• 방송공학회논문지
• /
• 제10권2호
• /
• pp.238-246
• /
• 2005

본 논문에서는 공간 적응적 제약조건과 정칙화 함수를 이용한 반복적 고해상도 영상보간 기법을 제안한다. 제안된 정칙화 영상보간 알고리듬은 에지 방향에 따라 제약조건들을 적응적으로 적용하고, 각각의 반복 연산 단계에서 에지 방향별 정칙화에 적합한 정칙화 함수를 최적화하여 고해상도 영상보간을 구현한다. 제안한 알고리즘은 기존의 비적응적 정칙화 보간 방법뿐만 아니라 적응적 보간 방법보다도 방향성 고주파 성분을 적절히 보존하는 동시에 잡음과 같은 바람직하지 못한 효과들을 억제할 수 있다. 마지막으로 본 논문에서 제안한 알고리듬의 성능평가를 위해서 기존에 제안된 여러 가지의 고해상도 영상보간 알고리듬과의 다양한 비교실험을 수행하였고, 이를 통하여 제안한 고해상도 영상보간 기법이 주관적으로나 객관적으로 우수함을 보였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.123-125
• /
• 2005

Many researchers conducted the effort for improving the classification accuracy of satellite image. Most of the study has used optical spectrum information of each pixel for image classification. By applying this method for high resolution satellite image, number of class becomes increase. This situation is remarkable for house, because the roof of house has variety of many colors. Even if the classification is carried out for many classes, roof color information of each house is not necessary. Most of the case, we need the information that object is house or not. In this study, we propose the method for detecting the object by using Genetic Algorithms (GA). Aircraft was selected as object. It is easy for this object to detect in the airport. An aircraft was taken as a template. Object image was taken from QuickBird. Target image includes an aircraft and Haneda Airport. Chromosome has four or five parameters which are composed of number of template, position (x,y), rotation angle, rate of enlarge. Good results were obtained in the experiment.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2003년도 춘계종합학술대회논문집
• /
• pp.416-420
• /
• 2003

본 논문에서는 내삽법을 이용하여 빠른 육안 검색을 위한 이중 해상도 영상 데이터베이스 시스템을 구현하였다. 단일 고해상도 방식에서 발생하는 블록킹 현상과 두 개의 해상도를 가진 영상들을 각각 데이터베이스에 저장할 때 발생하는 큰 저장 공간의 두 가지 단점을 극복하였다. 제안한 방식은 원 영상을 부샘플링하여 부샘플링 영상을 만들고, 내삽법을 이용하여 부샘플링된 영상의 보간 영상을 만든다. 이 보간 영상과 원영상과의 차영상을 근간으로 복합 이중 해상도 영상 데이터베이스를 구성한다. 60명의 실험 영상으로 실험한 결과 제안한 방식의 검색 시간이 평균 0.003초로, 단순 고해상도 방식의 0.014초에 비해 빠르다, 또한 원영상 하나만을 저장하는 방식에 비해 19,821 byte에서 16,910 byte로 14.7% 개선 효과가 있다.

• 한국콘텐츠학회논문지
• /
• 제9권11호
• /
• pp.18-26
• /
• 2009

영상 해상도 향상 알고리즘은 영상 확대 및 영상 복원을 위한 기반 기술로 사용되며, 해상도 향상 과정에서 문제점은 흐려짐 현상이나 블록 현상으로 인한 화질 열화의 발생이다. 본 논문에서는 하위 레벨 보간을 이용한 손실 정보 추정과 영상 해상도 향상 기법을 제안한다. 제안하는 방법에서는 획득한 저해상도 영상의 다운샘플링-보간 과정을 이용해서 손실 정보를 계산하고, 손실 정보의 보간을 통해서 손실 정보를 추정하며, 가중치 계수와 결합한 추정 손실 정보를 고해상도로 보간 된 영상에 적용한다. 동일한 영상을 이용한 실험 결과, 제안한 방법이 기존의 방법들보다 PSNR에서 평균 2.3dB 이상 향상된 것을 검증하였고, 윤곽선 및 문자의 인식 정도에 대한 주관적인 화질 비교 결과도 개선되었음을 확인하였다. 제안한 방법은 영상 개선을 필요로 하는 다양한 비디오 응용 분야에서 유용하게 사용될 수 있다.

• 방송공학회논문지
• /
• 제17권2호
• /
• pp.344-353
• /
• 2012

본 논문에서는 이산 웨이블릿 변환(Discrete Wavelet Transform: DWT)을 이용한 새로운 초고해상도 기법을 제안한다. 기존의 단일 영상에 적용되는 초고해상도 기법들의 경우 영상에서의 고주파 대역을 찾기 위하여 확률 기반의 방법들을 사용하였다. 그로 인한 연산의 복잡도 증가는 처리시간 증가라는 문제점을 발생시켰다. 제안된 기법에서는 고주파 대역을 찾기 위한 방법으로 DWT를 이용한다. DWT 수행 시 수반되는 다운 샘플링 과정을 수행하지 않음으로써 입력 받은 영상과 동일한 크기의 고주파 부대역(sub-band)들을 생성하고, 이 부대역들과 입력 받은 영상을 조합하여 이산 웨이블릿 역변환(Inverse Discrete Wavelet Transform: Inverse DWT)을 수행함으로써 고해상도의 영상을 획득한다. 제안하는 기법에서 사용한 실험영상은 원본영상($512{\times}512$)을 다운 샘플링하여 획득한 실험영상($256{\times}256$)을 사용한다. 실험을 통하여 제안된 기법이 기존의 보간법에 비해 향상된 효율을 보이며, 확률 기반의 기법들에 비해 처리시간이 줄어드는 것을 확인하였다.

