• Journal of Wetlands Research
• /
• v.16 no.3
• /
• pp.393-401
• /
• 2014

The purpose of this study was to investigate the objective impact in accuracy and reliability with tendency depend on training samples by using the high-resolution images. Supervised classification was performed based on multi-spectral images which made by each satellite and aerial images for considering all of bands' characteristics. The highest accuracy was 84.7% with satellite image(3*3) and 83% with aerial image(5*5) at the accuracy verification phase. Also, the overall accuracy with the consideration of Kappa coefficient were 0.84 for satellite images and 0.82 for aerial images. In all of the images, the smaller training sample was, the higher accuracy showed. Therefore, tree species classification accuracy was tended to rely on training sample size.

• 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.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.507-519
• /
• 2023

Multi-temporal optical images have been utilized for time-series monitoring of croplands. However, the presence of clouds imposes limitations on image availability, often requiring a cloud removal procedure. This study assesses the applicability of various machine learning algorithms for effective cloud removal in optical imagery. We conducted comparative experiments by focusing on two key variables that significantly influence the predictive performance of machine learning algorithms: (1) land-cover types of training data and (2) temporal variability of land-cover types. Three machine learning algorithms, including Gaussian process regression (GPR), support vector machine (SVM), and random forest (RF), were employed for the experiments using simulated cloudy images in paddy fields of Gunsan. GPR and SVM exhibited superior prediction accuracy when the training data had the same land-cover types as the cloud region, and GPR showed the best stability with respect to sampling fluctuations. In addition, RF was the least affected by the land-cover types and temporal variations of training data. These results indicate that GPR is recommended when the land-cover type and spectral characteristics of the training data are the same as those of the cloud region. On the other hand, RF should be applied when it is difficult to obtain training data with the same land-cover types as the cloud region. Therefore, the land-cover types in cloud areas should be taken into account for extracting informative training data along with selecting the optimal machine learning algorithm.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.216-219
• /
• 2004

In this study, the concept and techniques to generate the level lA, lB and 2A image products have been reviewed. In particular, radiometric and geometric corrections and bands registration used to generate level lA, lB and 2A products have been focused in this study. Radiometric correction is performed to take into account radiometric gain and offset calculated by compensating the detector response non-uniformity. And, in order to compensate satellite altitude, attitude, skew effects, earth rotation and earth curvature, some geometric parameters for geometric corrections are computed and applied. Bands registration process using the matching function between a geometry, which is called 'reference geometry', and another one which is corresponds to the image to be registered is applied to images in case of multi-spectral imaging mode. In order to generate level-lA image products, a simple radiometric processing is applied to a level-0 image. Level-lB image has the same radiometry correction as a level-lA image, but is also issued from some geometric corrections in order to compensate skew effects, Earth rotation effects and spectral misregistration. Level-2A image is generated using some geo-referencing parameters computed by ephemeris data, orbit attitudes and sensor angles. Level lA image is tested by visual analysis. The difference between distances calculated level 1 B image and distances of real coordinate is tested. Level 2A image is tested Using checking points.

• Korean Journal of Remote Sensing
• /
• v.15 no.2
• /
• pp.131-146
• /
• 1999

The satellite visible data have been successfully applied to study the ocean color. Another ocean color sensor, the Ocean Scanning Multi-spectral Imager (OSMI) on the Korea Multi-Purpose Satellite (KOMPSAT) will be launched in 1999. In order to understand the characteristics of future OSMI images, we have first discussed the simulation models and procedures in detail, and produced typical patterns of radiances at visible bands by using radiative transfer models. The various simulated images of full satellite passes and Korean local areas for different seasons, water types, and the satellite crossing equator time (CET) are presented to illustrate the distribution of each component of radiance (i.e., aerosol scattering, Rayleigh scattering, sun glitter, water-leaving radiance, and total radiance). A method to evaluate the image quality and availability is then developed by using the characteristics of image defined as the Complex Signal Noise Ratio (CSNR). Meanwhile, a series of CSNR images are generated from the simulated radiance components for different cases, which can be used to evaluate the quality and availability of OSMI images before the KOMPSAT will be placed in orbit. Finally, the quality and availability of OSMI images are quantitatively analyzed by the simulated CSNR image. It is hoped that the results would be useful to all scientists who are in charge of OSMI mission and to those who plan to use the data from OSMI.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_4
• /
• pp.1341-1350
• /
• 2019

This research deals with algorithm for forest fire severity classification using multi-temporal KOMPSAT-3A image to mapping forest fire areas. The recent satellite of the KOMPSAT series, KOMPSAT-3A, demonstrates high resolution and multi-spectral imagery with infrared and high resolution electro-optical bands. However, there is a lack of research to classify forest fire severity using KOMPSAT-3A. Therefore, the purpose of this study is to analyze forest fire severity using KOMPSAT-3A images. In addition, this research used pre-fire and post-fire Sentinel-2 with differenced Normalized Burn Ratio (dNBR) to taking for burn severity distribution map. To test the effectiveness of the proposed procedure on April 4, 2019, Gangneung wildfires were considered as a case study. This research used the probability density function for the classification of forest fire damage severity based on R software, a free software environment of statistical computing and graphics. The burn severities were estimated by changing NDVI before and after forest fire. Furthermore, standard deviation of probability density function was used to calculate the size of each class interval. A total of five distribution of forest fire severity were effectively classified.

