• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1663-1676
• /
• 2022

Recently, a number of deep-learning based land cover segmentation studies have been introduced. Some studies denoted that the performance of land cover segmentation deteriorated due to insufficient training data. In this study, we verified the improvement of land cover segmentation performance through data augmentation. U-Net was implemented for the segmentation model. And 2020 satellite-derived landcover dataset was utilized for the study data. The pixel accuracies were 0.905 and 0.923 for U-Net trained by original and augmented data respectively. And the mean F1 scores of those models were 0.720 and 0.775 respectively, indicating the better performance of data augmentation. In addition, F1 scores for building, road, paddy field, upland field, forest, and unclassified area class were 0.770, 0.568, 0.433, 0.455, 0.964, and 0.830 for the U-Net trained by original data. It is verified that data augmentation is effective in that the F1 scores of every class were improved to 0.838, 0.660, 0.791, 0.530, 0.969, and 0.860 respectively. Although, we applied data augmentation without considering class balances, we find that data augmentation can mitigate biased segmentation performance caused by data imbalance problems from the comparisons between the performances of two models. It is expected that this study would help to prove the importance and effectiveness of data augmentation in various image processing fields.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.637-654
• /
• 2023

In recent years, the number of users has been increasing with the rapid development of earth observation satellites. In response, the Committee on Earth Observation Satellites (CEOS) has been striving to provide user-friendly satellite images by introducing the concept of Analysis Ready Data (ARD) and defining its requirements as CEOS ARD for Land (CARD4L). In ARD, a mask called an Unusable Data Mask (UDM), identifying unnecessary pixels for land analysis, should be provided with a satellite image. UDMs include clouds, cloud shadows, terrain shadows, etc. Terrain shadows are generated in mountainous terrain with large terrain relief, and these areas cause errors in analysis due to their low radiation intensity. previous research on terrain shadow detection focused on detecting terrain shadow pixels to correct terrain shadows. However, this should be replaced by the terrain correction method. Therefore, there is a need to expand the purpose of terrain shadow detection. In this study, to utilize CAS500-4 for forest and agriculture analysis, we extended the scope of the terrain shadow detection to shaded areas. This paper aims to analyze the potential for terrain shadow detection to make a terrain shadow mask for South and North Korea. To detect terrain shadows, we used a Hill-shade algorithm that utilizes the position of the sun and a surface's derivatives, such as slope and aspect. Using RapidEye images with a spatial resolution of 5 meters and Sentinel-2 images with a spatial resolution of 10 meters over the Korean Peninsula, the optimal threshold for shadow determination was confirmed by comparing them with the ground truth. The optimal threshold was used to perform terrain shadow detection, and the results were analyzed. As a qualitative result, it was confirmed that the shape was similar to the ground truth as a whole. In addition, it was confirmed that most of the F1 scores were between 0.8 and 0.94 for all images tested. Based on the results of this study, it was confirmed that automatic terrain shadow detection was well performed throughout the Korean Peninsula.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.1D
• /
• pp.81-88
• /
• 2012

This present research was carried out by dividing two parts; field surveying and data processing, in order to analyze changed patterns of a shoreline. Firstly, the shoreline information measured by the precise GPS positioning during long duration was collected. Secondly, the algorithm for detecting an auto boundary with regards to the changed shoreline with multi-image data was developed. Then, a comparative research was conducted. Haeundae beach which is one of the most famous ones in Korea was selected as a test site. RTK-GPS surveying had been performed overall eight times from September 2005 to September 2009. The filed test by aerial Lidar was conducted twice on December 2006 and March 2009 respectively. As a result estimated from both sensors, there is a slight difference. The average length of shoreline analyzed by RTK-GPS is approximately 1,364.6 m, while one from aerial Lidar is about 1,402.5 m. In this investigation, the specific algorithm for detecting the shoreline detection was developed by Visual C++ MFC (Microsoft Foundation Class). The analysis result estimated by aerial photo and satellite image was 1,391.0 m. The level of reliability was 98.1% for auto boundary detection when it compared with real surveying data.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.183-192
• /
• 2023

The remotely sensed data, such as satellite imagery and aerial photos, can be used to extract and detect some objects in the image through image interpretation and processing techniques. Significantly, the possibility for utilizing digital map updating and land monitoring has been increased through automatic object detection since spatial resolution of remotely sensed data has improved and technologies about deep learning have been developed. In this paper, we tried to extract plastic greenhouses into aerial orthophotos by using fully convolutional densely connected convolutional network (FC-DenseNet), one of the representative deep learning models for semantic segmentation. Then, a quantitative analysis of extraction results had performed. Using the farm map of the Ministry of Agriculture, Food and Rural Affairsin Korea, training data was generated by labeling plastic greenhouses into Damyang and Miryang areas. And then, FC-DenseNet was trained through a training dataset. To apply the deep learning model in the remotely sensed imagery, instance norm, which can maintain the spectral characteristics of bands, was used as normalization. In addition, optimal weights for each band were determined by adding attention modules in the deep learning model. In the experiments, it was found that a deep learning model can extract plastic greenhouses. These results can be applied to digital map updating of Farm-map and landcover maps.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.3
• /
• pp.1-11
• /
• 2017

