• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.765-779
• /
• 2022

This study evaluates the accuracy in identifying the burned area in South Korea using multi-temporal data from Sentinel-2 MSI and Landsat 8/9 OLI. Spectral indices such as the Difference Normalized Burn Ratio (dNBR), Relative Difference Normalized Burn Ratio (RdNBR), and Burned Area Index (BAI) were used to identify the burned area in the March 2022 forest fire in Uljin. Based on the results of six indices, the accuracy to detect the burned area was assessed for four satellites using Sentinel-2 and Landsat 8/9, respectively. Sentinel-2 and Landsat 8/9 produce images every 16 and 10 days, respectively, although it is difficult to acquire clear images due to clouds. Furthermore, using images taken before and after a forest fire to examine the burned area results in a rapid shift because vegetation growth in South Korea began in April, making it difficult to detect. Because Sentinel-2 and Landsat 8/9 images from February to May are based on the same date, this study is able to compare the indices with a relatively high detection accuracy and gets over the temporal resolution limitation. The results of this study are expected to be applied in the development of new indices to detect burned areas and indices that are optimized to detect South Korean forest fires.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.257-274
• /
• 2021

Although image segmentation is a critical part of object-based analysis of high resolution imagery, there has been lack of studies to evaluate the quality of image segmentation. In this study, we aimed to find practical and effective methods to obtain optimal parameters for image segmentation. Evaluations of image segmentation are divided into unsupervised, supervised, and qualitative visual interpretation methods. Using the multispectral UAV images, sampled from urban and forest over the Incheon Metropolitan City Park, three evaluation methods were compared. In overall, three methods showed very similar results regardless of the computational costs and applicability, although the optimal parameters determined by the evaluations were different between the urban and forest images. There is no single measure that outperforms in the unsupervised evaluation. Any combinations of intra-segment measures (V, COV, WV) and inter-segment measures (MI, BSH, DTNP) provided almost the same results. Although supervised method may be biased by subjective selection of reference data, it can be easily applied to detect object of interest. The qualitative visual interpretation on the segmentation results corresponded with the unsupervised and supervised evaluations.

• Ecology and Resilient Infrastructure
• /
• v.9 no.4
• /
• pp.218-227
• /
• 2022

This study attempted classification through deep learning-based image training for land cover classification in river spaces which is one of the important data for efficient river management. For this purpose, land cover classification analysis with the RGB image of the target section based on the category classification index of major land cover map was conducted by using the learning outcomes from the result of labeling. In addition, land cover classification of the river spaces was performed by unsupervised and supervised classification from Sentinel-2 satellite images provided in an open format, and this was compared with the results of deep learning-based image classification. As a result of the analysis, it showed more accurate prediction results compared to unsupervised classification results, and it presented significantly improved classification results in the case of high-resolution images. The result of this study showed the possibility of classifying water areas and wetlands in the river spaces, and if additional research is performed in the future, the deep learning based image train method for the land cover classification could be used for river management.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.157-168
• /
• 2023

Image segmentation and supervised classification techniques are widely used to monitor the ground surface using high-resolution remote sensing images. In order to classify various objects, a process of defining a class corresponding to each object and selecting samples belonging to each class is required. Existing methods for extracting class samples should select a sufficient number of samples having similar intensity characteristics for each class. This process depends on the user's visual identification and takes a lot of time. Representative samples of the class extracted are likely to vary depending on the user, and as a result, the classification performance is greatly affected by the class sample extraction result. In this study, we propose an image classification technique that minimizes user intervention when extracting class samples by applying the histogram back-projection technique and has consistent intensity characteristics of samples belonging to classes. The proposed classification technique using histogram back-projection showed improved classification accuracy in both the experiment using hue subchannels of the hue saturation value transformed image from Compact Advanced Satellite 500-1 imagery and the experiment using the original image compared to the technique that did not use histogram back-projection.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.33-43
• /
• 2024

This research assessed the applicability of the You Only Look Once (YOLO)v8 and DeepLabv3+ models for the effective detection of compost heaps, identified as a significant source of non-point source pollution. Utilizing high-resolution imagery acquired through Unmanned Aerial Vehicles(UAVs), the study conducted a comprehensive comparison and analysis of the quantitative and qualitative performances. In the quantitative evaluation, the YOLOv8 model demonstrated superior performance across various metrics, particularly in its ability to accurately distinguish the presence or absence of covers on compost heaps. These outcomes imply that the YOLOv8 model is highly effective in the precise detection and classification of compost heaps, thereby providing a novel approach for assessing the management grades of compost heaps and contributing to non-point source pollution management. This study suggests that utilizing UAVs and deep learning technologies for detecting and managing compost heaps can address the constraints linked to traditional field survey methods, thereby facilitating the establishment of accurate and effective non-point source pollution management strategies, and contributing to the safeguarding of aquatic environments.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1679-1692
• /
• 2023

