• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.490-492
• /
• 2000

본 논문에서는 방송영상 특성을 이용한 축구 경기 장면 분석을 제안한다. 동영상의 프레임들을 분할하기 위해서는 급격한 장면 변화나 화면의 색상과 같은 화면의 형식적인 변화가 주요 결정사항이다. 그러나 축구경기와 같은 동영상에서의 하이라이트는 화면의 형식적인 변화와는 조금 다른 의미를 가진다. 그러므로, 축구 경기 동영상에서 하이라이트 부분을 검출하기 위해서는 장면의 변화와 더불어 화면의 의미를 해석할 필요가 있다. 본 논문에서는 축구 경기 동영상의 모든 프레임을 순차적으로 검사한다. 임의의 프레임에 대하여 RGB 정보의 분석을 통하여 영상의 구성내용을 파악한 후, 구성 내용의 위치와 분포를 참조하여 하이라이트 여부를 판단한다. 제안된 방법에서는 RGB 값의 변화 문제를 해결하기 위하여, 주 RGB 범위 군집화(Dominant RGB Grouping) 방법을 통하여 임의의 영상에서 RGB 값의 변화에 최대한 덜 민감한 방법으로 대상의 RGB 정보를 취득할 수 있는 방법을 사용하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.441-443
• /
• 2018

This paper deals with the analysis of leg motion using RGB image. We used RGB image as gait analysis element by using BMC(Background Model Challenge) method and by using combining object recognition segmentation algorithm and attitude detection algorithm. It is considered that gait analysis incorporating image can be used as a parameter for classification of gait pattern recognition and abnormal gait.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.448-450
• /
• 2012

본 논문에서는 Kinect 방식의 RGB-D 영상센서를 사용하여, 깊이(Depth) 영상으로부터 3차원 객체의 기하정보를 표현하는 표면 정규 벡터(Surface Normal Vector)를 추출하고, 그 결과를 영상화하는 방법을 제안하며, 제안된 방법으로 생성된 영상으로부터 깊이 영상의 특징점 및 특징 기술자를 추출하여 3차원 객체 인식 성능을 향상시키는 방법을 제안한다. 또한 생성된 RGB-D 특징 기술자들을 객체 단위로 구분 가능한 코드북(CodeBook) 학습을 통한 인식방법을 제안하여 객체의 인식 성능을 높이는 방법을 제안한다. 제안하는 RGB-D 기반의 특징 추출 및 학습 방법은 텍스쳐 유무, 카메라 회전 및 이동 변화 등의 환경변화에 강건함을 실험적으로 증명하였으며, 이 방법은 Kinect 방식의 RGB-D 영상을 사용하는 3차원 객체/공간 인식 및 추적, 혹은 이를 응용하는 증강현실 시스템에 적용하여 사용될 수 있다.

• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.48-52
• /
• 2023

Many studies have been conducted to ensure that Visual Place Recognition is reliable in various environments, including edge cases. However, existing approaches use visible imaging sensors, RGB cameras, which are greatly influenced by illumination changes, as is widely known. Thus, in this paper, we use an invisible imaging sensor, a long wave length infrared camera (LWIR) instead of RGB, that is shown to be more reliable in low-light and highly noisy conditions. In addition, although the camera sensor used to solve this problem is an LWIR camera, but since the thermal image is converted into RGB image the proposed method is highly compatible with existing algorithms and databases. We demonstrate that the proposed method outperforms the baseline method by about 0.19 for recall performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.2
• /
• pp.334-343
• /
• 1997

Reference white in color television receiver can be achieved by adjusting the RGB gun current ratio and it is necessary to provide additional gain ratio adjustment for the RGB video signal. Generally, the gun current density profile has a gaussian distribution and the gain-bandwidth product of RGB channel amplifieris constant. Therefore brightness and spatial resolution are changed with variations in reference white of receiver. In this paper, the effect of RGB gun current and channel gain ratios on brightness and resolution of CPT is analyzed. Brightness is increased with the color temperature of referenc white because of Helmholtz-kohlrausch effect. The change in ligh output is more abrupt and spatial resolution is improved with unity current ratio. For more bright and improved ressolution we also present the range of color temperature of reference white for P22 phosphors.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.439-448
• /
• 2020

