• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.1
• /
• pp.30-44
• /
• 2022

The advent of deep learning-based algorithms has facilitated researches on target detection from synthetic aperture radar(SAR) imagery. While most of them concentrate on detection tasks for ships with open SAR ship datasets and for aircraft from SAR scenes of airports, there is relatively scarce researches on the detection of SAR ground vehicle targets where several adverse factors such as high false alarm rates, low signal-to-clutter ratios, and multiple targets in close proximity are predicted to degrade the performances. In this paper, a dataset of ground vehicle targets acquired from TerraSAR-X(TSX) satellite SAR images is presented. Then, both detection and instance segmentation are simultaneously carried out on this dataset based on the deep learning-based Mask R-CNN. Finally, this paper shows the future research directions to further improve the performances of detecting the SAR ground vehicle targets.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.111-114
• /
• 2007

One of future remote sensing techniques for the estimation of damage by storm and flood is the extraction of water area, which could be the basis of measuring the damage by storm and flood and estimate restoration cost. This paper introduces an approach to damage estimation using satellite Image. The project site was Ansung area and a set of Radarsat-1 SAR image at 6.25m resolution was used for the test. Authors investigated methods of SAR image processing such as shadow-effect removal, orthorectification of SAR image and calculation of damage area by flood. Consequetly, this study showed that technique improvement of image processing and the best of result for extracting water area. Also, found the new possibility of damage estimation using satellite image.

• Proceedings of the KSRS Conference
• /
• 2007.03a
• /
• pp.126-129
• /
• 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. The MRF is incorporated into digital image analysis by viewing pixel type s as states of molecules in a lattice-like physical system defined on a GRF. Because of the MRFGRF equivalence, the assignment of an energy function to the physical system determines its Gibbs measure, which is used to model molecular mteractions. The proposed adaptive iterative method was evaluated using simulation data generated by the Monte Carlo method. In the extensive experiments of this study, the proposed method demonstrated the capability to relax speckle noise and estimate noise-free intensity.

• 한국지형공간정보학회:학술대회논문집
• /
• 2002.11a
• /
• pp.51-57
• /
• 2002

국내에서 활발하게 연구되고 있는 위성영상을 이용한 원격탐사는 매핑, 환경관리, 시설물 관리 등에 이용되어 왔다. 본 연구에서는 날씨나 태양의 제약을 받지 않는 RADARSAT SAR 영상의 수계지역을 신경망 기법을 이용하여 분류하고자 하였다. RADARSAT은 경사관측을 통하여 영상을 취득하며 지형의 기복에 의한 음영효과(Shadow effect)로 인하여 수계지역 분류시 정확도를 감소시킨다. 이러한 문제를 해결하기 위해서 본 연구에서는 RADARSAT SAR 영상의 역산란계수를 계산하고 음영효과에 의한 분류오류를 감소시키기 위하여 수치고도모형을 사용하였다. 지형의 기복이 작은 평지와 지형의 기복이 심한 산악지로 나누어 연구를 수행하여 각 지역별로 분류 정확도를 평가하였다. 연구결과로 역산란계수를 신경망기법의 단일 입력 자료로 사용한 경우보다 수치고도모형을 같이 사용한 것이 분류 정확도가 높았다. 또한, 수치고도모형을 역산란계수와 함께 입력 자료로 이용할 경우 평지보다 산악지에서 효율적이었다. 산악지역이 많은 국내에서는 SAR영상의 수계지역 추출을 신경망 기법으로 할 경우에는 수치고도모형을 함께 이용함으로써 분류정확도 향상을 시킬 수 있다고 사료된다.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.431-444
• /
• 2014

As applications of spaceborne SAR imagery are extended, there are increased demands for accurate registrations for better understanding and fusion of radar images. It becomes common to adopt multi-resolution SAR images to apply for wide area reconnaissance. Geometric correction of the SAR images can be performed by using satellite orbit and attitude information. However, the inherent errors of the SAR sensor's attitude and ground geographical data tend to cause geometric errors in the produced SAR image. These errors should be corrected when the SAR images are applied for multi-temporal analysis, change detection applications and image fusion with other sensor images. The undesirable ground registration errors can be corrected with respect to the true ground control points in order to produce complete SAR products. Speeded Up Robust Feature (SURF) technique is an efficient algorithm to extract ground control points from images but is considered to be inappropriate to apply to SAR images due to high speckle noises. In this paper, an attempt is made to apply SURF algorithm to SAR images for image registration and fusion. Matched points are extracted with respect to the varying parameters of Hessian and SURF matching thresholds, and the performance is analyzed by measuring the imaging matching accuracies. A number of performance measures concerning image registration are suggested to validate the use of SURF for spaceborne SAR images. Various simulations methodologies are suggested the validate the use of SURF for the geometric correction and image registrations and it is shown that a good choice of input parameters to the SURF algorithm should be made to apply for the spaceborne SAR images of moderate resolutions.

• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.351-358
• /
• 2017

A new method to decompose the footprints of marine atmosphere boundary layer (MABL) on Synthetic Aperture Radar (SAR) imagery into characteristic spatial scales is proposed. Using two-dimensional Empirical Mode Decomposition (EMD) we obtain three Intrinsic Mode Functions (IMFs), which mainly present longitudinal rolls, three-dimensional cells and atmospheric gravity waves (AGW). The rolls and cells have spatial scales between 3.0 km and 3.8 km and between 5.3 km and 7.1 km, respectively. Based on previous observations and mixed-layer similarity theory, we estimated MABL's depths that vary from 0.95 km to 1.2 km over the rolls and from 3.0 km to 3.8 km over the cells. The AGW has maximum spectrum at 14.3 km wavelength. The method developed in this work can be used to decompose other satellite imageries into individual features through characteristic spatial scales.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.9
• /
• pp.854-864
• /
• 2016

The use of small drone platform has become a popular topic in these days but its application for SAR operation has been little known due to the burden of the payload implementation. Drone platforms are distinguished from the conventional UAV system by the increased vulnerability to the turbulences, control-errors and poor motion stability. Consequently, sophisticated motion compensation may be required to guarantee the successful acquisition of high quality SAR imagery. Extremely limited power and mass budgets may prevent the use of additional hardwares for motion compensation and the difficulty of SAR focusing is further aggravated. In this paper, we have carried out a feasibility study of mico-SAR drone operation. We present the image acquisition results from the preliminary flight tests and a quality assessment is followed on the experimental SAR images. The in-flight motion errors derived from the unique drone movements are investigated and attempts have been made to compensate for the geometrical and phase errors caused by motions against the nominal trajectory. Finally, the successful operation of drone SAR system is validated through the focussed SAR images taken over test sites.

• Proceedings of KOSOMES biannual meeting
• /
• 2004.11a
• /
• pp.43-47
• /
• 2004

Two different sensors (here, KOMPSAT and RADARSAT) are considered for ship detection, and are used to delineate the detection performance for their data The experiments are set for coastal regions of Mokpo Port and Ulsan Port and field experiments on board pilot boat are conducted to collect in situ ship validation information such as ship type and length This paper introduce mainly the experiment result of ship detection by both RADARSAT SAR imagery and land-based RADAR data, operated by the local Authority of South Korean, so called vessel traffic system (VTS) radar. Fine imagery of Ulsan Port was acquired on June 19, 2004 and in-situ data such as wind speed and direction, taking pictures of ships and natural features were obtained aboard a pilot ship. North winds, with a maximum speed of 3.1 m/s were recorded Ship's position, size and shape and natural features of breakwaters, oil pipeline and alongside ship were compared using SAR and VTS. It is shown that KOMPSAT/EOC has a good performance in the detection of a moving ship at a speed of kts or more an hour that ship and its wake can be imaged. The detection capability of RADARSAT doesn't matter how fast ship is running and depends on a ship itself, e.g. its material, length and type. Our results indicate that SAR can be applicable to automated ship detection for a VTS and SAR combination service.

• 한국지형공간정보학회:학술대회논문집
• /
• 2002.03a
• /
• pp.48-53
• /
• 2002

본 연구에서는 각각 1998년 8월 12일(홍수 발생시), 8월 19일(홍수 발생 후) 옥천, 보은 지역을 촬영한 RADARSAT SAR 위성영상을 이용하여 수계지역 및 홍수지역 분류를 수행하고자 하였다. 이를 위해, 먼저 두 장의 위성영상에 대해서 각각 스페클 잡영(speckle noise)을 제거하고, ${\sigma}^0$(sigma naught, dB)을 계산한 후 수계지역에 대한 ${\sigma}^0$값을 분석하였다. 이 값을 기준으로 각각 두 장의 위성영상에서 각각 최대우도법을 이용하여 수계지역을 분류하였다. SAR 영상은 영상취득의 원리에 의해 지형의 기복에 따른 음영효과(shadow effect)가 발생하는데, 음영효과가 발생하는 지역의 ${\sigma}^0$값은 수계지역과 비슷한 반사특성(낮은 dB 값)을 보인다. 따라서 지형의 기복이 심한 지역의 수계지역 분류시 음영효과를 제거해야 효과적적인 분류를 할 수 있으며, 이를 위해 위성의 헤더자료로부터 촬영시 각각의 촬영중심을 계산하고, 촬영중심과 지상좌표와의 기하학적 관계를 고려하여 음영효과를 제거하였다. 마지막으로, 수계지역만이 추출된 영상에 대해 영상의 기하보정을 수행하였으며, 기하 보정된 두장의 위성영상에 대해 차분영상를 생성함으로서 홍수지역을 분류하였다.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.186-191
• /
• 1998

The first step in change detection in any SAR monitoring, including SAR interferometry, is the co-registration of the images. CCPs (Ground Control Points) for co-registration are usually detected manually, but for qualitative analyses of enormous volumes of data, some automation of the process will become necessary. An automated determination of common CCPs for the same path/row data is especially desirable. We selected the intersections of linear features as the candidates of common GCPs Very bright point targets, which are commonly used as GCPs, have the drawback of appearing and disappearing depending on the conditions of the observation. But in the case of linear features, some detailed elements may appear differently in some case, but the overall line-likeness will remain. In this study, we selected 18 common GCPs for a single-look JERS-1 SAR image of Omaezaki area in central Japan. Although the GCPs in the first image had to be selected either interactively or semi-automatically, the same GCPs in all other images were successively detected automatically using a tiny sub-image around each GCP and a dilated mask of each linear feature in the first image as the reference data.