South Korea is a country that emits a large amount of pollutants as a result of population growth and industrial development and is also severely affected by transboundary air pollution due to its geographical location. As pollutants from both domestic and foreign sources contribute to air pollution in Korea, the location of air pollutant emission sources is crucial for understanding the movement and distribution of pollutants in the atmosphere and establishing national-level air pollution management and response strategies. Based on this background, this study aims to effectively acquire spatial information on domestic and international air pollutant emission sources, which is essential for analyzing air pollution status, by utilizing high-resolution optical satellite images and deep learning-based image segmentation models. In particular, industrial parks and quarries, which have been evaluated as contributing significantly to transboundary air pollution, were selected as the main research subjects, and images of these areas from multi-purpose satellites 3 and 3A were collected, preprocessed, and converted into input and label data for model training. As a result of training the U-Net model using this data, the overall accuracy of 0.8484 and mean Intersection over Union (mIoU) of 0.6490 were achieved, and the predicted maps showed significant results in extracting object boundaries more accurately than the label data created by course annotations.

• Korean Journal of Remote Sensing
• /
• v.29 no.5
• /
• pp.517-525
• /
• 2013

Time-series data of Normal Difference Vegetation Index (NDVI) obtained by the Moderate-resolution Imaging Spectroradiometer(MODIS) satellite imagery gives a waveform that reveals the characteristics of the phenology. The waveform can be decomposed into harmonics of various periods by the Fourier transformation. The resulting $n^{th}$ harmonics represent the amount of NDVI change in a period of a year divided by n. The values of each harmonics or their relative relation have been used to classify the vegetation species and to build a vegetation map. Here, we propose a method to estimate the annual amount of carbon absorbed on the forest from the $1^{st}$ harmonic NDVI value. The $1^{st}$ harmonic value represents the amount of growth of the leaves. By the allometric equation of trees, the growth of leaves can be considered to be proportional to the total amount of carbon absorption. We compared the $1^{st}$ harmonic NDVI values of the 6220 sample points with the reference data of the carbon absorption obtained by the field survey in the forest of South Korea. The $1^{st}$ harmonic values were roughly proportional to the amount of carbon absorption irrespective of the species and ages of the vegetation. The resulting proportionality constant between the carbon absorption and the $1^{st}$ harmonic value was 236 tCO2/5.29ha/year. The total amount of carbon dioxide absorption in the forest of South Korea over the last ten years has been estimated to be about 56 million ton, and this coincides with the previous reports obtained by other methods. Considering that the amount of the carbon absorption becomes a kind of currency like carbon credit, our method is very useful due to its generality.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1177-1186
• /
• 2021

As the Arctic melt ponds play an important role in determining the interannual variation of the sea ice extent and changes in the Arctic environment, it is crucial to monitor the Arctic melt ponds with high accuracy. Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), which is the NASA's latest altimeter satellite based on the green laser (532 nm), observes the global surface elevation. When compared to the CryoSat-2 altimetry satellite whose along-track resolution is 250 m, ICESat-2 is highly expected to provide much more detailed information about Arctic melt ponds thanks to its high along-track resolution of 70 cm. The basic products of ICESat-2 are the surface height and the number of reflected photons. To aggregate the neighboring information of a specific ICESat-2 photon, the segments of photons with 10 m length were used. The standard deviation of the height and the total number of photons were calculated for each segment. As the melt ponds have the smoother surface than the sea ice, the lower variation of the height over melt ponds can make the melt ponds distinguished from the sea ice. When the melt ponds were extracted, the number of photons per segment was used to classify the melt ponds covered with open-water and specular ice. As photons are much more absorbed in the water-covered melt pondsthan the melt ponds with the specular ice, the number of photons persegment can distinguish the water- and ice-covered ponds. As a result, the suggested melt pond detection method was able to classify the sea ice, water-covered melt ponds, and ice-covered melt ponds. A qualitative analysis was conducted using the Sentinel-2 optical imagery. The suggested method successfully classified the water- and ice-covered ponds which were difficult to distinguish with Sentinel-2 optical images. Lastly, the pros and cons of the melt pond detection using satellite altimetry and optical images were discussed.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1009-1029
• /
• 2023

Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R² of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R² of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.