• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1505-1514
• /
• 2022

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.2
• /
• pp.87-92
• /
• 2010

Large pressure on the growing population has increased rapid change in the LULC (land use/land cover) patterns in the watershed area. Spatial distribution of LULC information and its changes are desirable for any effective planning, managing and monitoring activities. The aim of the study is to produce the 1,50,000 scaled LULC change map for the sub-watershed, Western Moyar, India using the multi-temporal satellite image dataset of IRS LISS III images for the year 1989, 1999, and 2002. About 9 classes are extracted using onscreen visual interpretation techniques for all the three years. The change detection analysis was performed using matrix method for period I (1989-1999) and period II (1999-2002). The study reveals that the changes noticed in period II (1999-2002) is comparatively more than period I (1989-1999), which is dynamic information to protect the sub-watershed area from the deterioration and paves the way to for the sustainable development.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.4
• /
• pp.275-292
• /
• 2022

In order to detect climate changes using satellite imagery, the GCOS (Global Climate Observing System) defines requirements such as spatio-temporal resolution, stability by the time change, and uncertainty. Due to limitation of GK-2A sensor performance, the level-2 products can not satisfy the requirement, especially for spatial resolution. In this paper, we found the optimal pan-sharpening algorithm for GK-2A products. The six pan-sharpening methods included in CS (Component Substitution), MRA (Multi-Resolution Analysis), VO (Variational Optimization), and DL (Deep Learning) were used. In the case of DL, the synthesis property based method was used to generate training dataset. The process of synthesis property is that pan-sharpening model is applied with Pan (Panchromatic) and MS (Multispectral) images with reduced spatial resolution, and fused image is compared with the original MS image. In the synthesis property based method, fused image with desire level for user can be produced only when the geometric characteristics between the PAN with reduced spatial resolution and MS image are similar. However, since the dissimilarity exists, RD (Random Down-sampling) was additionally used as a way to minimize it. Among the pan-sharpening methods, PSGAN was applied with RD (PSGAN_RD). The fused images are qualitatively and quantitatively validated with consistency property and the synthesis property. As validation result, the GSA algorithm performs well in the evaluation index representing spatial characteristics. In the case of spectral characteristics, the PSGAN_RD has the best accuracy with the original MS image. Therefore, in consideration of spatial and spectral characteristics of fused image, we found that PSGAN_RD is suitable for GK-2A products.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.251-263
• /
• 2019

Sentinel-2 Multi Spectral Instrument(MSI) launched by the European Space Agency (ESA) offered high spatial resolution optical products, enhanced temporal revisit of five days, and 13 spectral bands in the visible, near infrared and shortwave infrared wavelengths similar to Landsat mission. Landsat satellite imagery has been applied to various previous studies, but Sentinel-2 optical satellite imagery has not been widely used. Currently, for global coverage, Sentinel-2 products are systematically processed and distributed to Level-1C (L1C) products which contain the Top-of-Atmosphere (TOA) reflectance. Furthermore, ESA plans a systematic global production of Level-2A(L2A) product including the atmospheric corrected Bottom-of-Atmosphere (BOA) reflectance considered the aerosol optical thickness and the water vapor content. Therefore, the Sentinel-2 L2A products are expected to enhance the reliability of image quality for overall coverage in the Sentinel-2 mission with enhanced spatial,spectral, and temporal resolution. The purpose of this work is a quantitative comparison Sentinel-2 L2A products and fully simulated image to evaluate the applicability of the Sentinel-2 dataset in cultivated land growing various kinds of crops in Korea. Reference image of Sentinel-2 L2A data was simulated by airborne hyperspectral data acquired from AISA Fenix sensor. The simulation imagery was compared with the reflectance of L1C TOA and that of L2A BOA data. The result of quantitative comparison shows that, for the atmospherically corrected L2A reflectance, the decrease in RMSE and the increase in correlation coefficient were found at the visible band and vegetation indices to be significant.