• Korean Journal of Remote Sensing
• /
• v.16 no.1
• /
• pp.1-11
• /
• 2000

Multi-temporal data have been used frequently for analyzing dynamic characteristics of ecological environment. Little research, however, shows the characteristics and problems of the analysis of continental- or global-scale, multi-temporal satellite data. This research investigated the characteristics of large-area, multi-temporal data analysis and the problems of phenological difference of ground vegetation and scarcity of training data for a long term period. This research suggested a latitudinal image segmentation method and an invariant pixel method. As an application, the image segmentation and invariant pixel methods were applied to a set of AVHRR data covering most part of Asia from 1982 to 1993. Fuzzy classification results showed the decrease of forests and the increase of croplands at densely populated areas, however an opposite trend was detected at sparsely populated or depopulated areas.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.214-222
• /
• 2022

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.

• Atmosphere
• /
• v.33 no.1
• /
• pp.61-72
• /
• 2023

Accurate estimation of forest carbon stocks is important in establishing greenhouse gas reduction plans. In this study, we estimate the spatial distribution of forest carbon stocks using machine learning techniques based on high-resolution remote sensing data and detailed field survey data. The high-resolution remote sensing data used in this study are Landsat indices (EVI, NDVI, NDII) for monitoring vegetation vitality and Shuttle Radar Topography Mission (SRTM) data for describing topography. We also used the forest growing stock data from the National Forest Inventory (NFI) for estimating forest biomass. Based on these data, we built a model based on machine learning methods and optimized for Korean forest types to calculate the forest carbon stocks per grid unit. With the newly developed estimation model, we created forest carbon stocks maps and estimated the forest carbon stocks in South Korea. As a result, forest carbon stock in South Korea was estimated to be 432,214,520 tC in 2020. Furthermore, we estimated the loss of forest carbon stocks due to the Donghae-Uljin forest fire in 2022 using the forest carbon stock map in this study. The surrounding forest destroyed around the fire area was estimated to be about 24,835 ha and the loss of forest carbon stocks was estimated to be 1,396,457 tC. Our model serves as a tool to estimate spatially distributed local forest carbon stocks and facilitates accounting of real-time changes in the carbon balance as well as managing the LULUCF part of greenhouse gas inventories.

• Journal of the Korean earth science society
• /
• v.27 no.1
• /
• pp.83-94
• /
• 2006

The objective of this paper is to extract and analyze the sediment environment change information in the Sachencheon, Gangneung, Korea that was seriously damaged as a result of typhoon Rusa aftermath early in September, 2002 using multi-temporal remote sensing data. For the extraction of change information, an unsupervised approach based on the automatic determination of thresholding values was applied. As the change detection results, turbidity changes right after typhoon Rusa, the decrease of wetlands, the increase of dry sand and channel width and changes of relative level in the stream due to seasonal variation were observed. Sedimentation in the cultivated areas and restoration works also affected the change near the Sacheoncheon. In addition to the change detection analysis, several environmental thematic maps including microtopographic map, distributions of estimated amount of flood deposits and flood hazard landform classification map were generated by using remote sensing and field survey data. In conclusion, multi-temporal remote sensing data can be effectively used for natural hazard analysis and damage information extraction and specific data processing techniques for high-resolution remote sensing data should also be developed.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.325-329
• /
• 1999

The characteristic of East Asian summer monsoon is investigated using 8-year (March 1987-February 1995) - averaged monthly and 5-day mean 1 degree latitude-longitude gridded GMS high-cloud-amount data (HCA). An analysis of these data shows the convective zone (ITCZ) clouds which defined as the percentage of the total grid area covered by clouds with a cloud-top temperature below the 400 hPa-level climatological temperature. The HCA increased clearly over equatorial zone during December and January and 30-40 $^{\circ}$N during May and June. These HCA patterns are coincided with seasonal cycles of summer monsoon which is introduced in historical references. The relationship with the summer monsoon winds as climatological changing of wind direction is analyzed by ECMWF re-analysis 2.5-degree latitude-longitude grid surface data which is calculated with 8-year averaged from January 1987 to January 1995. In addition, the monsoon winds are showed by separated U, V-wind components far manifestation a tendency of onset and retreat data of seasonal monsoon.

• Korean Journal of Remote Sensing
• /
• v.23 no.5
• /
• pp.447-453
• /
• 2007

The demand for more accurate and realistic 3D urban models has been increasing more and more. Many studies have been conducted to extract 3D features from remote sensing data such as satellite images, aerial photos, and airborne laser scanning data. In this paper a technique is presented to extract and reconstruct 3D buildings in urban areas using airborne laser scanning data. Firstly all points in a building were divided into some groups by height difference. From segmented laser scanning data of irregularly distributed points we generalized and regularized building boundaries which better approximate the real boundaries. Then the roof points which are subject to the same groups were classified using pre-defined models by least squares fitting. Finally all parameters of the roof surfaces were determined and 3D building models were constructed. Some buildings with complex shapes were selected to test our presented algorithms. The results showed that proposed approach has good potential for reconstructing complex buildings in detail using only airborne laser scanning data.

