• 전기학회논문지
• /
• 제57권2호
• /
• pp.294-302
• /
• 2008

In this paper, we present a new image up-sampling method which registers low resolution images to the high resolution grid when Bayesian super-resolution image processing is performed. The proposed up-sampling method interpolates high-resolution pixels using high-frequency data lying in all the low resolution images, instead of up-sampling each low resolution image separately. The interpolation is based on B-spline non-uniform re-sampling, adjusted for the super-resolution image processing. The experimental results demonstrate the effects when different up-sampling methods generally used such as zero-padding or bilinear interpolation are applied to the super-resolution image reconstruction. Then, we show that the proposed hybird up-sampling method generates high-resolution images more accurately than conventional methods with quantitative and qualitative assess measures.

• 한국측량학회지
• /
• 제31권6_2호
• /
• pp.559-565
• /
• 2013

Spatial resolution of land covers from remotely sensed images can be increased using super-resolution mapping techniques for soft-classified land cover proportions. A further development of super-resolution mapping technique is downscaling the original remotely sensed image using super-resolution mapping techniques with a forward model. In this paper, the model for increasing spatial resolution of remote sensing multispectral image is tested with real SPOT 5 imagery at 10m spatial resolution for an area in Bac Giang Province, Vietnam in order to evaluate the feasibility of application of this model to the real imagery. The soft-classified land cover proportions obtained using a fuzzy c-means classification are then used as input data for a Hopfield neural network (HNN) to predict the multispectral images at sub-pixel spatial resolution. The 10m SPOT multispectral image was improved to 5m, 3,3m and 2.5m and compared with SPOT Panchromatic image at 2.5m resolution for assessment.Visually, the resulted image is compared with a SPOT 5 panchromatic image acquired at the same time with the multispectral data. The predicted image is apparently sharper than the original coarse spatial resolution image.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.197-200
• /
• 2005

Super resolution image reconstruction method refers to image processing algorithms that produce a high resolution(HR) image from observed several low resolution(LR) images of the same scene. This method is proved to be useful in many practical cases where multiple frames of the same scene can be obtained, such as satellite imaging, video surveillance, video enhancement and restoration, digital mosaicking, and medical imaging. In this paper we applied super resolution reconstruction method in spatial domain to video sequences. Test images are adjacently sampled images from continuous video sequences and overlapped for high rate. We constructed the observation model between the HR images and LR images applied by the Maximum A Posteriori(MAP) reconstruction method that is one of the major methods in the super resolution grid construction. Based on this method, we reconstructed high resolution images from low resolution images and compared the results with those from other known interpolation methods.

• 한국컴퓨터그래픽스학회논문지
• /
• 제25권3호
• /
• pp.21-29
• /
• 2019

본 논문에서는 구조-텍스처 분할 기법을 기반으로 위성영상을 분할 융합하여 공간 해상도를 개선시키는 프레임워크를 제시한다. 위성영상은 센서가 감지하는 파장에 따라 다양한 공간해상도를 가진다. 전정 영상 (panchromatic image)은 일반적으로 높은 공간해상도를 가지지만 단일 흑백컬러를 가지고 있는 반면, 다중분광 영상 (multi-spectral image)나 적외선 영상은 전정 영상에 비해 낮은 공간해상도를 가지지만 다양한 분광 밴드정보와 열 정보를 가지고 있다. 본 논문에서는 다중분광 영상이나 적외선 영상의 공간 해상도를 향상시키기 위해 영상의 디테일이 텍스처 영상에만 존재한다는 것에 착안하여 본 프레임워크를 고안하였다. 고안된 프레임워크에서는 저해상도 영상과 고해상도 영상이 구조 영상과 텍스처 영상으로 분할된 뒤, 저해상도 구조영상은 고해상도 구조 영상을 참조하여 가이디드 필터링 된다. 구조-텍스처 영상 모델에 따라 필터링된 저해상도 영상의 구조 영역과 고해상도 영상의 텍스처 영역을 픽셀 단위로 더해져서 최종 영상이 생성된다. 생성된 영상은 저해상도 영상의 밴드와 고해상도 영상의 디테일을 포함한다. 제시하는 방법은 분광해상도와 공간해상도를 모두 보존할 수 있음을 실험적으로 확인하였다.

• 전자공학회논문지
• /
• 제51권3호
• /
• pp.105-111
• /
• 2014

영상 해상도 개선은 저해상도 획득 영상의 해상도를 개선하여 고해상도 영상을 생성하는 기술이다. 영상 해상도 개선을 위해서는 저해상도 획득 영상의 열화 과정에서 발생하는 손실된 화소 정보를 정확하게 추정하는 것이 중요하다. 따라서 본 논문에서는 영상 해상도 개선을 위한 다중 부족분 추정 방법을 제안한다. 제안하는 방법은 획득 영상의 부영상 집합에 알려진 열화 및 복원 과정을 수행하여 서로 다른 형태의 다중 부족분을 추정하고, 추정된 부족분과 획득 영상의 보간 영상의 결합을 통해서 결과 영상을 생성하고, 디블러링을 수행하여 최종 복원 영상을 생성한다. 객관적 화질 측정 지표인 PSNR, SSIM, FSIM으로 비교한 결과 제안한 방법이 보간만을 사용하는 방법들보다 높은 값을 가지는 것을 확인하였다. 또한 결과 영상의 시각적 비교 결과 주관적 관점의 화질도 가장 뛰어난 것을 알 수 있었고, 보간만을 사용하는 방법들보다 빠른 계산시간을 가지는 것을 확인할 수 있었다. 제안하는 방법은 영상 해상도 개선을 위한 응용 환경에서 유용하게 사용될 수 있다.

• 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.

• 한국통신학회논문지
• /
• 제34권10B호
• /
• pp.1124-1132
• /
• 2009

본 논문은 집적영상의 요소영상을 초해상도 영상복원에 이용하여 집적영상의 해상도를 향상시키는 방법을 제안한다. 집적영상에서 전체 요소영상의 인접한 단일 요소영상들 사이에는 대상물체의 동일한 부분의 상을 포함하는 공통부분이 존재한다. 이러한 공통부분들을 초해상도 영상복원의 저해상도 영상으로 이용하게 되면 CCD(Charge Coupled Device) 등의 영상취득 장치의 제한된 해상도로 인한 집적영상의 낮은 해상도 문제를 보완 할 수 있게 된다. 전체 요소영상과 제안된 방법을 이용하여 해상도를 향상시킨 전체 요소영상을 비교하여 제안된 방법의 타당성을 증명하였다.

• 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.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2004년도 봄 학술발표논문집 Vol.31 No.1 (B)
• /
• pp.715-717
• /
• 2004

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on a recursive error back-projection of top-down machine learning. A face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes, In addition to, a recursive error back-projection is applied to improve the accuracy of synthesized high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution one captured at a distance.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2007년도 춘계학술발표회 논문집
• /
• pp.141-144
• /
• 2007

Satellite image for national land monitoring is required high resolution and natural color with multi spectral band. the image is expensive as higher resolution. We need cheap image relatively in economic viewpoint but the image serves sufficient resolution to monitor national land. We merged two images to one image and evaluated the result. the two images which are used at the merge test are high resolution(2.5m per pixel) panchromatic and low resolution(10m per pixel) multi spectral image of SPOT-5 satellite. The result of this study. We made the merge image to have sufficient resolution for national monitoring.