• 대한전자공학회논문지SP
• /
• 제43권2호
• /
• pp.12-18
• /
• 2006

이 논문은 저해상도 동영상에서 자동화된 방식으로 한 장의 좋은 화질의 고해상도 영상을 얻는 방안을 제시한다. 여러 장의 저해상도 영상을 이용하여 고해상도 영상을 얻는 방법이 한 장의 저해상도 영상만을 이용하는 전통적인 보간 방법에 비해 좋은 결과를 보이기 위해서는 입력 영상들이 공통된 고해상도 격자에 잘 정합되어야 하므로, 정합오차를 충분히 고려하여 입력영상들을 주의 깊게 선택한다. 본 논문에서는 움직임 보상된 저해상도 영상들로부터 얻어진 통계적 특성을 활용하여 입력 영상 후보들의 입력 영상으로서의 적합성을 평가한다. 고해상도 영상획득모델로부터 움직임 보상오차의 최대값을 추정한다. 입력 영상 후보의 움직임 보상오차가 추정된 움직임 보상오차의 최대값보다 크면 입력 영상후보는 선정에서 제외된다. 선정된 적절한 유효 입력 영상 후보의 수와 움직임 보상오차의 통계치를 고려하여 최종 입력 영상들을 선별한다. 입력 영상 선별부에서 최종적으로 선별된 입력 영상들은 뒤따르는 고해상도 영상복원부로 입력된다. 제안된 방식은 사용자의 간섭없이 저해상도 동영상에서 효과적으로 입력 영상들을 선별하여 좋은 화질의 고해상도 영상을 얻는 응용에 사용될 것으로 기대된다.

• 대한원격탐사학회지
• /
• 제23권6호
• /
• pp.547-552
• /
• 2007

본 연구에서는 고해상도의 panchromatic 영상을 이용하여 저해상도의 multispectral 영상을 고해상도로 재구축하는 방법을 제시하고 있다. 제안된 방법은 저해상도와 고해상도 간의 선형 모형 사용하여 실제의 spectral 값에 부합하는 고해상도 영상을 재구축하며 두 단계로 이루어 진다. 첫 단계는 고해상도 feature와 연관된 저해상도의 선형 모형을 이용하여 최소 자승 오류 법에 의한 global 추정 과정이고 두 번째 단계는 재구축된 영상을 지역적으로 원래의 spectral 값과 일관되게 만드는 local 수정 과정이다. 본 연구에서 제안 방법을 이용하여 6m KOMPSAT-1 EOC 자료와 30m LANDSAT ETM+에 적용하였고 또한 IKONOS 1m RGB 영상 생성하였다. 실험 결과는 새로이 제시된 방법이 저해상도 Multispectral 영상의 고해상도 재구축에 탁월한 성능을 가지고 있음을 보여주었다.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2009년도 춘계학술대회 논문집
• /
• pp.455-457
• /
• 2009

The purposes of this study are to consider the influence of topography resolution on atmospheric flow simulation and to suggest a method of atmospheric flow simulation using a low-resolution DEM. Simulations using a low-resolution DEM has more critical error at near surface than simulations using high-resolution DEM because it is ignored the small curve topography of high-resolution DEM. Therefore when we convert the height differences between low-resolution DEM and high-resolution DEM into the topography roughness, we can be able to reduce the error on atmospheric flow simulations.

• 스마트미디어저널
• /
• 제8권4호
• /
• pp.64-71
• /
• 2019

The performance of an OMR (Optical Music Recognition) system is usually determined by the characterizing features of the input music score images. Low resolution is one of the main factors leading to degraded image quality. In this paper, we handle the low-resolution problem using the super-resolution technique. We propose the use of a deep neural network with instance normalization to improve the quality of music score images. We apply instance normalization which has proven to be beneficial in single image enhancement. It works better than batch normalization, which shows the effectiveness of shifting the mean and variance of deep features at the instance level. The proposed method provides an end-to-end mapping technique between the high and low-resolution images respectively. New images are then created, in which the resolution is four times higher than the resolution of the original images. Our model has been evaluated with the dataset "DeepScores" and shows that it outperforms other existing methods.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 추계학술발표대회
• /
• pp.781-784
• /
• 2017

얼굴인식 시스템은 비접촉데이터 채집의 특성과 함께, 그 정확도가 점차 향상되고 있다. 공공 감시카메라와 같이 사진을 멀리서 찍는 상황에서는 저해상도의 얼굴 이미지로 인해 얼굴인식 시스템을 효과적으로 사용할 수 없는 경우가 있다. 이론적으로는 저해상도영상을 Super Resolution (SR) 방법으로 고해상도 영상으로 바꾸어 얼굴인식에 사용할 수 있지만, 기존의 SR 방법들은 얼굴 인식에 만족할만한 결과를 내지 못할 수 있다. 이 논문은 극 저해상도 (very low resolution) 얼굴인식 문제를 살펴보고 편미분방정식 기반 SR 방법을 제안하고, CNN 기반 얼굴인식 시스템에 응용한다.