• Korean Journal of Remote Sensing
• /
• v.1 no.1
• /
• pp.5-27
• /
• 1985

A hill-sliding technique was devised to extract Gaussian clusters from the multivariate probability density estimates of sample data for the first step of iterative unsupervised classification. The underlying assumption in this approach was that each cluster possessed a unimodal normal distribution. The key idea was that a clustering function proposed could distinguish elements of a cluster under formation from the rest in the feature space. Initial clusters were extracted one by one according to the hill-sliding tactics. A dimensionless cluster compactness parameter was proposed as a universal measure of cluster goodness and used satisfactorily in test runs with Landsat multispectral scanner (MSS) data. The normalized divergence, defined by the cluster divergence divided by the entropy of the entire sample data, was utilized as a general separability measure between clusters. An overall clustering objective function was set forth in terms of cluster covariance matrices, from which the cluster compactness measure could be deduced. Minimal improvement of initial data partitioning was evaluated by this objective function in eliminating scattered sparse data points. The hill-sliding clustering technique developed herein has the potential applicability to decomposition of any multivariate mixture distribution into a number of unimodal distributions when an appropriate diatribution function to the data set is employed.

• Korean Journal of Remote Sensing
• /
• v.22 no.1
• /
• pp.75-85
• /
• 2006

This paper has dealt with a data fusion for the problem of land-cover classification using multisensor imagery. Dempster-Shafer evidence theory has been employed to combine the information extracted from the multiple data of same site. The Dempster-Shafer's approach has two important advantages for remote sensing application: one is that it enables to consider a compound class which consists of several land-cover types and the other is that the incompleteness of each sensor data due to cloud-cover can be modeled for the fusion process. The image classification based on the Dempster-Shafer theory usually assumes that each sensor is represented by a single channel. The evidential approach to image classification, which utilizes a mass function obtained under the assumption of class-independent beta distribution, has been discussed for the multiple sets of mutichannel data acquired from different sensors. The proposed method has applied to the KOMPSAT-1 EOC panchromatic imagery and LANDSAT ETM+ data, which were acquired over Yongin/Nuengpyung area of Korean peninsula. The experiment has shown that it is greatly effective on the applications in which it is hard to find homogeneous regions represented by a single land-cover type in training process.

• Korean Journal of Remote Sensing
• /
• v.40 no.2
• /
• pp.219-228
• /
• 2024

Vessels can operate with their Automatic Identification System (AIS) turned off, prompting the development of strategies to identify them. Among these, utilizing satellites to collect radio frequency (RF) data in the absence of AIS has emerged as the most effective and practical approach. The purpose of this study is to develop a matching algorithm for RF with AIS data and find the RF's applicability to classify a suspected ship. Thus, a matching procedure utilizing three RF datasets and AIS data was employed to identify ships in the Yellow Sea and the Korea Strait. The matching procedure was conducted based on the proximity to AIS points, ensuring accuracy through various distance-based sections, including 2 km, 3 km, and 6 km from the AIS-based estimated points. Within the RF coverage, the matching results from the first RF dataset and AIS data identified a total of 798 ships, with an overall matching rate of 78%. In the cases of the second and third RF datasets, 803 and 825 ships were matched, resulting in an overall matching rate of 84.3% and 74.5%, respectively. The observed results were partially influenced by differences in RF and AIS coverage. Within the overlapped region of RF and AIS data, the matching rate ranged from 80.2% to 98.7%, with an average of 89.3%, with no duplicate matches to the same ship.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.14-17
• /
• 2005

Global latent heat flux data sets are crucial for many studies such as those related to air-sea interaction and climate variation. Currently, various global latent heat flux data sets are constructed using satellite data. Japanese Ocean Flux data sets with Use of Remote sensing Observations (J-OFURO) includes one of the satellite-derived global latent heat flux data (Kubota et aI., 2000). In this study, we review future development of J-OFURO global latent heat flux data set. In particular, we investigate usage of multi-satellite data for estimating accurate global latent heat flux. Accurate estimation of surface wind speeds over the global ocean is one of key factors for the improved estimation of global latent heat flux. First, we demonstrate improvement of daily wind speed estimation using multi-satellites data from microwave radiometers and scatterometers such as DMSP/SSMI, ERS/AMI, QuikSCAT/SeaWinds, AqualAMSR-E, ADEOS2/AMSR etc. Next, we demonstrate improvement of global latent heat flux estimation using the wind speed data derived from multi-satellite data.