하학 정보만으로 계산하여 표현해 주는 방법을 제안한다.

• Journal of Korea Game Society
• /
• v.19 no.3
• /
• pp.33-42
• /
• 2019

This paper is the result of research on how to represent 'Landscape' of Oriental painting in 3D space within virtual reality. Based on the similarities between the characteristics of Oriental painting and virtual reality put together three features of painting and put them into the digital content. For the expression of painting style, we produced texture, represented spaces and shadows as a content development environment, and the view point with helper storytelling.

• Annual Conference of KIPS
• /
• 2010.04a
• /
• pp.296-299
• /
• 2010

본 논문은 템플릿 모델을 이용하여 차량의 외관에 따른 종류를 인식하는 방법을 제안한다. 우선, 영상에서 차량을 검출하기 위하여 누적 차영상 기법을 이용하여 배경 영상을 추출한 후 차량 영역을 획득한다. 획득한 차량 영상은 날씨와 조명 영향에 따라서 그림자가 존재할 수 있다. 따라서 외곽선을 추출하고 가로와 세로, 대각선 방향으로 사영한 결과를 이용하여 그림자를 제거한다. 그림자 영역이 제거된 최종 차량 영역은 템플릿 모델과의 매칭을 통하여 가장 적합한 차량 종류로 인식한다. 제안된 방법을 이용하여 차량 종류를 인식하였을 때 만족할 만한 성능을 나타내는 것을 실험을 통하여 확인하였다.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.635-638
• /
• 2008

Online games' environments have recently changed with developments of computer technique. Various factors such as respective for realistic expression, solidity, the quality of the material, shadow, should be considered. In these factors, shadow expression plays a important role for realistic one. A lot of repeated operation should be executed to provide shadow. In other words, realm division against a lot of dots to estimate objections and the degree of brightness should be divided. This paper provides effective methods to perform realistic shadow through mapping LOD of objections as shadow without drawing data to judge the realm of shadow for shadow creation.

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.1027-1030
• /
• 2011

휴머노이드 로봇 중 초상화를 그리는 로봇이 있지만 다양한 영상을 입력받아 명암 및 그림자까지 그림을 그리는 로봇은 흔하지 않다. 기존의 화가로봇들은 사용자의 얼굴을 영상으로 입력받아 윤곽선만 추출하여 그리는 방식으로, 입력된 영상으로부터 로봇 암을 제어하는 과정에서 제대로 동기화가 이뤄지지 못해 드로잉 속도가 느리고 원본 영상과 비교 시 차이가 많이 난다. 본 연구에서는 입력된 영상으로부터 명암과 그림자를 인식하여 표현해 줌으로써 입체감 있는 그림의 드로잉이 가능하다. 또한, 로봇 암의 미세한 컨트롤을 통해 드로잉 선 두께를 제어함으로써 자연스러운 그림을 그리고, 드로잉 속도가 향상되어 정확도를 높일 수 있게 하는 휴리스틱 암 제어 기술을 제안한다. 이를 구현하기 위해서는 영상으로부터 명암, 그림자의 농도에 따라 레벨을 결정하고, 레벨을 바탕으로 주변 명암 픽셀들을 평활화 하여 좌표 집합을 추출한다. 좌표 값들로 부터 유효 궤적을 분석하여 로봇 암이 이동할 경로를 추출하고, 효율적인 드로잉 기법을 통해 명암을 표현하여 드로잉하려 한다.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.621-626
• /
• 2006

Today's commercial high resolution satellite imagery such as IKONOS and QuickBird, offers the potential to extract useful spatial information for geographical database construction and GIS applications. Extraction of 3D building information from high resolution satellite imagery is one of the most active research topics. There have been many previous works to extract 3D information based on stereo analysis, including sensor modelling. Practically, it is not easy to obtain stereo high resolution satellite images. On single image performance, most studies applied the roof-bottom points or shadow length extracted manually to sensor models with DEM. It is not suitable to apply these algorithms for dense buildings. We aim to extract 3D building information from a single satellite image in a simple and practical way. To measure as many buildings as possible, in this paper, we suggested a new way to extract building height by triangular vector structure that consists of a building bottom point, its corresponding roof point and a shadow end point. The proposed method could increase the number of measurable building, and decrease the digitizing error and the computation efficiency.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1343-1356
• /
• 2022

