• Journal of Korean Society of Rural Planning
• /
• v.30 no.1
• /
• pp.57-66
• /
• 2024

This study aimed to develop a precise vegetation cover classification model for small streams using the combination of drone remote sensing and support vector machine (SVM) techniques. The chosen study area was the Idong stream, nestled within Geosan-gun, Chunbuk, South Korea. The initial stage involved image acquisition through a fixed-wing drone named ebee. This drone carried two sensors: the S.O.D.A visible camera for capturing detailed visuals and the Sequoia+ multispectral sensor for gathering rich spectral data. The survey meticulously captured the stream's features on August 18, 2023. Leveraging the multispectral images, a range of vegetation indices were calculated. These included the widely used normalized difference vegetation index (NDVI), the soil-adjusted vegetation index (SAVI) that factors in soil background, and the normalized difference water index (NDWI) for identifying water bodies. The third stage saw the development of an SVM model based on the calculated vegetation indices. The RBF kernel was chosen as the SVM algorithm, and optimal values for the cost (C) and gamma hyperparameters were determined. The results are as follows: (a) High-Resolution Imaging: The drone-based image acquisition delivered results, providing high-resolution images (1 cm/pixel) of the Idong stream. These detailed visuals effectively captured the stream's morphology, including its width, variations in the streambed, and the intricate vegetation cover patterns adorning the stream banks and bed. (b) Vegetation Insights through Indices: The calculated vegetation indices revealed distinct spatial patterns in vegetation cover and moisture content. NDVI emerged as the strongest indicator of vegetation cover, while SAVI and NDWI provided insights into moisture variations. (c) Accurate Classification with SVM: The SVM model, fueled by the combination of NDVI, SAVI, and NDWI, achieved an outstanding accuracy of 0.903, which was calculated based on the confusion matrix. This performance translated to precise classification of vegetation, soil, and water within the stream area. The study's findings demonstrate the effectiveness of drone remote sensing and SVM techniques in developing accurate vegetation cover classification models for small streams. These models hold immense potential for various applications, including stream monitoring, informed management practices, and effective stream restoration efforts. By incorporating images and additional details about the specific drone and sensors technology, we can gain a deeper understanding of small streams and develop effective strategies for stream protection and management.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.2
• /
• pp.52-61
• /
• 2018

Urban heat islands occur due to increases in the extent of artificial surfaces such as concrete, asphalt and high-rise buildings. In this regard, research into the use of satellite thermal infrared images for thermal environment analysis of urban areas is being carried out. However, such analysis of the characteristics of individual land cover with low-resolution satellite images suffers from limitations because land cover patterns in urban areas are complicated. Recently, UAV has been widely used, which can compensate for this limitation as it is able to acquire high-resolution images. In this paper, the accuracy of UAV infrared images is verified and the applicability of UAV in urban thermal environment analysis is examined by comparing the results with land surface temperatures from Landsat 8 thermal images. The results show a high positive correlation of temperature values at 0.95, and no statistically significant difference between the two groups. Comparisons of land surface temperature according to land cover showed that the largest difference observed was $4.63^{\circ}C$ in the Used area, and UAV images with small cell units reflected various surface temperatures. Furthermore, it was possible to analyze the surface temperatures of various green spaces such as wetlands and street tree areas, which can lower surface temperatures in urban areas, with street tree shadows reducing surface temperatures by about $4-6^{\circ}C$. UAV can easily and rapidly measure the surface temperature of urban areas and is able to analyze various types of green spaces. Thus, this is an effective tool for thermal environment analysis in urban areas to aid in the design or management of urban green spaces, as it can allow for land cover and the effects of the various green spaces.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.5
• /
• pp.594-604
• /
• 2021

To evaluate the causes of beach erosion in Sinji-Myeongsasimni Beach, external forces, such as tides, tidal currents, and waves, were observed seasonally from March 2019 to March 2020, and the surface sediments were analyzed for this period. In addition, the shoreline positions and beach elevations were regularly surveyed with a VRS GPS and fixed-wing drone. From these field data, the speed of the tidal currents was noted to be insufficient, but the waves were observed to af ect the deformation of the beach. As the beach is open to the southern direction, waves of heights over 1 m were received in the S-SE direction during the spring, summer, and fall seasons. Large waves with heights over 2 m were observed during typhoons in summer and fall. Because of the absence of typhoons for the previous two years from July 2018, the beach area over datum level (DL) as of July 2018 was greater by 30,138m² compared with that of March 2019, and the beach area as of March 2020 decreased by 61,210m² compared with that of March 2019 because of four typhoon attacks after July 2018. The beach volume as of March 2019 decreased by 5.4% compared with that of July 2018 owing to two typhoons, and the beach volume as of September 2019 decreased by 7.3% because of two typhoons during the observation year. However, the volume recovered slightly by about 3% during fall and winter, when there were no high waves. According to the sediment transport vectors by GSTA, the sediments were weakly influxed from small streams located at the center of the beach; the movement vectors were not noticeable at the west beach site, but the westward sediment transport under the water and seaward vectors from the foreshore beach were prominently observed at the east beach site. These patterns of westward sediment vectors could be explained by the angle between the annual mean incident wave direction and beach opening direction. This angle was inclined 24° counterclockwise with the west-east direction. Therefore, the westward wave-induced currents developed strongly during the large-wave seasons. Hence, the sand content is high in the west-side beach but the east-side beach has been eroded seriously, where the pebbles are exposed and sand dune has decreased because of the lack of sand sources except for the soiled dunes. Therefore, it is proposed that efforts for creating new sediment sources, such as beach nourishment and reducing wave heights via submerged breakwaters, be undertaken for the eastside of the beach.