Earticle

본 논문에서는 함정전투체계의 EOTS나 IRST에서 획득한 영상을 초고해상도 영상으로 복원한다. 저해상도에서 초고해상도의 영상을 생성하는 생성 모델과 이를 판별하는 판별 모델로 구성된 생성적 적대 신경망을 이용하고, 다양한 학습 파라미터의 변화를 통한 최적의 값을 제안한다. 실험에 사용되는 학습 파라미터는 crop size와 sub-pixel layer depth, 학습 이미지 종류로 구성되며, 평가는 일반적인 영상 품질 평가 지표에 추가적으로 특징점 추출 알고리즘을 함께 사용하였다. 그 결과, Crop size가 클수록, Sub-pixel layer depth가 깊을수록, 고해상도의 학습이미지를 사용할수록 더 좋은 품질의 영상을 생성한다.

In this paper, we perform Single Image Super Resolution(SISR) for acquired images of EOTS or IRST from naval combat system. In order to conduct super resolution, we use Generative Adversarial Networks(GANs), which consists of a generative model to create a super-resolution image from the given low-resolution image and a discriminative model to determine whether the generated super-resolution image is qualified as a high-resolution image by adjusting various learning parameters. The learning parameters consist of a crop size of input image, the depth of sub-pixel layer, and the types of training images. Regarding evaluation method, we apply not only general image quality metrics, but feature descriptor methods. As a result, a larger crop size, a deeper sub-pixel layer, and high-resolution training images yield good performance.

Image super resolution reconstruction has important significance in remote sensing image feature extraction and classification etc.. Because the remote sensing image size is larger, it is difficult to super resolution reconstruction using multiple images, the compressed sensing (CS) theory was introduced into the super-resolution reconstruction. Algorithm designed the low pass filter to reduce the sample correlation matrix and wavelet, at the same time, the algorithm selects the partial Hadamard-matrix as the measurement matrix, it has faster reconstruction speed and low storage requirements, which ensure that the image reconstruction keep with the RIP criterion of compressed sensing theory . Finally, this paper realizes the remote sensing image super resolution reconstruction through the improved iterative algorithm. Experiments show that the reconstructed images of the PSNR value has increased, the reconstructed image has a better visual effect.

In Bilateral Total Variation (BTV) regularized super-resolution reconstruction (SRR), the fidelity item is only applicable to a specific noise model, and the fixed weight of BTV regularization term cannot adapt to the changes in an image. Thus, this paper proposes a SRR algorithm based on the Tukey fidelity term and adaptive BTV regularization term. The Tukey fidelity term has a more effective outliers suppression feature to deal with complex noises, and the weight of adaptive BTV regularization term can resize itself according to the changes of image textures, which can achieve the purposes of suppressing noises and preserving edges. Experimental results show that, compared with other algorithms, the proposed algorithm has better vision effects and higher Peak Signal-to-noise Ratio (PSNR) values.

In this paper, we present a new approach to reconstruct a high resolution (HR) image from a low resolution (LR) input image based on a two dimensional (2D) sparse method. The new method consists of three phases. Firstly, the nonlinear feature of the input LR image is divided into the linear subspace, and then LR-HR dictionaries are learned to reduce the blurred artifacts of the image. Secondly, 2D sparse representation and self-similarity are developed to strengthen and enhance the image structure. Finally, the final HR image is achieved by reconstruction of all HR patches. Simulation results demonstrated that our proposed method achieved superior results on real images, and shows various improvements in terms of PSNR and SSIM values as compared with some other competent methods.

In the paper a weighted Projection onto to convex sets (POCS) algorithm for image super-resolution reconstruction is proposed, which using POCS scheme to reconstruct image without knowing the degradation model and related parameters. In the proposed algorithm, adaptive block matching is utilized to estimate translational motion among various images firstly, and then APRX algorithm is adopted to estimate the point spread function (PSF) and the ideal high resolution image. Finally based on the traditional POCS algorithm, the paper introduced the prior information about low resolution image definition into POCS to calculate the residual and control the threshold by weighted parameter of image relative definition, and realized the dynamic threshold selection in the whole progress of reconstruction. Results of experiments show that the algorithm in the objective evaluation and visual effects achieves better reconstruction results, which confirm the validity and robustness of the proposed algorithm.

