김용일 교수

Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional

Local Climate Zones (LCZ) offer a climate-aware and standardized classification scheme composed of 17 urban and natural landscape classes. Recent deep learning-based LCZ classification studies have adopted a scene classification approach with computer vision-inspired models. In light of these advancements, this study introduces a multi-scale, multi-level attention network (MSMLA-Net) for deep learning-based LCZ classification. MSMLA-Net integrates a multi-scale (MS) module to generate multi-scal

This study proposes a light convolutional neural network (LCNN) well-fitted for medium-resolution (30-m) land-cover classification. The LCNN attains high accuracy without overfitting, even with a small number of training samples, and has lower computational costs due to its much lighter design compared to typical convolutional neural networks for high-resolution or hyperspectral image classification tasks. The performance of the LCNN was compared to that of a deep convolutional neural network, s

Thermal data products derived from remotely sensed data play significant roles as key parameters for biophysical phenomena. However, a trade-off between spatial and spectral resolutions has existed in thermal infrared (TIR) remote sensing systems, with the end product being the limited resolution of the TIR sensor. In order to treat this problem, various disaggregation methods of TIR data, based on the indices from visible and near-infrared (VNIR), have been developed to sharpen the coarser spat

Although semantic segmentation of remote-sensing (RS) images using deep-learning networks has demonstrated its effectiveness recently, compared with natural-image datasets, obtaining RS images under the same conditions to construct data labels is difficult. Indeed, small datasets limit the effective learning of deep-learning networks. To address this problem, we propose a combined U-net model that is trained using a combined weighted loss function and can handle heterogeneous datasets. The netwo

We propose a new spatial feature extraction method for supervised classification of satellite images with high spatial resolution. The proposed shape–size index (SSI) feature combines homogeneous areas using spectral similarity between one central pixel and its neighbouring pixels. A spatial index considers the shape and size of the homogeneous area, and suitable spatial features are parametrically selected. The generated SSI feature is integrated with the original high resolution multispectral

Acquiring information about earthquake-damaged buildings is essential for effective rescue and restoration operations. Building damage must be assessed to provide detailed information regarding the location and proportion of damage to individual buildings. Automatic processing of damage assessment is also critical in hastening relief efforts. Therefore, we propose a new method for automatically extracting damaged building parts and quantitatively assessing the damage to individual buildings caus

In physical aspects, urban growth means the expansion of built up areas. There have been numerous approaches to model and interpret the growth of a city. However, these approaches - especially the common bid-rent models - over-simplify the spatial variations of a city. Although these approaches might be powerful tools for a clear understanding of urban growth, they usually fail to generate detailed spatial implications required for planning practices due to their simplicity in assumptions. This

The application of remote sensing techniques for disaster management often requires rapid damage assessment to support decision-making for post-treatment activities. As the on-demand acquisition of pre-event very high-resolution (VHR) images is typically limited, PlanetScope (PS) offers daily images of global coverage, thereby providing favorable opportunities to obtain high-resolution pre-event images. In this study, we propose an unsupervised change detection framework that uses post-fire VHR

Image super-resolution (SR) is a significant technique in image processing as it enhances the spatial resolution of images, enabling various downstream applications. Based on recent achievements in SR studies in computer vision, deep-learning-based SR methods have been widely investigated for remote sensing images. In this study, we proposed a two-stage approach called bicubic-downsampled low-resolution (LR) image-guided generative adversarial network (BLG-GAN) for remote sensing image super-res

Meteorological satellite images provide crucial information on solar irradiation and weather conditions at spatial and temporal resolutions which are ideal for short-term photovoltaic (PV) power forecasts. Following the introduction of next-generation meteorological satellites, investigating their application on PV forecasts has become imminent. In this study, Communications, Oceans, and Meteorological Satellite (COMS) and Himawari-8 (H8) satellite images were inputted in a deep neural network (

Pansharpening algorithms are important methods for overcoming the technical limitations of satellite sensors. However, most approaches to pansharpening have tended either to distort the spectral characteristics of the original multispectral image or reduce the visual sharpness of the panchromatic image. In this paper, we propose a pansharpening algorithm that uses both a global and a local context-adaptive parameter based on component substitution. The purpose of this algorithm is to produce fus

Change detection (CD) networks based on supervised learning have been used in diverse CD tasks. However, such supervised CD networks require a large amount of data and only use information from current images. In addition, it is time consuming to manually acquire the ground truth data for newly obtained images. Here, we proposed a novel method for CD in case of a lack of training data in an area near by another one with the available ground truth data. The proposed method automatically entails g