• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.878-880
• /
• 2015

파티클 필터 기반 얼굴추적은 비교적 빠른 속도와 구현의 용이성으로 널리 사용되고 있으나 조명이나 포즈변화가 있는 영상에서 드리프트(drift) 현상에 의해 얼굴추적의 정확도가 급격히 저하된다. 본 논문에서는 앞에 언급한 얼굴의 다양성에 강인한 얼굴 텍스처 특징을 제안한다. 제안방법은 인접한 픽셀들 간의 관계를 고려한 텍스처 패턴을 정의할 때 인접한 픽셀들의 평균(average)을 적용하여 조명변화에 강인하다. 또한 얼굴의 구조적 정보를 반영한 블록 기반의 텍스처 패턴 풀링(pooling)에 의해 포즈변화에 강인하다. 실제 감시환경을 가정해 CCTV 카메라로 자체 제작한 비디오 영상에서 Local Binary Pattern(LBP)와 같은 대표적인 특징들과 비교 실험을 수행하였다. 실험결과, 드리프트(drift) 폭이 적어 더 높은 얼굴추적 정확도를 보였으며 초당 28 프레임의 매우 빠른 처리속도를 보였다.

• Journal of Korea Multimedia Society
• /
• v.15 no.4
• /
• pp.472-484
• /
• 2012

Raised or plain block is widely used for the pedestrian's safe passage. The insincere construction, insufficient maintenance and obstacle overlaid on the pavement cause pedestrian's accidents. This paper proposes a method to detect brick path by analyzing the shape pattern and texture feature of brick located in visible distance for a safe passage. A brick appears to a regular type because of its specific shape which repeats with its sized gap and its type varies according to the surrounding environment or use. This paper shows a method which extracts the shape pattern by analyzing single surface polygon and its frequency appearing in road area. The shape pattern is used to detect similar shape regions. Some regions are not detected because extraneous substances or chopped bricks distort the original shape. This problem can be solved by analyzing the texture feature vector. The analyzed vector of the previously detected regions yields the Gaussian distribution. This value in each undetected region is computed and checked whether it's satisfied with Gaussian distribution or not. The satisfied region is detected as the brick path. The experiment was performed with the various type's bricks to recognize so that the results showed as accurate as 95.9% in average.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.437-443
• /
• 2015

This paper presents face recognition based on the fusion of visible image and thermal infrared (IR) texture estimated from the face image in the visible spectrum. The proposed face recognition scheme uses a multi- layer neural network to estimate thermal texture from visible imagery. In the training process, a set of visible and thermal IR image pairs are used to determine the parameters of the neural network to learn a complex mapping from a visible image to its thermal texture in the low-dimensional feature space. The trained neural network estimates the principal components of the thermal texture corresponding to the input visible image. Extensive experiments on face recognition were performed using two popular face recognition algorithms, Eigenfaces and Fisherfaces for NIST/Equinox database for benchmarking. The fusion of visible image and thermal IR texture demonstrated improved face recognition accuracies over conventional face recognition in terms of receiver operating characteristics (ROC) as well as first matching performances.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.5
• /
• pp.31-40
• /
• 2023

As display resolution increases, many apps also tend to include high-resolution texture maps. Recent advancements in deep-learning-based image super-resolution techniques make it possible to automate high-resolution texture generation. However, there is still a lack of comprehensive analysis of the application of these techniques to texture maps. In this paper, we selected three recent super-resolution techniques, namely BSRGAN, Real-ESRGAN, and SwinIR (classical and real-world image SR), and applied them to upscale texture maps. We then conducted a quantitative and qualitative analysis of the experimental results. The findings revealed various artifacts after upscaling, which indicates that there are still limitations in directly applying super-resolution techniques to texture-map upscaling.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.123-131
• /
• 2020

This study proposes a real-time rendering algorithm for lighting when each of more than 100,000 moving particles exists as a light source. Two 3D textures are used to dynamically determine the range of influence of each light, and the first 3D texture has light color and the second 3D texture has light direction information. Each frame goes through two steps. The first step is to update the particle information required for 3D texture initialization and rendering based on the Compute shader. Convert the particle position to the sampling coordinates of the 3D texture, and based on this coordinate, update the colour sum of the particle lights affecting the corresponding voxels for the first 3D texture and the sum of the directional vectors from the corresponding voxels to the particle lights for the second 3D texture. The second stage operates on a general rendering pipeline. Based on the polygon world position to be rendered first, the exact sampling coordinates of the 3D texture updated in the first step are calculated. Since the sample coordinates correspond 1:1 to the size of the 3D texture and the size of the game world, use the world coordinates of the pixel as the sampling coordinates. Lighting process is carried out based on the color of the sampled pixel and the direction vector of the light. The 3D texture corresponds 1:1 to the actual game world and assumes a minimum unit of 1m, but in areas smaller than 1m, problems such as stairs caused by resolution restrictions occur. Interpolation and super sampling are performed during texture sampling to improve these problems. Measurements of the time taken to render a frame showed that 146 ms was spent on the forward lighting pipeline, 46 ms on the defered lighting pipeline when the number of particles was 262144, and 214 ms on the forward lighting pipeline and 104 ms on the deferred lighting pipeline when the number of particle lights was 1,024766.