The paper introduces the Keren registration method and points out its disadvantage which means it will become inaccuracy on the large scale parameters. To reduce the error on large scale parameters of Keren registration, a two step method is proposed, which the phase correlation algorithm is used to estimate the large translation and rotation angle roughly and the improved Keren algorithm is used to estimate accurately the small translation and rotation angle. The experimental results show that the two step method makes less absolute error of angle than Keren method in the situation of large translation and rotation angle. A new method of estimating the standard deviation of noise is introduced to the robust certainty function, which reduces the impact of noise in the process of interpolation using normalized convolution algorithm. By the edge detection of fusion image in the first stage of the interpolation process of normalized convolution algorithm, a calculation method of long axis and short axis of the structure self-adaptive function is improved. The experimental results show that the proposed interpolation method can improve the performance of the original algorithm and enhance the effect of image super-resolution reconstruction.

The High resolution (HR) images can be obtained from a set of noisy and blurred low resolution (LR) observations by applying the Super Resolution (SR) technique. In this paper a new SR algorithm that uses Singular Value Decomposition (SVD) based Fusion and Blind deconvolution techniques is proposed. The algorithm significantly improves the resolution and eliminates the noise and blur associated with low resolution images, when compared with the other existing methods.

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.

본 논문은 높은 품질 SR 이미지를 획득하기 위해 국소 그라디언트를 기반으로 적응형 보간법을 이용하는 SR 방법을 제공한다. 이 방법에서, 내삽 화소와 인접하는 유효한 화소 사이에 거리는 국소 그라디언트 특징을 이용하여 고려되며, 보간 계수는 LR 이미지의 국소 그라디언트를 고려한다. 픽셀의 국소 그라디언트는 더 작을수록, 그리고 메디안 필터는 보간된 HR 이미지의 블러링과 노이즈를 감소시키기 위해 적용된다. 실험 결과는 특히 이미지의 에지 부분에서, 다른 방법과 비교하여 제안된 방법의 유효성을 보여준다.

This paper presents a SR method using adaptive interpolation based on local gradient features to obtain a high quality SR image. In this method, the distance between the interpolated pixel and the neighboring valid pixel is considered by using local gradient properties. The interpolation coefficients take the local gradient of the LR images into account. The smaller the local gradient of a pixel is, the more influence it should have on the interpolated pixel. And the median filter is finally applied to reduce the blurring and noise of the interpolated HR image. Experiment results show the effectiveness of the proposed method in comparison with other methods, especially in the edge areas of the images.

Images with high resolution are desired and often required in many visual applications. When resolution can not be improved by replacing sensors, either because of cost or hardware physical limits, super resolution image reconstruction method is what can be resorted to. Super resolution image reconstruction method refers to image processing algorithms that produce high quality and high resolution images from a set of low quality and low resolution images. The method is proved to be useful in many practical cases where multiple frames of the same scene can be obtained, including satellite imaging, video surveillance, video enhancement and restoration, digital mosaicking, and medical imaging. The method can be either the frequency domain approach or the spatial domain approach. Much of the earlier works concentrated on the frequency domain formulation, but as more general degradation models were considered, later researches had been almost exclusively on spatial domain formulations. The method in spatial domains has three stages: i) motion estimate or image registration, ii) interpolation onto high resolution grid and iii) deblurring process. The super resolution grid construction in the second stage was discussed in this paper. We applied the Maximum A­Posteriori(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 a set of low resolution images and compared the results with those from other known interpolation methods.

초해상도 영상복원은 동일 지역을 촬영한 여러 장의 저해상도 영상을 이용하여 고해상도의 영상으로 재구성하는 영상처리 알고리즘 기법이다. 이 기법은 위성영상, 비디오 감시, 영상 강조 및 복원, 영상 모자이킹, 의료 영상과 같이 여러 장의 프레임 영상을 획득할 수 있는 분야에서 유용하게 사용될 수 있다. 본 연구에서는 지상을 촬영한 비디오 영상 열에 공간영역 초해상도 기법을 적용하였다. 실험에 사용된 영상은 높은 중복도로 촬영된 연속적인 비디오 영상에서 부표본화되었으며, 저해상도 영상과 고해상도 영상간의 관측 모델을 구성하고 초해상도 영상복원 기법중의 하나인 MAP 알고리즘을 적용하였다. MAP 기법을 이용하여 여러 장의 저해상도 영상에서 고해상도 영상으로 복원하였으며, 그 결과를 기존의 영상보간 방법들과 비교하였다.

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 has proven 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 the super resolution reconstruction method in spatial domain to video sequences. Test images are adjacently sampled images from continuous video sequences and are overlapped at high rate. We constructed the observation model between the HR images and LR images applied with the Maximum A Posteriori(MAP) reconstruction method which is one of the major methods in the super resolution grid construction. Based on the MAP method, we reconstructed high resolution images from low resolution images and compared the results with those from other known interpolation methods.

