• 한국전자통신학회논문지
• /
• 제15권6호
• /
• pp.1081-1088
• /
• 2020

본 논문에서는 합성곱 신경망을 기반으로 CCTV 이미지를 통한 해무 탐지 방법을 제안한다. 학습에 필요한 자료로 시정 1km 기준으로 총 11개의 항만 또는 해수욕장(부산항, 부산신항, 평택항, 인천항, 군산항, 대산항, 목포항, 여수광양항, 울산항, 포항항, 해운대해수욕장)에서 수집된 해무와 해무가 아닌 이미지 10004장을 랜덤 추출하였다. 전체 10004장의 데이터셋 중에 80%를 추출하여 합성곱 신경망 모델 학습에 사용하였다. 사용된 모델은 16개의 합성곱층과 3개의 완전 연결층을 가지고 있으며, 마지막 완전 연결층에서 Softmax 분류를 수행하는 합성곱 신경망을 활용하였다. 나머지 20%를 이용하여 모델 정확도 평가를 수행하였고 정확도 평가 결과 약 96%의 분류 정확도를 보였다.

• 한국측량학회지
• /
• 제39권2호
• /
• pp.113-122
• /
• 2021

Urban expansion, particularly converting sub-urban areas to residential and commercial land use in metropolitan areas, has been considered as a significant signal of regional economic development. However, this results in urban climate change. One of the key impacts of rapid urbanization on the environment is the effect of UHI (Urban Heat Island). Understanding the effects of urban land cover change on UHI is crucial for improving the ecology and sustainability of cities. This research reports an application of remote sensing data, GIS (Geographic Information Systems) for assessing effects of urban land cover change on the LST (Land Surface Temperature) and heat budget components in Ho Chi Minh City, where is one of the fastest urbanizing region of Vietnam. The change of urban land cover component and LST in the city was derived by using multi-temporal Landsat data for the period of 1998 - 2020. The analysis showed that, from 1998 to 2020 the city had been drastically urbanized into multiple directions, with the urban areas increasing from approximately 125.281 km² in 1998 to 162.6 km² in 2007, and 267.2 km² in 2020, respectively. The results of retrieved LST revealed the radiant temperature for 1998 ranging from 20.2℃ to 31.2℃, while that for 2020 remarkably higher ranging from 22.1℃ to 42.3℃. The results also revealed that given the same percentage of urban land cover components, vegetation area is more effective to reduce the value of LST, meanwhile the impervious surface is the most effective factor to increase the value of the LST.

• 한국농공학회논문집
• /
• 제64권1호
• /
• pp.15-26
• /
• 2022

3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important dataset for various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manual way is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV images and developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models using different data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN (K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value, using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our model performance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach, while it also classified actual non-crop points (e.g. weeds) as crops.

• 한국농공학회논문집
• /
• 제64권1호
• /
• pp.51-63
• /
• 2022

Up-to-date statistics of crop cultivation status is essential for farm land management planning and the advancement in remote sensing technology allows for rapid update of farming information. The objective of this study was to develop a classification model of rice paddy or winter crop fields based on NDWI, NDVI, and HSV indices using Sentinel-2 satellite images. The 18 locations in central Korea were selected as target areas and photographed once for each during summer and winter with a eBee drone to identify ground truth crop cultivation. The NDWI was used to classify summer paddy fields, while the NDVI and HSV were used and compared in identification of winter crop cultivation areas. The summer paddy field classification with the criteria of -0.195

• 한국물환경학회지
• /
• 제37권6호
• /
• pp.531-538
• /
• 2021

In this study, the TOC in six estuarine reservoirs in the West Sea (Ganwol, Namyang, Daeho, Bunam, Sapkyo, and Asan) was estimated using optically-active water quality factors by the water environment monitoring network. First, specification data and land use maps of each estuarine reservoir were collected. Subsequently, water quality data from 2013 to 2020 were collected. The data comprised of 11 parameters: pH, dissolved oxygen, BOD, COD, suspended solids (SS), total nitrogen, total phosphorus, water temperature, electrical conductivity, total coliforms, and chlorophyll-a (Chl-a). The TOC in the estuarine reservoirs was 4.9~7.0 mg/L, with the highest TOC of 7.0 mg/L observed at the Namyang reservoir, which has a low shape coefficient and high drainage density. The correlation of TOC with water quality factors was also analyzed, and the correlation coefficients of Chl-a and SS were 0.28 and 0.19, respectively, while the correlation coefficients of these factors in the Namyang reservoir were 0.42 and 0.27, respectively. To improve the estimation of TOC using Chl-a and SS, the TOC was averaged in 5 mg/L units, and Chl-a and SS were averaged. Correlation analysis was then performed and the R² of Chl-a-TOC was 0.73. The R² of SS-TOC was 0.73 with a non-linear relationship. TOC had a significant non-linear relationship with Chl-a and SS. However, the relationship should be assessed in terms of the spatial and temporal variations to construct a reliable remote sensing system.

