• Korean Journal of Remote Sensing
• /
• v.23 no.1
• /
• pp.33-42
• /
• 2007

In this paper, an iterative MAP approach using a Bayesian model based on the lognormal distribution for image intensity and a GRF for image texture is proposed for despeckling the SAR images that are corrupted by multiplicative speckle noise. When the image intensity is logarithmically transformed, the speckle noise is approximately Gaussian additive noise, and it tends to a normal probability much faster than the intensity distribution. MRFs have been used to model spatially correlated and signal-dependent phenomena for SAR speckled images. The MRF is incorporated into digital image analysis by viewing pixel types as slates of molecules in a lattice-like physical system defined on a GRF Because of the MRF-SRF equivalence, the assignment of an energy function to the physical system determines its Gibbs measure, which is used to model molecular interactions. The proposed Point-Jacobian Iterative MAP estimation method was first evaluated using simulation data generated by the Monte Carlo method. The methodology was then applied to data acquired by the ESA's ERS satellite on Nonsan area of Korean Peninsula. In the extensive experiments of this study, The proposed method demonstrated the capability to relax speckle noise and estimate noise-free intensity.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.3
• /
• pp.219-230
• /
• 2022

In implementing a robust automatic target recognition(ATR) system with synthetic aperture radar(SAR) imagery, one of the most important issues is accurate classification of target variants, which are the same targets with different serial numbers, configurations and versions, etc. In this paper, a deep learning network with channel attention modules is proposed to cope with the recognition problem for target variants based on the previous research findings that the channel attention mechanism selectively emphasizes the useful features for target recognition. Different from other existing attention methods, this paper employs the channel attention modules without dimensionality reduction along the channel direction from which direct correspondence between feature map channels can be preserved and the features valuable for recognizing SAR target variants can be effectively derived. Experiments with the public benchmark dataset demonstrate that the proposed scheme is superior to the network with other existing channel attention modules.

• Korean Journal of Remote Sensing
• /
• v.16 no.1
• /
• pp.13-24
• /
• 2000

SAR imagery usually reveals the influence of antenna look-direction on the delineation of geological structures. In this study, the look-direction bias in SAR image is quantitatively analyzed specifically for geological lineament study. Geologic lineaments are estimated using both Landsat TM and JERS-1 SAR images over the study area to quantitatively compare and analyze the look-direction bias in the SAR image. The standard geologic lineaments in the study area are established from lineaments estimated from TM images, field mapping, and fault lines in a published geologic map. The results show that lineaments normal to radar look-direction are extremely well enhanced while those parallel to look-direction are less visible as expected. However, certain lineaments even parallel to radar look-direction can still be detectable in a favorable topographic condition. Compared with TM image, the total number of detected lineaments in each direction in the SAR image increases or decreases ranging from 33% to 159% in length and from 28% to 187% in occurrence. The ratio of lineaments in SAR image to those in TM image with respect to direction can be fitted by a cosine function. The fitted function indicates that geological lineament is more easily detected in SAR image than in TM image within about $\pm$50$^{\circ}$ normal to radar look-direction. And lineaments with limited extension appear to be more sensitive to the look direction bias effect.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.2
• /
• pp.175-186
• /
• 2021

In the field of automatic target recognition(ATR) with synthetic aperture radar(SAR) imagery, it is usually impractical to obtain SAR target images covering a full range of aspect views. When the database consists of SAR target images with limited angular diversity, it can lead to performance degradation of the SAR-ATR system. To address this problem, this paper proposes a deep learning-based method where channel attention modules(CAMs) are inserted to a convolutional neural network(CNN). Motivated by the idea of the squeeze-and-excitation(SE) network, the CAM is considered to help improve recognition performance by selectively emphasizing discriminative features and suppressing ones with less information. After testing various CAM types included in the ResNet18-type base network, the SE CAM and its modified forms are applied to SAR target recognition using MSTAR dataset with different reduction ratios in order to validate recognition performance improvement under the limited angular diversity condition.

• Journal of Cadastre & Land InformatiX
• /
• v.47 no.2
• /
• pp.79-90
• /
• 2017

Urban environment represent one of the most dynamic regions on earth. As in other countries, forests, green areas, agricultural lands are rapidly changing into residential or industrial areas in South Korea. Monitoring such rapid changes in land use requires rapid data acquisition, and satellite imagery can be an effective method to this demand. In general, SAR(Synthetic Aperture Radar) satellites acquire images with an active system, so the brightness of the image is determined by the surface roughness. Therefore, the water areas appears dark due to low reflection intensity, In the residential area where the artificial structures are distributed, the brightness value is higher than other areas due to the strong reflection intensity. If we use these characteristics of SAR images, settlement areas can be extracted efficiently. In this study, extraction of settlement areas was performed using TerraSAR-X of German high-resolution X-band SAR satellite and KOMPSAT-5 of South Korea, and object-oriented image classification method using the image segmentation technique is applied for extraction. In addition, to improve the accuracy of image segmentation, the speckle divergence was first calculated to adjust the reflection intensity of settlement areas. In order to evaluate the accuracy of the two satellite images, settlement areas are classified by applying a pixel-based K-means image classification method. As a result, in the case of TerraSAR-X, the accuracy of the object-oriented image classification technique was 88.5%, that of the pixel-based image classification was 75.9%, and that of KOMPSAT-5 was 87.3% and 74.4%, respectively.

