• The Journal of the Korea Contents Association
• /
• v.10 no.12
• /
• pp.34-42
• /
• 2010

The DOA(direction of arrival), which is based on parametric and nonparametric estimation algorithm, and adaptive beamforming algorithm for mobile communication environments are researched and analyzed. In parametric estimation algorithm, eigenvalues of the signal component and the noise component are obtained from correlation matrix of received signal by array antenna and power spectrum of the received signal is discriminated from them. Otherwise, in nonparametric estimation algorithm, we minimize a regularized objective function for finding a estimate of the signal energy as a function of angle, using nonquadratic norm which leads to supper resolution and noise suppression. And then, DOA is estimated by the signal and noise spatial steering vector, and adaptive beam-forming pattern is improved by weight vectors obtained from the spatial vector. Therefore, the improved directional estimation algorithm with regularizing sparsity constraints offers super-resolution and noise suppression compared to other algorithms.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.1
• /
• pp.18-23
• /
• 2008

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.

• Communications of the Korean Mathematical Society
• /
• v.16 no.3
• /
• pp.445-458
• /
• 2001

The shape and the distribution of material construction of the scatterer may be obtained from its scattered fields by the iterative inversion in the spectral domain. The illposedness, the resolution, and the uniqueness of the inversion are the key problems in the inversion and inter-related. The illposedness is shown to be caused by the evanescent modes which carries and amplifies exponentially the measurement errors in the back-propagation of the measured scattered fields. By filtering out all the evanescent modes in the cost functional defined as the squared difference between the measured and the calculated spatial spectrum of the scattered fields from the iteratively chosen medium parameters of the scatterer, one may regularize the illposedness of the inversion in the expense of the resolution. There exist many local minima of the cost functional for the inversion of the large and the high-contrast scatterer and the hybrid algorithm combining the genetic algorithm and the Levenberg-Marquardt algorithm is shown to find efficiently its global minimum. The resolution of reconstruction obtained by keeping all the propating modes and filtering out the evanescent modes for the regularization becomes 0.5 wavelength. The super resolution may be obtained by keeping the evanescent modes when the measurement error and instance, respectively, are small and near.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.104-123
• /
• 2022

Style transfer based on neural network provides very high quality results by reflecting the high level structural characteristics of images, and thereby has recently attracted great attention. This paper deals with the problem of resolution limitation due to GPU memory in performing such neural style transfer. We can expect that the gradient operation for style transfer based on partial image, with the aid of the fixed size of receptive field, can produce the same result as the gradient operation using the entire image. Based on this idea, each component of the style transfer loss function is analyzed in this paper to obtain the necessary conditions for partitioning and padding, and to identify, among the information required for gradient calculation, the one that depends on the entire input. By structuring such information for using it as auxiliary constant input for partition-based gradient calculation, this paper develops a recursive algorithm for super high-resolution image style transfer. Since the proposed method performs style transfer by partitioning input image into the size that a GPU can handle, it can perform style transfer without the limit of the input image resolution accompanied by the GPU memory size. With the aid of such super high-resolution support, the proposed method can provide a unique style characteristics of detailed area which can only be appreciated in super high-resolution style transfer.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.21-32
• /
• 2022

Image labeling must be preceded in order to perform object detection, and this task is considered a significant burden in building a deep learning model. Tens of thousands of images need to be trained for building a deep learning model, and human labelers have many limitations in labeling these images manually. In order to overcome these difficulties, this study proposes a method to perform object detection without significant performance degradation, even though labeling some images rather than the entire image. Specifically, in this study, low-resolution oriental painting images are converted into high-quality images using a super-resolution algorithm, and the effect of SSIM and PSNR derived in this process on the mAP of object detection is analyzed. We expect that the results of this study can contribute significantly to constructing deep learning models such as image classification, object detection, and image segmentation that require efficient image labeling.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.113-117
• /
• 2020

Images were taken under various weather such as rain, haze, snow often show low visibility, which can dramatically decrease accuracy of some tasks in computer vision: object detection, segmentation. Besides, previous work to enhance image usually downsample the image to receive consistency features but have not yet good upsample algorithm to recover original size. So, in this research, we jointly implement removal streak in heavy rain image and super resolution using a deep network. We put forth a 2-stage network: a multi-model network followed by a refinement network. The first stage using rain formula in the single image and two operation layers (addition, multiplication) removes rain streak and noise to get clean image in low resolution. The second stage uses refinement network to recover damaged background information as well as upsample, and receive high resolution image. Our method improves visual quality image, gains accuracy in human action recognition task in datasets. Extensive experiments show that our network outperforms the state of the art (SoTA) methods.

• Journal of the Korea Society for Simulation
• /
• v.13 no.2
• /
• pp.1-12
• /
• 2004

This paper estimated the arrival angle and electric wave delay time using the space method law and the directions of arrival (DOA) estimation algorithm in case of signal correlation. Space method law is the method used to repress cross correlation before applying the weight value to the receiving signal. The values of the diagonal elements in the correlation matrix were averaged to replace as the diagonal elements value. In the area of wireless communication or mobile communication, there are high correlations in case of low delay time difference in multiple waves. This causes the quality of the communication to drop due to interference with the desired signal elements. This paper estimated the arrival angle and electric wave delay time using the space method law and the MUSIC algorithm. With the arrival angle algorithm, the arrival angle cannot be estimated below 5 in case of signal correlations because the angle resolution capacity decreases accordingly. The super resolution capacity was estimated to determine the arrival angle below 5 in this paper. In addition, the proposed algorithm estimated the short delay time difference to be below 20ns.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.1
• /
• pp.1-10
• /
• 2015

In urban area, since multipath and signal attenuations frequently occur due to street trees, street lights and buildings, it is difficult to obtain accurate navigation solution using GPS. As these problems also impact negatively on the INS/GPS coupled system, implementing advanced transportation systems such as autonomous navigation system and Intelligent Transportation System (ITS) become quite hard. For this reason, to alleviate deterioration of navigation system performance in urban area, direction information extraction algorithm using vision system is proposed in this paper. 2D Finite Rate of Innovation (FRI) technique is applied to extract lane edges. The proposed technique is simulated using road images and feasibility of proposed technique is analyzed through the simulation results.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.175-183
• /
• 2015

The proposed algorithm consists of two stages: the learning and synthesis stages. At the learning stage, we first collect various high-resolution (HR)-low-resolution (LR) text image pairs, and quantize the LR images, and extract HR-LR block pairs. Based on quantized LR blocks, the LR-HR block pairs are clustered into a pre-determined number of classes. For each class, an optimal 2D-FIR filter is computed, and it is stored into a dictionary with the corresponding LR block for indexing. At the synthesis stage, each quantized LR block in an input LR image is compared with every LR block in the dictionary, and the FIR filter of the best-matched LR block is selected. Finally, a HR block is synthesized with the chosen filter, and a final HR image is produced. Also, in order to cope with noisy environment, we generate multiple dictionaries according to noise level at the learning stage. So, the dictionary corresponding to the noise level of the input image is chosen, and a final HR image is produced using the selected dictionary. Experimental results show that the proposed algorithm outperforms the previous works for noisy images as well as noise-free images.