• 한국전자통신학회논문지
• /
• 제17권1호
• /
• pp.91-98
• /
• 2022

본 연구에서는 오픈소스 하드웨어인 라즈베리파이와 딥러닝 기술 기반 객체 탐지 알고리즘을 이용해 부경대학교 교내 유동인구 조사 및 분석을 수행하였다. 라즈베리파이를 이용하여 이미지를 수집한 후 YOLO3의 IMAGEAI, YOLOv5 모델을 사용하여 수집한 이미지의 인물 검출을 진행하였으며 정확도 비교 분석을 위해 Haar-like features, HOG 모델을 사용하였다. 분석결과, 개교기념일로 인한 휴교에 가장 적은 유동인구가 관측되었다. 대체적으로 입구의 유동인구가 출구의 유동인구보다 많았으며, 입구와 출구 모두 학교의 기념일과 행사에 따라 유동인구가 많은 영향을 받는 것으로 나타났다.

• 한국환경과학회지
• /
• 제31권1호
• /
• pp.61-76
• /
• 2022

In this study, surface particulate matter (PM_2.5) concentrations were calculated based on empirical equations using measurements of ceilometer backscatter intensities and meteorological variables taken over 19 months. To quantify the importance of meteorological conditions on the calculations of surface PM_2.5 concentrations, eight different meteorological conditions were considered. For each meteorological condition, the optimal upper limit height for an integration of ceilometer backscatter intensity and coefficients for the empirical equations were determined using cross-validation processes with and without considering meteorological variables. The results showed that the optimal upper limit heights and coefficients depended heavily on the meteorological conditions, which, in turn, exhibited extensive impacts on the estimated surface PM_2.5 concentrations. A comparison with the measurements of surface PM_2.5 concentrations showed that the calculated surface PM_2.5 concentrations exhibited better results (i.e., higher correlation coefficient and lower root mean square error) when considering meteorological variables for all eight meteorological conditions. Furthermore, applying optimal upper limit heights for different weather conditions revealed better results compared with a constant upper limit height (e.g., 150 m) that was used in previous studies. The impacts of vertical distributions of ceilometer backscatter intensities on the calculations of surface PM_2.5 concentrations were also examined.

• 한국군사과학기술학회지
• /
• 제25권4호
• /
• pp.372-380
• /
• 2022

This study proposes a distributed parallel processing system, called the Fast Analysis System for remote sensing daTa(FAST), for large-scale satellite image processing and analysis. FAST is a system that designs jobs in vertices and sequences, and distributes and processes them simultaneously. FAST manages data based on the Hadoop Distributed File System, controls entire jobs based on Apache Spark, and performs tasks in parallel in multiple slave nodes based on a docker container design. FAST enables the high-performance processing of progressively accumulated large-volume satellite images. Because the unit task is performed based on Docker, it is possible to reuse existing source codes for designing and implementing unit tasks. Additionally, the system is robust against software/hardware faults. To prove the capability of the proposed system, we performed an experiment to generate the original satellite images as ortho-images, which is a pre-processing step for all image analyses. In the experiment, when FAST was configured with eight slave nodes, it was found that the processing of a satellite image took less than 30 sec. Through these results, we proved the suitability and practical applicability of the FAST design.

• 한국환경과학회지
• /
• 제31권10호
• /
• pp.815-824
• /
• 2022

It is necessary to understand the amount of snowfall and area of snow cover of Mt. Halla to ensure the safety of mountaineers and to protect the ecosystem of Mt. Halla against climate change. However, there are not enough related studies and observation posts for monitoring snow load. Therefore, to supplement the insufficient data, this study proposes an analysis of snow load and snow cover using normalized-difference snow index. Using the images obtained from the Sentinel2 satellite, the normalized-difference snow index image of Mt. Halla could be acquired. This was examined together with the meteorological data obtained from the existing observatory to analyze the change in snow cover for the years 2020 and 2021. The normalized-difference snow index images showed a smaller snow pixel number in 2021 than that in 2020. This study concluded that 2021 may have been warmer than 2020. In the future, it will be necessary to continuously monitor the amount of snow and the snow-covered area of Mt. Halla using the normalized-difference snow index image analysis method.

• Journal of Forest and Environmental Science
• /
• 제38권3호
• /
• pp.174-183
• /
• 2022

The study aims to examine population indices of mature trees in Jebel Elgarrie forest, Blue Nile State, Sudan. We used remote sensing techniques to stratify the forest into vegetation classes depending on tree density. We distributed 97 circular sample plots (0.1 ha) proportionally to the area of the vegetation classes. In each sample plot we identified, counted and recorded all mature trees (DBH ≥10 cm). We calculated frequency, density, abundance, richness, evenness and diversity for each species and we drew abundance rank curve of mature trees. We used One-Way ANOVA to test for differences (α=0.05) in mean density (No./ha) of mature trees between vegetation classes. Results revealed that the forest was conveniently sub-divided into high density (C1), medium density (C2), low density (C3) and bare farm land (C4) classes. We identified fifteen tree species that belong to 10 families and 14 genera. Combretaceae and Fabaceae were the common families while Anogeissus leiocarpa was the most frequently occurring species. While species diversity varied between vegetation classes, diversity of the forest as a whole is low. While mean density of mature trees in C1, C2, C3 and C4 it was 100, 74, 10, and 0, respectively, it was 54 for the whole forest indicating low stocking, Following One-Way ANOVA, multiple comparisons revealed significant differences in mean density of mature trees between C1 & C3 and C2 & C3. The study provided empirical results on population indices of mature tree species, which would be of importance for successful management and conservation of the forest.