Background The recently introduced super-resolution (SR) deep learning image reconstruction (DLR) is potentially effective in reducing noise level and enhancing the spatial resolution. We aimed to investigate whether SR-DLR has advantages in the overall image quality and intensity homogeneity on coronary computed tomography (CT) angiography with four different approaches: filtered-back projection (FBP), hybrid iterative reconstruction (IR), DLR, and SR-DLR. Methods Sixty-three patients (mean age, 61 ± 11 years; range, 18?81 years; 40 men) who had undergone coronary CT angiography between June and October 2022 were retrospectively included. Image noise, signal to noise ratio, and contrast to noise ratio were quantified in both proximal and distal segments of the major coronary arteries. The left ventricle myocardium contrast homogeneity was analyzed. Two independent reviewers scored overall image quality, image noise, image sharpness, and myocardial homogeneity. Results Image noise in Hounsfield units (HU) was significantly lower (P < 0.001) for the SR-DLR (11.2 ± 2.0 HU) compared to those associated with other image reconstruction methods including FBP (30.5 ± 10.5 HU), hybrid IR (20.0 ± 5.4 HU), and DLR (14.2 ± 2.5 HU) in both proximal and distal segments. SR-DLR significantly improved signal to noise ratio and contrast to noise ratio in both the proximal and distal segments of the major coronary arteries. No significant difference was observed in the myocardial CT attenuation with SR-DLR among different segments of the left ventricle myocardium (P = 0.345). Conversely, FBP and hybrid IR resulted in inhomogeneous myocardial CT attenuation (P < 0.001). Two reviewers graded subjective image quality with SR-DLR higher than other image reconstruction techniques (P < 0.001). Conclusions SR-DLR improved image quality, demonstrated clearer delineation of distal segments of coronary arteries, and was seemingly accurate for quantifying CT attenuation in the myocardium.

본 논문에서는 시차의 신뢰도를 기반으로 플렌옵틱 영상의 초고해상도 복원 알고리즘을 제안한다. 그리고 플렌옵틱 카메라 영상으로부터 생성한 서브어퍼처(sub-aperture) 이미지는 TV_L1알고리즘에 기반한 시차 추정과 초고해상도 영상 복원에 활용된다. 특히 제안된 알고리즘은 시차가 부정확하게 나타날 수 있는 경계 역역에서 향상된 성능을 보인다. 시차 벡터의 신뢰도는 서브어퍼처 이미지의 상하좌우 각 위치별 영역에 따른 분산을 고려하여 판단한다. 신뢰도가 낮은 시차벡터는 초고해상도 영상 복원시 제외된다. 제안된 방법은 바이큐빅 보간 방법과 기존의 시차기반방법 그리고 사전기반 방법과 비교하여 평가되었다. 성능 평가에서 초고해상도 영상복원의 결과는 PSNR, SSIM 관점에서 성능을 비교하여 최상의 성능을 보여준다.

In this paper, we propose a super-resolution reconstruction algorithm for plenoptic images based on the reliability of disparity. The subperture image generated by the Flanoptic camera image is used for disparity estimation and reconstruction of super-resolution image based on TV_L1 algorithm. In particular, the proposed image reconstruction method is effective in the boundary region where disparity may be relatively inaccurate. The determination of reliability of disparity vector is based on the upper, lower, left and right positional relationship of the sub-aperture image. In our method, the unreliable vectors are excluded in reconstruction. The performance of the proposed method was evaluated by comparing to a bicubic interpolation method, a conventional disparity based method and dictionary based method. The experimental results show that the proposed method provides the best performance in terms of PSNR(Peak Signal to noise ratio), SSIM(Structural Similarity).

초해상도 영상복원은 저해상도 영상을 이용하여 하나의 고해상도 영상을 획득하는 기법이다. 초해상도 영상복원은 크게 두 가지 방법으로 구현된다. 단일 영상을 이용한 초해상도 영상복원과, 여러 장의 저해상도 영상을 이용한 초해상도 영상복원 기법이 연구되고 있다. 여러 장의 저해상도 영상을 이용한 공간영역에서의 초해상도 영상복원 알고리즘은 크게 정합, 보간, 후처리 과정을 거치게 된다. 본 논문에서는 정합과정 이전에 입력영상보정을 통한 전처리과정을 수행하여 잡음으로 인한 부정확한 위치정보추정 확률을 감소시키고, 입력영상보정과정인 전처리과정으로 인해 후처리과정을 통한 영상복원 영상보다 향상된 영상을 획득하는 기법을 제안하며, 실험결과에서 기존의 방법보다 좋은 영상을 얻음을 확인하였다.