• Korean Journal of Remote Sensing
• /
• v.26 no.2
• /
• pp.115-122
• /
• 2010

In this study, we analyzed ridge-runnel structure and ripple marks by using Envisat ASAR, JERS-1 SAR images and in-situ data in Mongsanpo intertidal flat located in Taean-Gun, Korea. A group of light-and-dark lines parallel to the shoreline, alternating 3-5 times, were observed in the intertidal flat in Envisat ASAR images. The patterns are related to ridge-runnel structure in the intertidal flat exposed to air. Well-drained runnels, typically with ripple marks, showed strong backscattering while runnels submerged by surface water or ridges, typically smooth with no ripple, have weak backscattering coefficients in Envisat ASAR images. In JERS-1 SAR images, however, the backscattering was very low on the entire intertidal flat and no ridge-runnel structure could be observed. The wavelengths of ripple marks measured from in-situ observations have ranges from 4 to 10 cm that satisfies the Bragg scattering condition of the 1st-order in Envisat ASAR images operating in C-band, but not in JERS-1 SAR that used L-band. Through this study using SAR images, we could successfully analyze the sedimentary conditions of intertidal flats with ridge-runnel and ripple marks which are not easily observed by optical sensors. It is expected that the results of this study with SAR images will contribute to the sedimentary research over intertidal flats.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.327-336
• /
• 2019

The caldera lake "Chun-ji" is located at the summit of Baekdu volcano, which is in the border of China and North Korea. Chun-ji Lake has altitude 2,189 m above sea level. The Chun-ji is freezing in the winter when the water temperature goes down to zero for a year, and it melts in the season when the water temperature goes up again. However,since it is located at a high altitude, there are many cloudy days, and it is difficult to observe with optical images. For this reason, radar images, which are less influenced by weather than optical images, are more effective for observing the ice of heaven and earth. In this study, 75 TerraSAR-X images from chun-ji area were used for analysis from 2015 to 2017, and the calculated ice area and temperature changes were analyzed. As a result, the ice of the caldera lake formed was formed in early December and slowly melted until mid-April. During this period, temperatures in the Samjiyeon area were about $-10^{\circ}C$ when ice was produced, and the temperature was about $0^{\circ}C$ in mid-April when it was thawing. Correlation coefficients between ice surface area and temperature in winter 2015 and 2016, where global ice is produced,show a high correlation of -0.82 and -0.75. In addition to the results of this study, it can be used as an indicator to monitor the volcanic activity by comparing the result of the recent volcanic activity with the result of the increase in water temperature using various imagery.

• Proceedings of the KSRS Conference
• /
• 2001.03a
• /
• pp.9-14
• /
• 2001

오랜 기간동안 진행되는 사회간접자본 건설의 진행 상황을 관측하는 것은 대규모 공사의 종합적인 관리를 위해 필수불가결한 요소이다. 동북아 지역의 중추 공항 기능을 담당할 영종도 국제공항의 공사진행 과정을 관측하기 위하여 인공위성 영상 자료가 활용되었다. 바다위에 건설되는 공항의 특성으로 인하여 방조제 건설과 매립공사가 수행되었다. 활주로, 유도로, 여객터미널과 복합교통센터 등이 건설되었으며, 공항의 건설로 산림이 훼손되고 양식장과 염전이 매립되는 것이 관측되었다. 이러한 공항공사의 진척상태를 분석하기 위해서 시계열 Landsat TM 영상을 사용하였으며, 타 위성영상에서는 공항의 공사현황이 어느정도 분석가능한지를 가늠하기 위해서 KOMPSAT EOC, IRS-1C PAN, RADARSAT SAR 영상이 활용되었다. 시계열 Landsat TM 영상에서는 공항 부지의 매립 진척 현황과 산림의 벌채 등을 잘 분석할 수 있었다. KOMPSAT EOC 과 IRS-1C PAN 영상은 높은 공간해상력으로 건설에 사용된 가건물과 같은 세부적인 시설물을 관측할 수 있었다. 15m PAN 영상을 제공하는 Landsat ETM은 IHS 합성 후 분석하였는데, 기존의 TM 영상에서 분류하지 못했던 방조제의 도로와 성토를 구분할 수 있었다. RADARSAT SAR 영상에서는 광학영상에서 볼 수 없었던 독특한 정부 를 얻을 수 있었다.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1030-1032
• /
• 2003

This study a imed to analyze the effect of combined optical and radar image for the land cover classification in coastal region. The study area, Gyeonggi Bay area has one of the largest tidal ranges and has frequent land cover changes due to the several reclamations and rather intensive land uses. Ten land cover types were classified using several datasets of combining Landsat ETM+ and RADARSAT imagery. The synergic effects of the merged datasets were analyzed by both visual interpretation and an ordinary supervised classification. The merged optical and SAR datasets provided better discrimination among the land cover classes in the coastal area. The overall classification accuracy of merged datasets was improved to 86.5% as compared to 78% accuracy of using ETM+ only.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.421-424
• /
• 1999

The purpose of this study is to demonstrate a variety of methods for reducing the speckle noise content of SAR images, whilst at the same time retaining the fined details and average radiometric properties of the original data. In order to increase the accuracy of classification, Two categories of filters are used (speckleblind(simple), Speckle aware(intelligent)) and Segmentation of highly speckled radar imagery is achieved by the use of the Gaussian Markov Random Field model(GMRF). The problems in applying filtering techniques to different object types are discussed and the GMRF procedure and efficiency of the segmentation also discussed.