• 한국재료학회지
• /
• 제32권8호
• /
• pp.345-353
• /
• 2022

In this study, using deep learning, super-resolution images of transmission electron microscope (TEM) images were generated for nanomaterial analysis. 1169 paired images with 256 × 256 pixels (high resolution: HR) from TEM measurements and 32 × 32 pixels (low resolution: LR) produced using the python module openCV were trained with deep learning models. The TEM images were related to DyVO₄ nanomaterials synthesized by hydrothermal methods. Mean-absolute-error (MAE), peak-signal-to-noise-ratio (PSNR), and structural similarity (SSIM) were used as metrics to evaluate the performance of the models. First, a super-resolution image (SR) was obtained using the traditional interpolation method used in computer vision. In the SR image at low magnification, the shape of the nanomaterial improved. However, the SR images at medium and high magnification failed to show the characteristics of the lattice of the nanomaterials. Second, to obtain a SR image, the deep learning model includes a residual network which reduces the loss of spatial information in the convolutional process of obtaining a feature map. In the process of optimizing the deep learning model, it was confirmed that the performance of the model improved as the number of data increased. In addition, by optimizing the deep learning model using the loss function, including MAE and SSIM at the same time, improved results of the nanomaterial lattice in SR images were achieved at medium and high magnifications. The final proposed deep learning model used four residual blocks to obtain the characteristic map of the low-resolution image, and the super-resolution image was completed using Upsampling2D and the residual block three times.

• 한국소음진동공학회논문집
• /
• 제15권3호
• /
• pp.329-333
• /
• 2005

This paper is concerned with the measurement of low-frequency vibrations of structures using the image processing method. To measure the vibrations visually, the measurement system consists of a camera, an image grabber board, and a computer. The specific target installed on the structure is used to calculate the vibration of structure. The captured image is then converted into a pixel-based data and then analyzed numerically. The limitation of the system depends on the image capturing speed and the size of image. In this paper, we propose the methodology for the vibration measurement using the image processing method. The method enables us to measure the displacement directly without any contact. The current resolution of the vibration measurement is limited to sub centimeter scale. However, the frequency bandwidth and resolution can be enhanced by a high-speed and high-resolution image processing system.

• 한국환경복원기술학회지
• /
• 제9권6호
• /
• pp.1-12
• /
• 2006

Remote sensing cannot provide a direct measurement of vegetation index (VI) but it can provide a reasonably good estimate of vegetation index, defined as the ratio of satellite bands. The monitoring of vegetation in nearby urban regions is made difficult by the low spatial resolution and temporal resolution image captures. In this study, enhancing spatial resolution method is adapted as to improve a low spatial resolution. Recent studies have successfully estimated normalized difference vegetation index (NDVI) using improved resolution method such as from the Moderate Resolution Imaging Spectroradiometer (MODIS) onboard EOS Terra satellite. Image enhancing spatial resolution is an important tool in remote sensing, as many Earth observation satellites provide both high-resolution and low-resolution multi-spectral images. Examples of enhancement of a MODIS multi-spectral image and a MODIS NDVI image of Cheongju using a Landsat TM high-resolution multi-spectral image are presented. The results are compared with that of the IHS technique is presented for enhancing spatial resolution of multi-spectral bands using a higher resolution data set. To provide a continuous monitoring capability for NDVI, in situ measurements of NDVI from paddy field was carried out in 2004 for comparison with remotely sensed MODIS data. We compare and discuss NDVI estimates from MODIS sensors and in-situ spectroradiometer data over Ochang plain region. These results indicate that the MODIS NDVI is underestimated by approximately 50%.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.526-529
• /
• 2007

Due to its inherent feature of high-resolution satellite, there is strong need in some specific area to minimize the processing time required to get a standard image on hand from downlink signal acquisition. However, in general image processing system, it takes considerable time to get image data up to certain level from raw data acquisition because the huge amount of data is dealt sequentially as input data. This paper introduces the high-speed image processing system which generates the image data only for the area selected by user. To achieve the high speed performance, this system includes Quick Look Image display function with sampling, ROI selection function, Image Line Index function, and Distributed processing function. The developed RPS was applied to KOMPSAT-2 320Mbps downlink channel and its effectiveness was successfully demonstrated. This feature to provide the image product very quickly is expected to promote the application of high resolution satellite image.

• 전자통신동향분석
• /
• 제35권4호
• /
• pp.91-102
• /
• 2020

Recently, generative adversarial networks (GANs) is a field of research that has rapidly emerged wherein many studies conducted shows overwhelming results. Initially, this was at the level of imitating the training dataset. However, the GAN is currently useful in many fields, such as transformation of data categories, restoration of erased parts of images, copying facial expressions of humans, and creation of artworks depicting a dead painter's style. Although many outstanding research achievements have been attracting attention recently, GANs have encountered many challenges. First, they require a large memory facility for research. Second, there are still technical limitations in processing high-resolution images over 4K. Third, many GAN learning methods have a problem of instability in the training stage. However, recent research results show images that are difficult to distinguish whether they are real or fake, even with the naked eye, and the resolution of 4K and above is being developed. With the increase in image quality and resolution, many applications in the field of design and image and video editing are now available, including those that draw a photorealistic image as a simple sketch or easily modify unnecessary parts of an image or a video. In this paper, we discuss how GANs started, including the base architecture and latest technologies of GANs used in high-resolution, high-quality image creation, image and video editing, style translation, content transfer, and technology.