초해상도 영상복원은 저해상도 영상을 이용하여 하나의 고해상도 영상을 획득하는 기법이다. 초해상도 영상복원은 크게 두 가지 방법으로 구현된다. 단일 영상을 이용한 초해상도 영상복원과, 여러 장의 저해상도 영상을 이용한 초해상도 영상복원 기법이 연구되고 있다. 여러 장의 저해상도 영상을 이용한 공간영역에서의 초해상도 영상복원 알고리즘은 크게 정합, 보간, 후처리 과정을 거치게 된다. 본 논문에서는 정합과정 이전에 입력영상보정을 통한 전처리과정을 수행하여 잡음으로 인한 부정확한 위치정보추정 확률을 감소시키고, 입력영상보정과정인 전처리과정으로 인해 후처리과정을 통한 영상복원 영상보다 향상된 영상을 획득하는 기법을 제안하며, 실험결과에서 기존의 방법보다 좋은 영상을 얻음을 확인하였다.

본 논문에서는 다시점 영상을 이용한 초고해상도 영상 복원 기법을 제안한다. 구체적으로 $5{\times}5$ 배열로 구성된 다시점 카메라로 25장의 영상을 취득하고, 가운데 카메라에 해당하는 초고해상도 영상을 저해상도 입력 영상과 24장의 저해상도 참조 영상을 활용하여 생성한다. 우선 입력 영상을 중심으로 스테레오 정합 기법을 이용하여 24개의 참조 영상에 대한 변이지도를 각각 추정한다. 그리고 저해상도 영상과 참조 영상에 있는 일치점들을 이용하여 초고해상도 영상을 복원한다. 최종적으로 반복적 균일화를 통해 초고해상도 영상을 보정한다. 실험을 통하여 본 논문에서 제안한 초고해상도 영상 복원 기법의 성능이 우수함을 확인한다.

In this paper, we propose a super-resolution (SR) image reconstruction algorithm using multi-view images. We acquire 25 images from multi-view cameras, which consist of a $5{\times}5$ array of cameras, and then reconstruct an SR image of the center image using a low resolution (LR) input image and the other 24 LR reference images. First, we estimate disparity maps from the input image to the 24 reference images, respectively. Then, we interpolate a SR image by employing the LR image and matching points in the reference images. Finally, we refine the SR image using an iterative regularization scheme. Experimental results demonstrate that the proposed algorithm provides higher quality SR images than conventional algorithms.

Inherent opportunities on research for restoring high resolution image from low resolution images are increasing in these days. Super resolution image reconstruction is the process of combining multiple low resolution images to form a higher resolution one. To achieve super resolution reconstruction, proper observation model which is based on subpixel shift information is required. In this context, the importance of the subpixel registration cannot be estimated because subpixel shift information cannot be obtained from original image. This paper presents a regularized adaptive super resolution reconstruction method based on phase correlated subpixel registration, where the Constrained Least Squares(CLS) Restoration is adopted as a post process.

콘크리트 터널과 같은 지하 구조물의 안전한 유지관리는 균열과 같은 열화 현상을 조기에 탐지하는 데 필수적이다. 노후구조물이 증가함에 따라, 효율적인 안전 관리를 위해 다양한 컴퓨터비전 기술이 구조물 유지 관리에 활용되고 있다. 그러나 현장에서 수집된 영상은 여러 이유로 저해상도 및 저품질로 수집될 수 있으며, 이는 특히 딥러닝을 활용한 균열 탐지에서 정확도 저하로 이어질 수 있다. 따라서, 본 연구에서는 초해상화 알고리즘을 적용하여 저해상도 영상에서도 높은 탐지 성능을 유지할 수 있는 방법을 제안하였다. 다양한 비율의 저해상도 영상을 대상으로 초해상화 알고리즘을 적용하여 균열을 효과적으로 탐지하는 방안을 제시하고, 이를 통해 여러 초해상화 알고리즘의 효용성을 검토하였다. 실험을 통해 제안된 방법이 다양한 입력 데이터 조건에서도 안정적이고 향상된 균열 탐지 성능을 나타냄을 확인하였다. 본 연구는 터널 유지 관리 측면에서 초해상화 알고리즘의 활용 가능성을 보여주며, 향후 실제 터널 유지관리에서 정확한 관리에 기여할 것으로 기대된다.

