• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.98-101
• /
• 2019

At present, deep convolutional neural networks have made a very important contribution in single-image super-resolution. Through the learning of the neural networks, the features of input images are transformed and combined to establish a nonlinear mapping of low-resolution images to high-resolution images. Some previous methods are difficult to train and take up a lot of memory. In this paper, we proposed a simple and compact deep recursive residual network learning the features for single image super resolution. Global residual learning and local residual learning are used to reduce the problems of training deep neural networks. And the recursive structure controls the number of parameters to save memory. Experimental results show that the proposed method improved image qualities that occur in previous methods.

• Nuclear Engineering and Technology
• /
• v.53 no.1
• /
• pp.294-303
• /
• 2021

Various types of sensors are used at industrial sites to measure vibration. With the increase in the diversity of vibration measurement methods, vibration monitoring methods using camera equipment have recently been introduced. However, owing to the physical limitations of the hardware, the measurement resolution is lower than that of conventional sensors, and real-time processing is difficult because of extensive image processing. As a result, most such methods in practice only monitor status trends. To address these disadvantages, a high-resolution vibration measurement method using image analysis of the edge region of the structure has been reported. While this method exhibits higher resolution than the existing vibration measurement technique using a camera, it requires significant amount of computation. In this study, a method is proposed for rapidly processing considerable amount of image data acquired from vision equipment, and measuring the vibration of structures with high resolution. The method is then verified through experiments. It was shown that the proposed method can fast measure vibrations of structures remotely.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.221-224
• /
• 2010

When the image registration methods which were generally used to the low medium resolution satellite images is applied to the high spatial resolution images, some matching errors or limitations might be occurred because of the local distortions in the images. This paper, therefore, proposed the automatic image-to-image registration of high resolution satellite images using local properties of control points to improve the registration result.

• Spatial Information Research
• /
• v.13 no.4 s.35
• /
• pp.345-354
• /
• 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 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1604-1611
• /
• 2020

Light field image captured by a microlens array-based camera has many limitations in practical use due to its low spatial resolution and angular resolution. High spatial resolution images can be easily acquired with a single image super-resolution technique that has been studied a lot recently. But there is a problem in that high angular resolution images are distorted in the process of using disparity information inherent among images, and thus it is difficult to obtain a high-quality angular resolution image. In this paper, we propose light field angular super-resolution that extracts an initial feature map using an dilated convolutional neural network in order to effectively extract the view difference information inherent among images and generates target image using a residual neural network. The proposed network showed superior performance in PSNR and subjective image quality compared to existing angular super-resolution networks.

• Korean Journal of Remote Sensing
• /
• v.26 no.3
• /
• pp.317-324
• /
• 2010

In recent years, many automatic classification approaches have been employed. An automatic classification method can be effective, time-saving and can produce objective results due to the exclusion of operator intervention. This paper proposes a classification method based on automated training for high resolution multispectral images using ancillary data. Generally, it is problematic to automatically classify high resolution images using ancillary data, because of the scale difference between the high resolution image and the ancillary data. In order to overcome this problem, the proposed method utilizes the classification results of a Landsat image as a medium for automatic classification. For the classification of a Landsat image, a maximum likelihood classification is applied to the image, and the attributes of ancillary data are entered as the training data. In the case of a high resolution image, a K-means clustering algorithm, an unsupervised classification, was conducted and the result was compared to the classification results of the Landsat image. Subsequently, the training data of the high resolution image was automatically extracted using regular rules based on a RELATIONAL matrix that shows the relation between the two results. Finally, a high resolution image was classified and updated using the extracted training data. The proposed method was applied to QuickBird and SPOT-5 images of non-accessible areas. The result showed good performance in accuracy assessments. Therefore, we expect that the method can be effectively used to automatically construct thematic maps for non-accessible areas and update areas that do not have any attributes in geographic information system.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.63-66
• /
• 2018

Recently, a convolutional neural network (CNN) models at single image super-resolution have been very successful. Residual learning improves training stability and network performance in CNN. In this paper, we compare four convolutional neural network models for super-resolution (SR) to learn nonlinear mapping from low-resolution (LR) input image to high-resolution (HR) target image. Four models include general CNN model, global residual learning CNN model, local residual learning CNN model, and the CNN model with global and local residual learning. Experiment results show that the results are greatly affected by how skip connections are connected at the basic CNN network, and network trained with only global residual learning generates highest performance among four models at objective and subjective evaluations.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.125-127
• /
• 2004

High-resolution satellite images offer abundance information of the earth surface for remote sensing applications. The information includes geometry, texture and attribute characteristic. The pixel-based image classification can't satisfy high-resolution satellite image's classification precision and produce large data redundancy. Object-oriented information extraction not only depends on spectrum character, but also use geometry and structure information. It can provide an accessible and truly revolutionary approach. Using Beijing Spot 5 high-resolution image and object-oriented classification with the eCognition software, we accomplish the cultures' precise classification. The test areas have five culture types including water, vegetation, road, building and bare lands. We use nearest neighbor classification and appraise the overall classification accuracy. The average of five species reaches 0.90. All of maximum is 1. The standard deviation is less than 0.11. The overall accuracy can reach $95.47\%.$ This method offers a new technology for high-resolution satellite images' available applications in remote sensing culture classification.

• Nuclear Engineering and Technology
• /
• v.55 no.7
• /
• pp.2567-2571
• /
• 2023

Scintillator materials are widely used in the medical and industrial fields for imaging systems using gamma cameras. In this study, image evaluation is performed by modeling a gamma camera system based on a lutetium-yttrium oxyorthosilicate (LYSO) scintillation detector using a pinhole collimator that can improve the spatial resolution. A LYSO detector-based gamma camera system is modeled using a Monte Carlo simulation tool. The geometric concept of the pinhole collimator is designed using various magnification factors, and the spatial resolution is measured using the acquired source image. To evaluate the resolution, the full width at half maximum (FWHM) and natural image quality assessment (NIQE), a no-reference-based parameter, are used. We confirm that the FWHM and NIQE values decrease simultaneously when the diameter of the pinhole collimator increases. Additionally, we confirm that the spatial resolution improves as the magnification factor increases under the same pinhole diameter condition. Particularly, a 0.57 mm FWHM value is obtained using the modeled gamma camera system with a LYSO scintillation detector. In conclusion, our results demonstrate that a pinhole collimator with a LYSO scintillation detector is a promising gamma camera imaging system.

• Progress in Medical Physics
• /
• v.33 no.4
• /
• pp.63-71
• /
• 2022

Purpose: To clarify the relationship between the diameter of the simulated bead and the Z-resolution of the tomosynthesis image. Methods: A simulated bead was placed on a 1,024×1,024×1,024-pixel base image. The diameters were set to 0.025, 0.05, 0.1, 0.2, 0.3, 0.7, 1.0, and 1.3 mm. A bead was placed at the center of the base image and projected at a simulated X-ray angle range of ±45° to obtain a projected image. A region of interest was placed at the center of the bead image and the slice sensitivity profile (SSP) was obtained by acquiring pixel values in the z-direction. The full width at half maximum of the SSP was defined as the Z-resolution and the frequency response was obtained by the 1-D Fourier transform of the SSP. Results: Z-resolution increased with increasing bead diameter. However, there was no change in Z-resolution between 0.025 and 0.1 mm. The frequency response was similar to that of the Z-resolution, with a significant difference between 0.1 and 0.2 mm diameter. Conclusions: Z-resolution is dependent on the diameter of the bead, which should be selected considering the pixel size of the tomosynthesis image.