• Journal of Korean Society for Geospatial Information Science
• /
• v.17 no.1
• /
• pp.21-35
• /
• 2009

KOMPSAT-2 is the seventh high-resolution image satellite in the world that provides both 1m-grade panchromatic images of the GSD and 4m-grade multispectral images of the GSD. It's anticipated to be used across many different areas including mapping, territory monitoring and environmental watch. However, due to the complexity and security concern involved with the use of the MSC, the use of KOMPSAT-2 images are limited in terms of geometric images, such as satellite orbits and detailed mapping information. Therefore, this study aims to produce DEM and orthoimage by using the stereo images of KOMPSAT-2, and to explore the applicability of geo-spatial information with KOMPSAT -2. Orientation interpretations were essential for the production of DEM and orthoimage using KOMPSAT-2 images. In the study, they are performed by utilizing both RPC and GCP. In this study, the orientation interpretations are followed by the generation of DEM and orthoimage, and the analysis of their accuracy based on a 1:5,000 digital map. The accuracy analysis of DEM is performed and the results indicate that their altitudes are, in general, higher than those obtained from the digital map. The altitude discrepancies on plains, hills and mountains are calculated as 1.8m, 7.2m, and 11.9m, respectively. In this study, the mean differences between horizontal position between the orthoimage data and the digital map data are found to be ${\pm}3.081m$, which is in the range of ${\pm}3.5m$, within the permitted limit of a 1:5,000 digital map. KOMPSAT-2 images are used to produce DEM and orthoimage in this research. The results suggest that DEM can be adequately used to produce digital maps under 1:5,000 scale.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.7 no.4
• /
• pp.77-87
• /
• 2004

It is important for hydrographers to extract the accurate cross section of a river for the hydrographical analysis of the topography. Aerial photographs were used to extract the cross section of a river for the advantages of the accuracy and economical efficiency in this study, while the direct measurement has been used in existing studies. An ortho-rectified photo map using imageries taken by the PKNU 2 (High-resolution, multi-spectral, aerial photographic system developed by our laboratory) was generated using the surveyed data and a digital map. The cross section of a river that was obtained from the ortho-rectified by the surveyed Kinematic data of GPS was compared with the result using ImageStation stereo-plotter of corp. Z/I Imaging. As a result of this study, the RMSE in the ortho-rect process using the surveyed GPS data was lowered as from 5.5788 pixels (about 2m) to 2.84 (about 1m) in comparison with it in the process using a digital map. The surveyed kinematic GPS in extraction of the cross section of a river was excellent as 6.6cm of the planimetric and precision in the confidence level of 95%. The correlation coefficient between the result from the using stereo-plotter and the extraction of cross section of a river using aerial photos was 0.8 hydrographical acquisition of it using PKNU 2 imagery will be possible.

• Korean Journal of Remote Sensing
• /
• v.28 no.4
• /
• pp.393-407
• /
• 2012

This study focuses on the correction of topographic effects caused by a combination of solar elevation and azimuth, and topographic relief in single optical remote sensing imagery, and by a combination of changes in position of the sun and topographic relief in comparative analysis of multi-temporal imageries. For the Jeju Island, Republic of Korea, where Mt. Halla and various cinder cones are located, a Landsat 7 ETM+ imagery and ASTER GDEM data were used to normalize the topographic effects on the imagery, using two topographic normalization methods: cosine correction assuming a Lambertian condition and assuming a non-Lambertian c-correction, with kernel sizes of $3{\times}3$, $5{\times}5$, $7{\times}7$, and $9{\times}9$ pixels. The effects of each correction method and kernel size were then evaluated. The c-correction with a kernel size of $7{\times}7$ produced the best result in the case of a land area with various land-cover types. For a land-cover type of forest extracted from an unsupervised classification result using the ISODATA method, the c-correction with a kernel size of $9{\times}9$ produced the best result, and this topographic normalization for a single land cover type yielded better compensation for topographic effects than in the case of an area with various land-cover types. In applying the relative radiometric normalization to topographically normalized three multi-temporal imageries, more invariant spectral reflectance was obtained for infrared bands and the spectral reflectance patterns were preserved in visible bands, compared with un-normalized imageries. The results show that c-correction considering the remaining reflectance energy from adjacent topography or imperfect atmospheric correction yielded superior normalization results than cosine correction. The normalization results were also improved by increasing the kernel size to compensate for vertical and horizontal errors, and for displacement between satellite imagery and ASTER GDEM.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.4
• /
• pp.1-11
• /
• 2019

With the development of remote sensing sensor technology, it has become possible to acquire satellite images with various spectral information. In particular, since the hyperspectral image is composed of continuous and narrow spectral wavelength, it can be effectively used in various fields such as land cover classification, target detection, and environment monitoring. Change detection techniques using remote sensing data are generally performed through differences of data with same dimensions. Therefore, it has a disadvantage that it is difficult to apply to heterogeneous sensors having different dimensions. In this study, we have developed a change detection method applicable to hyperspectral image and high spat ial resolution satellite image with different dimensions, and confirmed the applicability of the change detection method between heterogeneous images. For the application of the change detection method, the dimension of hyperspectral image was reduced by using correlation analysis and principal component analysis, and the change detection algorithm used CVA. The ROC curve and the AUC were calculated using the reference data for the evaluation of change detection performance. Experimental results show that the change detection performance is higher when using the image generated by adequate dimensionality reduction than the case using the original hyperspectral image.