• Korean Journal of Remote Sensing
• /
• v.23 no.2
• /
• pp.103-111
• /
• 2007

The spectral information based image analysis, visual interpretation and automatic classification have been widely carried out so far for remote sensing data processing. Yet recently, many researchers have tried to extract the spatial information which cannot be expressed directly in the image itself. Using the texture and wavelet scheme, we made a wavelet-based texture fusion image which includes the advantages of each scheme. Moreover, using these schemes, we carried out image classification for the urban spatial analysis and the geological structure analysis around the caldera area. These two case studies showed that image classification accuracy of texture image and wavelet-based texture fusion image is better than that of using only raw image. In case of the urban area using high resolution image, as both texture and wavelet based texture fusion image are added to the original image, the classification accuracy is the highest. Because detailed spatial information is applied to the urban area where detail pixel variation is very significant. In case of the geological structure analysis using middle and low resolution image, the images added by only texture image showed the highest classification accuracy. It is interpreted to be necessary to simplify the information such as elevation variation, thermal distribution, on the occasion of analyzing the relatively larger geological structure like a caldera. Therefore, in the image analysis using spatial information, each spatial information analysis method should be carefully selected by considering the characteristics of the satellite images and the purpose of study.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.212-216
• /
• 2007

3D 스캐너의 보급으로 3차원 모델 생성이 가능하게 되었으나 결과로 얻은 형상이 아직 사진에서와 같은 사실적 묘사에 미치지 못하고 있다. 본 논문에서는 얼굴의 3D 스캔 데이터에 효율적인 텍스처 매핑을 통해 사실적 렌더링 결과를 얻을 수 있는 방법을 기술한다. 3D 얼굴 스캔 데이터와 얼굴의 사진 이미지의 좌표를 정확하게 맞추어 3D 스캔 데이터와 얼굴 이미지의 버덱스를 매치시켜주고, 얼굴 이미지의 해당 버텍스에 들어 있는 칼라 값을 3D 스캔 데이터의 버텍스에 넘겨주는 텍스처 매핑을 구현한다. 본 논문에서는 정면, 좌측, 우측 3장의 이미지를 이용하여 간단히 멀티텍스처 매핑을 수행하는 방법과 이 때 발생하는 사진 간의 경계선에서 발생하는 문제 해결에 대해 기술한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.575-578
• /
• 2001

사진으로부터 실물과 같은 3차원 모델을 추출하고 텍스처를 추출하는 영상 기반 모델링 및 렌더링에 대한 많은 연구가 진행 중에 있다. 본 논문에서는 다중 입력 영상으로부터 다면체 프리미티브를 이용하여 3차원 모델을 생성하고 각 모델 면의 텍스처를 입력 영상으로부터 획득하는 영상 기반 모델러를 설계 및 구현하였다.

• Proceedings of the Materials Research Society of Korea Conference
• /
• 2007.11a
• /
• pp.50.1-50.1
• /
• 2007

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.3
• /
• pp.160-174
• /
• 2008

In this paper, we propose new coding techniques for photometry data of three-dimensional(3-D) mesh models. We make a good use of geometry and connectivity information to improve coding efficiency of color, normal vector, and texture data. First of all, we determine the coding order of photometry data exploiting connectivity information. Then, we exploit the obtained geometry information of neighboring vortices through the previous process to predict the photometry data. For color coding, the predicted color of the current vertex is computed by a weighted sum of colors for adjacent vortices considering geometrical characteristics between the current vortex and the adjacent vortices at the geometry predictor. For normal vector coding, the normal vector of the current vertex is equal to one of the optimal plane produced by the optimal plane generator with distance equalizer owing to the property of an isosceles triangle. For texture coding, our proposed method removes discontinuity in the texture coordinates and reallocates texture image segments according to the coding order. Simulation results show that the proposed compression schemes provide improved performance over previous works for various 3-D mesh models.