• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.501-503
• /
• 2022

초해상이란 해상도가 낮은 영상을 해상도가 높은 영상으로 합성하는 기술이다. 딥러닝은 영상의 해상도를 높이는 초해상 기술에도 응용되며 실현은 2아4년에 발표된 SRCNN(Super Resolution Convolutional Neural Network) 모델로부터 시작됐다. 이후 오토인코더 (Autoencoders) 구조로는 SRCAE(Super Resolution Convolutional Autoencoders), 합성된 영상을 실제 영상과 통계적으로 구분되지 않도록 강제하는 GAN (Generative Adversarial Networks) 구조로는 SRGAN(Super Resolution Generative Adversarial Networks) 모델이 발표됐다. 모두 SRCNN의 성능을 웃도는 모델들이나 그중 가장 높은 성능을 끌어내는 SRGAN 조차 아직 완벽한 성능을 내진 못한다. 본 논문에서는 SRGAN의 성능을 개선하기 위해 사전 훈련된 특징 추출기(Pre-trained Feature Extractor) VGG(Visual Geometry Group)-19 모델을 변경하고, 기존 모델과 성능을 비교한다. 실험 결과, VGG-19 모델보다 윤곽이 뚜렷하고, 실제 영상과 더 가까운 영상을 합성할 수 있는 모델을 발견할 수 있을 것으로 기대된다.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.264-272
• /
• 2010

Example-based super resolution is a method to restore a high resolution image from low resolution images through training and retrieval of image patches. It is not only good in its performance but also available for a single frame low-resolution image. However, its time complexity is very high because it requires lots of comparisons to retrieve image patches in restoration process. In order to improve the restoration speed, an efficient patch retrieval algorithm is essential. In this paper, we applied various high-dimensional feature retrieval methods, available for the patch retrieval, to a practical example-based super resolution system and compared their speed. As well, we propose to apply the multi-phase candidate reduction approach to the patch retrieval process, which was successfully applied in character recognition fields but not used for the super resolution. In the experiments, LSH was the fastest among conventional methods. The multi-phase candidate reduction method, proposed in this paper, was even faster than LSH: For $1024{\times}1024$ images, it was 3.12 times faster than LSH.

• Spatial Information Research
• /
• v.19 no.1
• /
• pp.29-40
• /
• 2011

GOCI the world first Ocean Color Imager in Geostationary Orbit, which could obtain total 8 images of the same region a day, however, its spatial resolution(500m) is not enough to use for the accurate land application, Super Resolution(SR), reconstructing the high resolution(HR) image from multiple low resolution(LR) images introduced by computer vision field. could be applied to the time-series remotely sensed images such as GOCI data, and the higher resolution image could be reconstructed from multiple images by the SR, and also the cloud masked area of images could be recovered. As the precedent study for developing the efficient SR method for GOCI images, on this research, it reproduced the simulated data under the acquisition process of the remote sensed data, and then the simulated images arc applied to the proposed algorithm. From the proposed algorithm result of the simulated data, it turned out that low resolution(LR) images could be registered in sub-pixel accuracy, and the reconstructed HR image including RMSE, PSNR, SSIM Index value compared with original HR image were 0.5763, 52.9183 db, 0.9486, could be obtained.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.2
• /
• pp.164-173
• /
• 2013

In this paper, we propose multi-frame based super resolution algorithm by using motion vector normalization and edge pattern analysis. Existing algorithms have constraints of sub-pixel motion and global translation between frames. Thus, applying of algorithms is limited. And single-frame based super resolution algorithm by using discrete wavelet transform which robust to these problems is proposed but it has another problem that quantity of information for interpolation is limited. To solve these problems, we propose motion vector normalization and edge pattern analysis for 2*2 block motion estimation. The experimental results show that the proposed algorithm has better performance than other conventional algorithms.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2010.06a
• /
• pp.312-313
• /
• 2010

초해상도 영상복원은 동일 지역에서 획득한 다수의 영상을 통해 고해상도의 영상으로 복원하는 영상처리 알고리즘 기법이다. 이 기법은 비디오 영상, 위성 영상, 의료 영상과 같이 동일지역에 대한 다수의 저해상도 영상을 획득 할 수 있는 분야에 적용이 가능하다. 본 연구에서는 세계최초의 정지궤도 해양위성인 GOCI 센서의 육상 활용도를 높이기 위한 초해상도 기법 개발을 위해 MODIS 영상을 활용한 시뮬레이션을 수행하여, GOCI 센서를 위한 효율적인 초해상도 알고리즘을 제안한다.

