• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1009-1024
• /
• 2018

With the increased use of LiDAR (Light Detection and Ranging) that can obtain over millions of point dataset, methodologies for efficient search and dimensionality reduction for the point cloud became a crucial technique. The existing octree-based "parametric algorithm" has proved its efficiency and contributed as a part of PCL (Point Cloud Library). However, the implementation of the algorithm on GPU (Graphics Processing Unit) is considered very difficult because of structural constraints of the octree implemented in PCL. In this paper, we present a method for the parametric algorithm on GPU environment and implement a projection of the queried points on four directions with an improved noise reduction.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.847-855
• /
• 2018

GMTI (Ground Moving Target Indicator) is a kind of airborne radar function that is used widely in military applications to detect the moving targets on the ground. In this paper, GMTI signal processing technique was presented and its performance was verified using sum and difference channels raw data obtained by the captive flight test.

• Korean Journal of Remote Sensing
• /
• v.35 no.1
• /
• pp.93-115
• /
• 2019

The availability of high-resolution laser scanning data and advanced machine learning algorithms has enabled an accurate potential rockfall source identification. However, the presence of other mass movements, such as landslides within the same region of interest, poses additional challenges to this task. Thus, this research presents a method based on an integration of Gaussian mixture model (GMM) and ensemble artificial neural network (bagging ANN [BANN]) for automatic detection of potential rockfall sources at Kinta Valley area, Malaysia. The GMM was utilised to determine slope angle thresholds of various geomorphological units. Different algorithms(ANN, support vector machine [SVM] and k nearest neighbour [kNN]) were individually tested with various ensemble models (bagging, voting and boosting). Grid search method was adopted to optimise the hyperparameters of the investigated base models. The proposed model achieves excellent results with success and prediction accuracies at 95% and 94%, respectively. In addition, this technique has achieved excellent accuracies (ROC = 95%) over other methods used. Moreover, the proposed model has achieved the optimal prediction accuracies (92%) on the basis of testing data, thereby indicating that the model can be generalised and replicated in different regions, and the proposed method can be applied to various landslide studies.

• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.1-11
• /
• 2021

This study measures the change of ice flow velocity of David Glacier, one of the fast-moving glaciers in East Antarctica that drains through Drygalski Ice Tongue. In order to effectively observe the rapid flow velocity, we applied the offset tracking technique to Sentinel-1A SAR images obtained from 2016 to 2020 with 36-day temporal baseline. The resulting velocity maps were averaged and the two relatively fast points (A1 and A2) were selected for further time-series analysis. The flow velocity increased during the Antarctic summer (around December to March) over the four years' observation period probably due to the ice surface melting and reduced friction on the ice bottom. Bedmap2 showed that the fast flow velocities at A1 and A2 are associated with a sharp decrease in the ice surface and bottom elevation so that ice volumetric cross-section narrows down and the crevasses are being created on the ice surface. The local maxima in standard deviation of ice velocity, S1 and S2, showed random temporal fluctuation due to the rotational ice swirls causing error in offset tracking method. It is suggested that more robust offset tracking method is necessary to incorporate rotational motion.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.33-43
• /
• 2022

This study presents a method to restore an optical satellite image with distortion and occlusion due to fog, haze, and clouds to one that minimizes degradation factors by referring to the same type of peripheral image. Specifically, the time and cost of re-photographing were reduced by partially occluding a region. To maintain the original image's pixel value as much as possible and to maintain restored and unrestored area continuity, a simulation restoration technique modified with the Cycle Generative Adversarial Network (CycleGAN) method was developed. The accuracy of the simulated image was analyzed by comparing CycleGAN and histogram matching, as well as the pixel value distribution, with the original image. The results show that for Site 1 (out of three sites), the root mean square error and R² of CycleGAN were 169.36 and 0.9917, respectively, showing lower errors than those for histogram matching (170.43 and 0.9896, respectively). Further, comparison of the mean and standard deviation values of images simulated by CycleGAN and histogram matching with the ground truth pixel values confirmed the CycleGAN methodology as being closer to the ground truth value. Even for the histogram distribution of the simulated images, CycleGAN was closer to the ground truth than histogram matching.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1771-1777
• /
• 2023

With the advancements of deep learning, many semantic segmentation-based methods for land cover classification have been proposed. However, existing deep learning-based models only use image information and cannot guarantee spatiotemporal consistency. In this study, we propose a land cover classification model using geographical coordinates. First, the coordinate features are extracted through the Coordinate Hash Encoder, which is an extension of the Multi-resolution Hash Encoder, an implicit neural representation technique, to the longitude-latitude coordinate system. Next, we propose an architecture that combines the extracted coordinate features with different levels of U-net decoder. Experimental results show that the proposed method improves the mean intersection over union by about 32% and improves the spatiotemporal consistency.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.37-40
• /
• 2008

The purpose of this paper is to extract DEMs from Spot-3 strips using orbit modeling technique. Spot-3 stereo strip images along 420km in distance were used for experiments. The orbit modeling technique has been suggested to establish accurate geometric models for a whole strip taken on the same orbit using only a small number of GCPs on the top area of the strip. This method enables extraction of orientation parameters of the scene along the strip that is needed to generate DEMs. Consequently, we were able to extract DEMs over the areas without accurate GCPs obtained by GPS surveying per each scene. Assessment of accuracy was carried out using USGS DTED. DEMs generated from the orbit modelling technique suggested showed satisfactory performance when quantitative analysis of accuracy assessment was carried out.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.229-232
• /
• 2005

This paper presents a preliminary analysis result on SAR-related journal papers published since 1960s. Abstracts of more than 2700 peer-reviewed English journal papers were collected and classified into various categories according to their systems, techniques, and application fields. Statistics on each category were provided so that one can understand historical and on-going development in SAR systems, techniques, and a variety of application fields such as land, ocean, cryosphere and atmosphere. This statistical data would be an essential guideline to establish a future SAR system application and satellite manoeuvring policy.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.11a
• /
• pp.384-388
• /
• 2003

현재 고해상도의 원격탐사 영상을 이용하기 위해서는 고가의 비용을 부담해야 하고 데이터의 용량도 매우 커서 실제로 사용에는 대부분의 사람들이 매우 소극적이다. 이미 수집된 저해상도의 활발한 활용을 위해서는 값이 저렴하면서도 해상도가 좋은 분광력이나 지상해상도를 높여주어야 한다. 따라서 본 연구에서는 해상도가 각기 다른 영상을 관련 자료들을 근거로 20년 전에 저해상도인 30m의 위성영상과 5m의 고해상도 위성사진과의 합성을 통하여 저해상도에서 판독할 수 없었던 여러 종류의 지형지물을 파악할 수 있는 고해상도의 퓨젼 영상을 생성시킨 것이다.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.268-273
• /
• 1998

This study applies an on-line system, which employes an adaptive reconstruction technique to monitor and forecast ocean surface changes. The system adaptively generates an appropriate synthetic time series with recovering missing measurements for sequential images. The reconstruction method incorporates temporal variation according to physical properties of targets and anisotropic spatial optical properties into image processing techniques. This adaptive approach allows successive refinement of the structure of objects that are barely detectable in the observed series. The system sequentially collects the estimated results from the adaptive reconstruction and then statistically analyzes them to monitor and forecast the change in surface characteristics.