In this paper, we propose a modified optimization algorithm for point cloud matching of multi-view RGB-D cameras. In general, in the computer vision field, it is very important to accurately estimate the position of the camera. The 3D model generation methods proposed in the previous research require a large number of cameras or expensive 3D cameras. Also, the methods of obtaining the external parameters of the camera through the 2D image have a large error. In this paper, we propose a matching technique for generating a 3D point cloud and mesh model that can provide omnidirectional free viewpoint using 8 low-cost RGB-D cameras. We propose a method that uses a depth map-based function optimization method with RGB images and obtains coordinate transformation parameters that can generate a high-quality 3D model without obtaining initial parameters.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.12
• /
• pp.23-30
• /
• 2009

LEDs are increasingly used for many applications including automotive, aviation, display, transportation and special lighting applications. Generally, the RGB multichip LED luminaire applied to signboard, emotional lighting system and display device and the white LED luminaire applied to general lighting system. white LED spectra for general lighting should be designed for high luminous efficacy as well as good color rendering. This paper describes characteristics of LED luminaire white LED and RGB multichip LED. Two type of LED luminaire prototype used experiment physical, electrical and optic test and performance analyzed. RGB multi-chip and phosphor-type white LED luminaire were analyzed by experiment on their color characteristics and luminous efficacy of radiation, distribution curve, and electrical characteristics. Research work is in progress to develop an improved performance for optic and electrical works well for two type of LED luminaires.

• Journal of the Korean earth science society
• /
• v.40 no.4
• /
• pp.406-413
• /
• 2019

Red-Green-Blue (RGB) imagery techniques are useful for both forecasters and public users because they are intuitively understood, have advantageous visualization, and do not lose observational information. This study presents a novel RGB convective cloud product and its application to tropical cyclone analysis using Communication, Oceanography, and Meteorology (COMS) satellite observations. The RGB convective cloud product was developed using the brightness temperature differences between WV ($6.75{\mu}m$) and IR1 ($10.8{\mu}m$), and IR2 ($12.0{\mu}m$) and IR1 ($10.8{\mu}m$) as well as the brightness temperature in the IR1 bands of the COMS, with the threshold values estimated from the Korea Meteorological Administration (KMA) radar observations and the EUMETSAT RGB recipe. To verify the accuracy of the convective cloud RGB product, the product was applied to the center positions analysis of two typhoons in 2013. Thus, the convective cloud RGB product threshold values were estimated for WV-IR1 (-20 K to 15 K), IR1 (210 K to 300 K), and IR1-IR2 (-4 K to 2 K). The product application in typhoon analysis shows relatively low bias and root mean square errors (RMSE)s of 23 and 28 km for DANAS in 2013, and 17 and 22 km for FRANCISCO in 2013, as compared to the best tracks data from the Regional Specialized Meteorological Center (RSMC) in Tokyo. Consequently, our proposed RGB convective cloud product has the advantages of high accuracy and excellent visualization for a variety of meteorological applications.

• Journal of Korea Multimedia Society
• /
• v.18 no.10
• /
• pp.1197-1204
• /
• 2015

Smoke detection plays an important role for the early detection of fire. In this paper, we suggest a newly developed method that generated LBPV(Local Binary Pattern Variance)s as special feature vectors from RGB contrast images can be applied to detect smoke using SVM(Support Vector Machine). The proposed method rearranges mean value of the block from each R, G, B channel and its intensity of the mean value. Additionally, it generates RGB contrast image which indicates each RGB channel’s contrast via smoke’s achromatic color. Uniform LBPV, Rotation-Invariance LBPV, Rotation-Invariance Uniform LBPV are applied to RGB Contrast images so that it could generate feature vector from the form of LBP. It helps to distinguish between smoke and non smoke area through SVM. Experimental results show that true positive detection rate is similar but false positive detection rate has been improved, although the proposed method reduced numbers of feature vector in half comparing with the existing method with LBP and LBPV.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.765-774
• /
• 2019

In this paper, we propose a point cloud matching algorithm for multiple RGB-D cameras. In general, computer vision is concerned with the problem of precisely estimating camera position. Existing 3D model generation methods require a large number of cameras or expensive 3D cameras. In addition, the conventional method of obtaining the camera external parameters through the two-dimensional image has a large estimation error. In this paper, we propose a method to obtain coordinate transformation parameters with an error within a valid range by using depth image and function optimization method to generate omni-directional three-dimensional model using 8 low-cost RGB-D cameras.