• Geophysics and Geophysical Exploration
• /
• v.14 no.4
• /
• pp.335-341
• /
• 2011

Most sensing and instrumentation systems should have very higher sampling rate than required data rate not to miss important information. This means that the system can be inefficient in some cases. This paper introduces two new research areas about information acquisition with high accuracy from less number of sampled data. One is Compressed Sensing technology (which obtains original information with as little samples as possible) and the other is Super-Resolution technology (which gains very high-resolution information from restrictively sampled data). This paper explains fundamental theories and reconstruction algorithms of compressed sensing technology and describes several applications to geophysical exploration. In addition, this paper explains the fundamentals of super-resolution technology and introduces recent research results and its applications, e.g. FRI (Finite Rate of Innovation) and LIMS (Least-squares based Iterative Multipath Super-resolution). In conclusion, this paper discusses how these technologies can be used in geophysical exploration systems.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.242-251
• /
• 2020

Recently, many deep convolutional neural networks for image super-resolution have been studied. Existing deep learning-based super-resolution algorithms are architecture that up-samples the resolution at the end of the network. The post-upsampling architecture has an inefficient structure at large scaling factor result of predicting a lot of information for mapping from low-resolution to high-resolution at once. In this paper, we propose a single image super-resolution using Channel Attention Residual Dense Block based on an iterative up-down sampling architecture. The proposed algorithm efficiently predicts the mapping relationship between low-resolution and high-resolution, and shows up to 0.14dB performance improvement and enhanced subjective image quality compared to the existing algorithm at large scaling factor result.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.540-541
• /
• 2018

In this paper, we propose an super-resolution method that improves resolution by using DWT (Discrete Wavelet Transform) for low resolution infra-red images. In this method, DWT is performed in a manner that does not reduce the resolution of an image input through an infra-red camera to generate sub-bands of the same resolution (LH, HL, and HH) And the original infra-red image is used to perform an inverse-DWT to obtain an infra-red image with improved resolution. Experimental results show that the mean SSIM value of the proposed method is 0.989861, which is about 0.004 higher than that of the conventional Bi-linear and Bi-cubic filters.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.3
• /
• pp.154-161
• /
• 2015

A novel multiframe super-resolution (SR) algorithm is presented to overcome the limitation of existing single-image SR algorithms using motion information from adjacent frames in a video. The proposed SR algorithm consists of three steps: i) definition of a local region using interframe motion vectors, ii) multiscale patch generation and adaptive selection of multiple optimum patches, and iii) combination of optimum patches for super-resolution. The proposed algorithm increases the accuracy of patch selection using motion information and multiscale patches. Experimental results show that the proposed algorithm performs better than existing patch-based SR algorithms in the sense of both subjective and objective measures including the peak signal-to-noise ratio (PSNR) and structural similarity measure (SSIM).

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.264-267
• /
• 2015

본 논문에서는 개선된 고속의 Back Projection 기법과 에지맵 보간을 이용한 단일영상 기반의 초해상도(super resolution) 영상을 생성하는 알고리즘을 제안한다. 본 논문에서 제안하는 알고리즘은 영상의 색채 왜곡을 방지하기 위해 RGB 컬러 도메인에서 HSV 컬러 도메인으로 변경하여 밝기정보인 V만 이용한다. 먼저 잡음제거와 속도 향상을 위해 개선된 고속 back projection을 이용해 영상을 확대 재구성한다. 이와 함께 LoG(laplacian of gaussian) 필터링을 이용하여 에지 맵을 추출한다. 에지의 정보와 back projection의 결과를 이용하여 고해상도 영상을 재구성한다. 제안하는 알고리즘을 이용하여 복원한 영상은 부자연스러운 인공물을 효과적으로 제거하고, blur현상을 줄여 에지 정보를 보정하고 강조해준다. 또한 실험을 통해 제안하는 알고리즘이 기존의 보간법과 전통적인 back projection 결과보다 주관적인 화질이 우수하고 객관적으로 우수한 성능을 나타내는 것을 입증한다.