• Korean Journal of Remote Sensing
• /
• v.22 no.5
• /
• pp.451-456
• /
• 2006

Epipolar images have to be generated to stereo display aerial images or satellite images. Pushbroom sensor is used to acquire high resolution satellite images. These satellite images have curvilinear epipolar lines unlike the epipolar lines of frame images, which are straight lines. The aforementioned fact makes it difficult to generate epipolar images for pushbroom satellite images. If we assume a linear transition of the sensor having constant speed and attitude during image acquisition, we can generate epipolar images based on parallel projection model (20 Affine model). Recent high resolution images are provided with RPC values so that we can exploit these values to generate epipolar images without using ground control points and tie point. This paper provides a procedure based on the parallel projection model for generating epipolar images directly from a stereo IKONOS images, and experimental results.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.4
• /
• pp.137-143
• /
• 2013

The high resolution satellite images are used in many fields such as weather observation, remote sensing, military facilities monitoring, cultural properties protection etc. Although satellite images are obtained in same satellite imaging system, the satellite images are degraded depending on the condition of hardware(optical device, satellite operation altitude, image sensor, etc.). Due to the fact that changing the hardware of satellite imaging system is impossible for resolution enhancement of these degraded satellite after launching a satellite, therefore the method of resolution enhancement with satellite images is necessary. In this paper the resolution is enhances by using a Super Resolution(SR) algorithm. The SR algorithm is an algorithm to enhance the resolution of an image by uniting many low resolution images, so an output image has higher resolution than using other interpolation methods. But It is difficult to obtain many images of the same area. Therefore, to solve this problem, we applied SR after by applying the affine and projection transform. As a results, we found that the images applied SR after affine and projection transform have higher resolution than the images only applied SR.

• Spatial Information Research
• /
• v.19 no.1
• /
• pp.29-40
• /
• 2011

GOCI the world first Ocean Color Imager in Geostationary Orbit, which could obtain total 8 images of the same region a day, however, its spatial resolution(500m) is not enough to use for the accurate land application, Super Resolution(SR), reconstructing the high resolution(HR) image from multiple low resolution(LR) images introduced by computer vision field. could be applied to the time-series remotely sensed images such as GOCI data, and the higher resolution image could be reconstructed from multiple images by the SR, and also the cloud masked area of images could be recovered. As the precedent study for developing the efficient SR method for GOCI images, on this research, it reproduced the simulated data under the acquisition process of the remote sensed data, and then the simulated images arc applied to the proposed algorithm. From the proposed algorithm result of the simulated data, it turned out that low resolution(LR) images could be registered in sub-pixel accuracy, and the reconstructed HR image including RMSE, PSNR, SSIM Index value compared with original HR image were 0.5763, 52.9183 db, 0.9486, could be obtained.

• 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.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.71-76
• /
• 2020

In this paper, we propose a super-resolution method that reconstructs compressed low-resolution images into high-resolution images. We propose a CNN model with a small number of parameters, and even if quantization is applied to the proposed model, super-resolution can be implemented without deteriorating the image quality. To further improve the quality of the compressed low-resolution image, a new degradation model was proposed instead of the existing bicubic degradation model. The proposed degradation model is used only in the training process and can be applied by changing only the parameter values to the original CNN model. In the super-resolution image applying the proposed degradation model, visual artifacts caused by image compression were effectively removed. As a result, our proposed method generates higher PSNR values at compressed images and shows better visual quality, compared to conventional CNN-based SR methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.757-770
• /
• 2022

Palmprint recognition has drawn increasingly attentions in the past decade due to its uniqueness and reliability. Traditional palmprint recognition methods usually use high-resolution images as the identification basis so that they can achieve relatively high precision. However, high-resolution images mean more computation cost in the recognition process, which usually cannot be guaranteed in mobile computing. Therefore, this paper proposes an improved low-resolution palmprint image recognition method based on residual networks. The main contributions include: 1) We introduce a channel attention mechanism to refactor the extracted feature maps, which can pay more attention to the informative feature maps and suppress the useless ones. 2) The ResStage group structure proposed by us divides the original residual block into three stages, and we stabilize the signal characteristics before each stage by means of BN normalization operation to enhance the feature channel. Comparison experiments are conducted on a public dataset provided by the Hong Kong Polytechnic University. Experimental results show that the proposed method achieve a rank-1 accuracy of 98.17% when tested on low-resolution images with the size of 12dpi, which outperforms all the compared methods obviously.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• 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.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.555-563
• /
• 2018

Thermal infrared images have the characteristic of being able to detect objects that can not be seen with the naked eye and have the advantage of easily obtaining information of inaccessible areas. However, TIR (Thermal InfraRed) images have a relatively low spatial resolution. In this study, the applicability of the pansharpening algorithm used for satellite imagery on images acquired by the UAV (Unmanned Aerial Vehicle) was tested. RGB image have higher spatial resolution than TIR images. In this study, pansharpening algorithm was applied to TIR image to create the images which have similar spatial resolution as RGB images and have temperature information in it. Experimental results show that the pansharpening algorithm using the PC1 band and the average of RGB band shows better results for the quantitative evaluation than the other bands, and it has been confirmed that pansharpening results by ATWT (${\grave{A}}$ Trous Wavelet Transform) exhibit superior spectral resolution and spatial resolution than those by HPF (High-Pass Filter) and SFIM (Smoothing Filter-based Intensity Modulation) pansharpening algorithm.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.5
• /
• pp.413-422
• /
• 2018

Many applications using satellite data from high-resolution multispectral sensors require an image fusion step, known as pansharpening, before processing and analyzing the multispectral images when spatial fidelity is crucial. Image fusion methods are to improve images with higher spatial and spectral resolutions by reducing spectral distortion, which occurs on image fusion processing. The image fusion methods can be classified into MRA (Multi-Resolution Analysis) and CSA (Component Substitution Analysis) approaches. To suggest the efficient image fusion method for Pleiades and KOMPSAT (Korea Multi-Purpose Satellite) 3 satellites, this study will evaluate image fusion methods for multispectral and panchromatic images. HPF (High-Pass Filtering), SFIM (Smoothing Filter-based Intensity Modulation), GS (Gram Schmidt), and GSA (Adoptive GS) were selected for MRA and CSA based image fusion methods and applied on multispectral and panchromatic images. Their performances were evaluated using visual and quality index analysis. HPF and SFIM fusion results presented low performance of spatial details. GS and GSA fusion results had enhanced spatial information closer to panchromatic images, but GS produced more spectral distortions on urban structures. This study presented that GSA was effective to improve spatial resolution of multispectral images from Pleiades 1A and KOMPSAT 3.

• Journal of Information Processing Systems
• /
• v.18 no.1
• /
• pp.12-25
• /
• 2022

In recent years, deep convolutional neural networks have made significant progress in the research of single image super-resolution. However, it is difficult to be applied in practical computing terminals or embedded devices due to a large number of parameters and computational effort. To balance these problems, we propose CSRNet, a lightweight neural network based on channel split residual learning structure, to reconstruct highresolution images from low-resolution images. Lightweight refers to designing a neural network with fewer parameters and a simplified structure for lower memory consumption and faster inference speed. At the same time, it is ensured that the performance of recovering high-resolution images is not degraded. In CSRNet, we reduce the parameters and computation by channel split residual learning. Simultaneously, we propose a double-upsampling network structure to improve the performance of the lightweight super-resolution network and make it easy to train. Finally, we propose a new evaluation metric for the lightweight approaches named 100_FPS. Experiments show that our proposed CSRNet not only speeds up the inference of the neural network and reduces memory consumption, but also performs well on single image super-resolution.