The main source of water pollution in Doam Lake is turbid incoming water from upland fields in the upper watershed. The large scale, elevation, and slope of this region means that it is inaccessible, and it is difficult to collect information and update data. Field survey results show that there is a difference between classification of upland fields and grasslands in the cadastral data and land-cover map. In this study, MODIS NDVI was calculated from May 2000 to September 2015 in order to improve classification accuracy of upland fields.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.11 no.2
• /
• pp.7-15
• /
• 1993

In order to generate database, we need to obtain speedy and corret topographic information according to requisite purpose. Generally methods to an acquisition of topographic information are available by the use of maps, satellite images, stereo models of aerophoto and so forth. But we must choose a optimal method in consideration of area of object region, spatial solution of image, required accuracy and economic. Therefore, this study aims at providing the establish method of efficient topographic data base of small object region by means of spatial layer techniques of geo-spatial information system and using acquisition of geo-information and production method of base map with photoballoon system to obtain topographic information for reasonable plan and design of object region which select a zone preparation of a collective village with small region. As a result of this study, we decided an f-stop and a shutter speed of camera to obtain accurate stereo model and were able to obtain stereo photography and topography for small region by using of photoballoon system through accuracy analysis according to change flight height and air base speedly and economically. We can establish the data base useable to efficient plan and design as existence map with overlay plan drawing.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.16 no.1
• /
• pp.75-84
• /
• 1998

To achieve more accurate information from satellite image data, a research on a technique for mixed pixel ex-traction has been produced. The mixed pixels with only two land covers have been experimented. By analyzing canonical vector in canonical correlation classification, the mixed pixels have been classified. The ratio of the two canonical weighted values-the elements of canonical vector have been used as a threshold to discriminate mixed pixels. In case of the classification for the mixed pixels of bridge and water class in TM data before or after the 1st of September, the threshold for the optimal classification of the mixed pixels is 4.0. That is, if the ratio of the two canonical weighted values is less than 4.0, the pixel is a mixed pixel. Also, using the distribution of canonical weighted values, the constitution percentages of land covers within one mixed pixel can be approximately deducted. The accuracy of mixed pixel extraction for experimental area is 90％ and quite acceptable. Conclusively, a technique for mixed pixel extraction by canonical vector analysis is effective.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2011.06a
• /
• pp.34-36
• /
• 2011

ENCs is edited based on the numerical charts for publishing paper charts and serviced in forms of grid styles. For this reason, the density of sounding information of ENCs is not consistent and was required for improvement. In this study, K-Means, ISODATA clustering algorithm as classification methods for satellite image was reviewed and adopted to case study. The developed results include loading module of ENC data, improvement algorithm of sounding information, writing module of ENC data. According to the results of algorithm, we could confirm the improved result.

• Korean Journal of Remote Sensing
• /
• v.31 no.1
• /
• pp.29-38
• /
• 2015

The coastline influenced naturally and artificially changes dynamically. While the long-term change is influenced by the rise in the surface of the sea and the changes in water level of the rivers, the short-term change is influenced by the tide, earthquake and storm. Also, man-made thoughtless development such as construction of embankment and reclaimed land not considering erosion and deformation of coast has been causes for breaking functions of coast and damages on natural environment. In order to manage coastal environment and resources effectively, In this study is intended to analyze and predict erosion in coastal environment and changes in sedimentation quantitatively by detecting changes in coastal line from data collection for satellite images and aerial LiDAR data. The coastal line in 2007 and 2012 was extracted by manufacturing Digital Surface Model (DSM) with Aviation LiDAR materials. For the coastal line in 2009 and 2010, Normalized Difference Vegetation Index (NDVI) method was used to extract the KOMPSAT-2 image selected after considering tide level and wave height. The change rate of the coastal line is varied in line with the forms of the observation target but most of topography shows a tendency of being eroded as time goes by. Compared to the relatively monotonous beach of Taean, the gravel and rock has very complex form. Therefore, there are more errors in extraction of coastlines and the combination of transect and shoreline, which affect overall changes. Thus, we think the correction of the anomalies caused by these properties is required in the future research.

• Korean Journal of Remote Sensing
• /
• v.15 no.2
• /
• pp.107-117
• /
• 1999

A comparison of a neural network approach with the conventional statistical methods, multiple regression and band ratio analyses, for the estimation of water quality parameters in presented in this paper. The Landsat TM image of Lake Daechung acquired on March 18, 1996 and the thirty in-situ sampling data sets measured during the satellite overpass were used for the comparison. We employed a three-layered and feedforward network trained by backpropagation algorithm. A cross validation was applied because of the small number of training pairs available for this study. The neural network showed much more successful performance than the conventional statistical analyses, although the results of the conventional statistical analyses were significant. The superiority of a neural network to statistical methods in estimating water quality parameters is strictly because the neural network modeled non-linear behaviors of data sets much better.