• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.248-249
• /
• 2022

In this paper, we propose a method for classifying and tracking objects based on information of multiple users obtained using RGB-D cameras. The 3D information and color information acquired through the RGB-D camera are acquired and information about each user is stored. We propose a user classification and location tracking algorithm in the entire image by calculating the similarity between users in the current frame and the previous frame through the information on the location and appearance of each user obtained from the entire image.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.6
• /
• pp.49-55
• /
• 2012

Pacman is one of the world-famous and have been chosen game in the game room at the arcade. In this paper, pacman game gives you the ability to perform by simple hand movement alone. First, we obtain binary RGB image to extract skin color, and convert into binary image YCbCr by minus the luminance in this image. Next, we extract the hand region by the product of an binary RGB image and binary YCbCr image. Finally, the hand region, we obtain the center of gravity by the minimum bounding rectangle and the center of the hand pixel area, and we used to obtain the center of the hand area with an average of two center of gravity. In other words, we presented the game of motion that can take the place of arrow key by using the center coordinates of hand. In addition, these experiments showed the average movement and error rate, and cause of the error type was also investigated.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.717-721
• /
• 2008

This paper proposes an image system that can efficiently measure the spectral reflectance of a scene using RGB cameras and LED light sources. Multispectral imaging system is composed of LED controllers, LED clusters and RGB cameras. It captures full-spectral images at real-time. The system adopts a simple, empirical linear model to estimate the full spectral reflectance at each pixel. Since the model is linear, the reconstruction is efficient and stable. We estimated the spectral reflectance of various scenes using the system and showed the effectiveness of the proposed system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.766-769
• /
• 2015

본 논문에서는 컬러 영상과 깊이 영상으로부터 영상 전체의 정보를 활용하는 형판 정합 방법으로 특징을 추출하여, 사물의 속성을 인식하는 시스템을 제안한다. 본 시스템은 입력 영상으로부터 더 많은 정보를 얻기 위해 컬러 영상과 깊이 영상을 함께 사용하였다. 그리고 영상의 부분적인 정보가 아닌 전체 정보를 활용하는 형판 정합 방법을 사용하여 속성 인식률을 향상 시켰다. 본 시스템의 성능을 확인하기 위해 워싱턴 대학에서 제공하는 RGB-D 데이터 집합을 이용하여 다른 특징들 및 분류기와 비교실험을 진행하였고, 본 논문에서 제안하는 시스템의 높은 성능을 확인할 수 있었다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.3
• /
• pp.113-127
• /
• 2015

Recently, there has been a growing interest in UAS(Unmanned Aerial System), and it is required to develop techniques to effectively detect water body from the recorded images in order to implement flood monitoring using UAS. This study used a UAS with RGB and NIR+RG bands to achieve images, and applied supervised classification method to evaluate the accuracy of water body detection. Firstly, the result for accuracy in water body image classification by RGB images showed high Kappa coefficients of 0.791 and 0.783 for the artificial neural network and minimum distance method respectively, and the maximum likelihood method showed the lowest, 0.561. Moreover, in the evaluation of accuracy in water body image classification by NIR+RG images, the magalanobis and minimum distance method showed high values of 0.869 and 0.830 respectively, and in the artificial neural network method, it was very low as 0.779. Especially, RGB band revealed errors to classify trees or grasslands of Songsan amusement park as water body, but NIR+RG presented noticeable improvement in this matter. Therefore, it was concluded that images with NIR+RG band, compared those with RGB band, are more effective for detection of water body when the mahalanobis and minimum distance method were applied.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1603-1613
• /
• 2017

This paper proposes a method for effectively segmenting the hand region using a widely popular RGB color-based webcam. This performs the empirical preprocessing method four times to remove the noise. First, we use Gaussian smoothing to remove the overall image noise. Next, the RGB image is converted into the HSV and the YCbCr color model, and global fixed binarization is performed based on the statistical value for each color model, and the noise is removed by the bitwise-OR operation. Then, RDP and flood fill algorithms are used to perform contour approximation and inner area fill operations to remove noise. Finally, ROI (hand region) is selected by eliminating noise through morphological operation and determining a threshold value proportional to the image size. This study focuses on the noise reduction and can be used as a base technology of gesture recognition application.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.492-494
• /
• 2015

본 논문에서는 철도선상에서 발생할 수 있는 자살 사고를 예방하기 위한 전단계로서 열차의 철도를 추출하는 방법을 제안한다. 본 논문에서 제안된 방법은 철도 영상에서 각각의 RGB 채널 값을 추출한다. 추출된 각각의 RGB 채널 값을 삼각형 타입 의 소속 함수에 적용하여 상한 값과 하한 값을 퍼지 스트레칭 기법으로 철도 영상의 명암 대비를 강조시킨다. 퍼지 스트레칭 기법이 적용된 영상에서 각각의RGB 채널 값을 이용하여 배경을 제거한 후에 그레이 영상으로 변환한다. 변환된 그레이 영상에서 캐니 마스크를 적용하여 철도선의 에지를 검출하고 에지가 검출된 영상에서 허프 변환 기법과 유클리디안 거리를 적용하여 철도를 검출한다. 제안된 방법의 성능을 확인하기 위해서 다양한 각도의 철도 영상을 대상으로 실험한 결과, 제안된 방법이 철도 검출에 가능성 있는 방법인 것을 확인할 수 있었다.

• Journal of Digital Convergence
• /
• v.15 no.3
• /
• pp.307-312
• /
• 2017

The purpose of this paper is to develop a new type of RGB lighting pipeline that can save time in animation production. After identifying the problems of the current method, the researchers studied 8 steps through new methods and comparative analysis. A method of implementing a graphic image lighting effect by the RGB lighting pipeline according to the current method is to create a render layer for each light set and a set of digital light separated by texture, Three types of written information can be stored in one layer and graphic image, and the accuracy and precision of color correction can be improved. Through this study, we propose the new and improved RGB lighting pipeline according to the characteristics of the work and the industries.

• Journal of Korea Multimedia Society
• /
• v.12 no.7
• /
• pp.947-952
• /
• 2009

In this paper, we propose a method of generating color sketch images using the DIP operator. In the proposed method, an input RGB color image is first transformed into an HSV color image. A sketch image of the V component image is then extracted by applying the DIP operator to the V component image, which is the brightness component of the input image. For the visual convenience, the extracted sketch image of the V component image is next inverted and contrast-stretched. The S component image is also enhanced to deepen the color of output sketch image while maintaining its color. Finally, the V and S component images along with the original H component image are transformed into an output RGB color sketch image. Experimental results show that the proposed method yields output color sketch images similar to hand-drawn sketch pictures whose colors are the same as those of input color images.

• Journal of Korea Multimedia Society
• /
• v.4 no.2
• /
• pp.108-115
• /
• 2001

In this paper we are attempted to quantitative classification of the three object color regions on a RGB image using of an improved ML(Maximum Likelihood) classification method. A RGB color image consists of three bands i.e., red, green and blue. Therefore it has a 3 dimensional structure in view of the spectral and spatial elements. The 3D structural yokels were projected in RGB cube wherefrom the ML method applied. Between the conventionally and easily usable Box classification and the statistical ML classification based on Bayesian decision theory, we compared and reviewed. Using the ML method we obtained a good segmentation result to classify positive cell nucleus, negative cell Nucleus and background un a immuno-histological breast carcinoma image. Hopefully it is available to diagnosis and prognosis for cancer patients.