• 한국멀티미디어학회논문지
• /
• 제18권9호
• /
• pp.1039-1046
• /
• 2015

We propose a feature generation method for low-resolution face recognition. For this, we first generate new features from the input features (pixels) of a low-resolution face image by adding the higher-order terms. Then, we evaluate the separability of both of the original input features and new features by computing the discriminant distance of each feature. Finally, new data sample used for recognition consists of the features with high separability. The experimental results for the FERET, CMU-PIE and Yale B databases show that the proposed method gives good recognition performance for low-resolution face images compared with other method.

• 천문학회보
• /
• 제44권1호
• /
• pp.52.1-52.1
• /
• 2019

The Helioseismic and Magnetic Imager (HMI) is the instrument of Solar Dynamics Observatory (SDO) to study the magnetic field and oscillation at the solar surface. The HMI image is not enough to analyze very small magnetic features on solar surface since it has a spatial resolution of one arcsec. Super resolution is a technique that enhances the resolution of a low resolution image. In this study, we use a method for enhancing the solar image resolution using a Deep-learning model which generates a high resolution HMI image from a low resolution HMI image (4 by 4 binning). Deep learning networks try to find the hidden equation between low resolution image and high resolution image from given input and the corresponding output image. In this study, we trained a model based on a very deep residual channel attention networks (RCAN) with HMI images in 2014 and test it with HMI images in 2015. We find that the model achieves high quality results in view of both visual and measures: 31.40 peak signal-to-noise ratio(PSNR), Correlation Coefficient (0.96), Root mean square error (RMSE) is 0.004. This result is much better than the conventional bi-cubic interpolation. We will apply this model to full-resolution SDO/HMI and GST magnetograms.

• 대한원격탐사학회지
• /
• 제27권6호
• /
• pp.625-635
• /
• 2011

This paper investigates the effects of spatial autocorrelation structures in low resolution data on downscaling without ground measurements or secondary data, as well as the potential of geostatistical downscaling. An advanced geostatistical downscaling scheme applied in this paper consists of two analytical steps: the estimation of the point-support spatial autocorrelation structure by variogram deconvolution and the application of area-to-point kriging. Point kriging of block data without variogram deconvolution is also applied for a comparison purpose. Experiments using two low resolution thematic maps derived from remote sensing data showing very different spatial patterns are carried out to discuss the objectives. From the experiments, it is demonstrated that the advanced geostatistical downscaling scheme can generate the downscaling results that well preserve overall patterns of original low resolution data and also satisfy the coherence property, regardless of spatial patterns in input low resolution data. Point kriging of block data can produce the downscaling result compatible to that by area-to-point kriging when the spatial continuity in block data is strong. If heterogeneous local variations are dominant in input block data, the treatment of the low resolution data as point data cannot generate the reliable downscaling result, and this simplification should not be applied to donwscaling.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• 천문학회보
• /
• 제44권2호
• /
• pp.70.4-70.4
• /
• 2019

Image super-resolution (SR) is a technique that enhances the resolution of a low resolution image. In this study, we use three SR models (RCAN, ProSRGAN and Bicubic) for enhancing solar SDO/HMI magnetograms using deep learning. Each model generates a high resolution HMI image from a low resolution HMI image (4 by 4 binning). The pixel resolution of HMI is about 0.504 arcsec. Deep learning networks try to find the hidden equation between low resolution image and high resolution image from given input and the corresponding output image. In this study, we trained three models with HMI images in 2014 and test them with HMI images in 2015. We find that the RCAN model achieves higher quality results than the other two methods in view of both visual aspects and metrics: 31.40 peak signal-to-noise ratio(PSNR), Correlation Coefficient (0.96), Root mean square error (RMSE) is 0.004. This result is also much better than the conventional bi-cubic interpolation. We apply this model to a full-resolution SDO/HMI image and compare the generated image with the corresponding Hinode NFI magnetogram. As a result, we get a very high correlation (0.92) between the generated SR magnetogram and the Hinode one.