Clouds or shadows are the most problematic when monitoring crops using optical satellite images. To reduce this effect, a composite algorithm was used to select the maximum Normalized Difference Vegetation Index (NDVI) for a certain period. This Maximum NDVI Composite (MNC) method reduces the influence of clouds, but since only the maximum NDVI value is used for a certain period, it is difficult to show the phenomenon immediately when the NDVI decreases. As a way to maintain the spectral information of crop as much as possible while minimizing the influence of clouds, a Score-Based Composite (SBC) algorithm was proposed, which is a method of selecting the most suitable pixels by defining various environmental factors and assigning scores to them when compositing. In this study, the Sentinel-2A/B Level 2A reflectance image and cloud, shadow, Aerosol Optical Thickness(AOT), obtainging date, sensor zenith angle provided as additional information were used for the SBC algorithm. As a result of applying the SBC algorithm with a 15-day and a monthly period for Dangjin rice fields and Taebaek highland cabbage fields in 2021, the 15-day period composited data showed faster detailed changes in NDVI than the monthly composited results, except for the rainy season affected by clouds. In certain images, a spatially heterogeneous part is seen due to partial date-by-date differences in the composited NDVI image, which is considered to be due to the inaccuracy of the cloud and shadow information used. In the future, we plan to improve the accuracy of input information and perform quantitative comparison with MNC-based composite algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.4
• /
• pp.11-19
• /
• 2000

Real-time extraction of traffic information such as the number of vehicles passing, speed, road-occupancy rate, distance between vehicles, and vehicle types from the traffic scenes acquired from the camera on the road, is a core component of the intelligent transportation system(lTS) We present a scheme of extracting the traffic informations based on the spatio-temporal image analysis, which is robust to the variation of weather conditions and the shades. The images of two detection regions for each traffic lane are classified into one of the three categories: the road, the vehicle, and the shade, using the statistical and structural features Quantitative traffic informations are retrieved by analysing the two spatio-temporal images. Since only the local images of detection regions are processed, the real-time operation of more than 30 frames per second is realized while ensuring the detection performance robust to the operating condition.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.637-654
• /
• 2023

In recent years, the number of users has been increasing with the rapid development of earth observation satellites. In response, the Committee on Earth Observation Satellites (CEOS) has been striving to provide user-friendly satellite images by introducing the concept of Analysis Ready Data (ARD) and defining its requirements as CEOS ARD for Land (CARD4L). In ARD, a mask called an Unusable Data Mask (UDM), identifying unnecessary pixels for land analysis, should be provided with a satellite image. UDMs include clouds, cloud shadows, terrain shadows, etc. Terrain shadows are generated in mountainous terrain with large terrain relief, and these areas cause errors in analysis due to their low radiation intensity. previous research on terrain shadow detection focused on detecting terrain shadow pixels to correct terrain shadows. However, this should be replaced by the terrain correction method. Therefore, there is a need to expand the purpose of terrain shadow detection. In this study, to utilize CAS500-4 for forest and agriculture analysis, we extended the scope of the terrain shadow detection to shaded areas. This paper aims to analyze the potential for terrain shadow detection to make a terrain shadow mask for South and North Korea. To detect terrain shadows, we used a Hill-shade algorithm that utilizes the position of the sun and a surface's derivatives, such as slope and aspect. Using RapidEye images with a spatial resolution of 5 meters and Sentinel-2 images with a spatial resolution of 10 meters over the Korean Peninsula, the optimal threshold for shadow determination was confirmed by comparing them with the ground truth. The optimal threshold was used to perform terrain shadow detection, and the results were analyzed. As a qualitative result, it was confirmed that the shape was similar to the ground truth as a whole. In addition, it was confirmed that most of the F1 scores were between 0.8 and 0.94 for all images tested. Based on the results of this study, it was confirmed that automatic terrain shadow detection was well performed throughout the Korean Peninsula.