The maintenance of underground structures, such as concrete tunnels, is essential for the early detection of deterioration phenomena, such as cracks. As the number of aging structures increases, various computer-vision technologies are being applied to efficiently maintain these aging structures. However, images collected in the field can often be low-resolution and low-quality due to various reasons, which can lead to reduced accuracy, especially in crack detection using deep learning. Therefore, this study proposes a method to maintain high detection performance even in low-resolution images by applying super-resolution algorithms. By applying super-resolution algorithms to images with varying proportions of low-quality images, we present an effective method for crack detection and evaluate the utility of several super-resolution algorithms. The experimental results confirmed that the proposed method exhibits stable and improved crack detection performance across various input data conditions. This study demonstrates the potential of super-resolution algorithms in tunnel maintenance and is expected to contribute to accurate maintenance in future real-world tunnel management.

본 논문에서는 SR(Super Resolution) 복원 과정에 있어 사용되는 입력 후보 영상 중 적합한 입력 영상을 자동 선택하는 알고리즘을 제안함으로써 복원된 고해상도 영상의 질을 개선하고자 한다. SR 복원과정에서 이상적인 결과 영상을 얻기 위해서는 입력되는 모든 영상이 유기적으로 잘 정합 되어야 하지만, 실제로는 그렇지 못하다. 이런 이유로 입력 후보군 영상의 정합 적합성이 얼마나 높은가가 단순히 많은 입력 영상의 수보다 고품질의 고해상도 결과 영상을 얻는데 더욱 결정적이라 할 수 있다. 입력 영상의 적합성은 통계 특성 및 정합 특성을 이용하여 평가 가능하다. 그러므로 본 논문에서는 SR 복원과정에 정합 적합성을 자동으로 평가하여 이에 따라 입력 영상을 결정하는 전처리 과정을 제안하고 구조화하였다. 또한 비디오 시퀀스의 모든 입력 영상은 SR 복원과정의 기준 영상이나 저해상도 입력 영상과 같이 사용될 수 있으므로 본 논문에서는 연속적인 비디오 시퀀스를 위한 SR 복원알고리즘을 제안한다. 적합성의 유무는 임계값(Threshold Value)에 의해 결정되며, 이 임계값은 기준 영상과의 움직임 추정에서 그 보상 값의 오류 값 중 최대치(MMCE, Maximum Motion Compensation Error)로 결정된다. 만약 저해상도 입력 영상의 보상 오류 값의 범위가 0과 MMCE사이(0 < MCE < MMCE )값이라면 그 범위 안의 입력 후보 영상은 SR 복원과정에 사용되며 범위 밖의 후보영상은 제외된다. 최적의 저해상도 기준(ORLR, Optimal Reference Low Resolution)영상은 선택된 저해상도 입력(SLRI, Selected LR Input)영상들과 각각의 저해상도 기준 입력(RLRI, Reference Low Resolution Input)영상들의 비교를 통해 결정된다. 본 논문에서는 이와 같은 과정에 의해 결정된 저해상도의 최적 기준영상과 선택영상을 'Hardie' 보간법을 사용하여 고해상도 영상을 만들어 내는 것으로 사용자의 조정이 없이도 SR 복원영상의 질적 향상을 가져올 것이라 기대된다.

In this paper, we propose the input image selection-method to improve the reconstructed high-resolution (HR) image quality. To obtain ideal super-resolution (SR) reconstruction image, all input images are well-registered. However, the registration is not ideal in practice. Due to this reason, the selection of input images with low registration error (RE) is more important than the number of input images in order to obtain good quality of a HR image. The suitability of a candidate input image can be determined by using statistical and restricted registration properties. Therefore, we propose the proper candidate input Low Resolution(LR) image selection-method as a pre-processing for the SR reconstruction in automatic manner. In video sequences, all input images in specified region are allowed to use SR reconstruction as low-resolution input image and/or the reference image. The candidacy of an input LR image is decided by the threshold value and this threshold is calculated by using the maximum motion compensation error (MMCE) of the reference image. If the motion compensation error (MCE) of LR input image is in the range of 0 < MCE < MMCE then this LR input image is selected for SR reconstruction, else then LR input image are neglected. The optimal reference LR (ORLR) image is decided by comparing the number of the selected LR input (SLRI) images with each reference LR input (RLRI) image. Finally, we generate a HR image by using optimal reference LR image and selected LR images and by using the Hardie's interpolation method. This proposed algorithm is expected to improve the quality of SR without any user intervention.