• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.1
• /
• pp.12-21
• /
• 2021

For successful automatic target recognition(ATR) with synthetic aperture radar(SAR) imagery, SAR target images of the database should have the identical or highly similar resolution with those collected from SAR sensors. However, it is time-consuming or infeasible to construct the multiple databases with different resolutions depending on the operating SAR system. In this paper, an approach for resolution conversion of SAR target images is proposed based on conditional generative adversarial network(cGAN). First, a number of pairs consisting of SAR target images with two different resolutions are obtained via SAR simulation and then used to train the cGAN model. Finally, the model generates the SAR target image whose resolution is converted from the original one. The similarity analysis is performed to validate reliability of the generated images. The cGAN model is further applied to measured MSTAR SAR target images in order to estimate its potential for real application.

• 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.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.5
• /
• pp.443-461
• /
• 2022

Target Detection in synthetic aperture radar(SAR) image is critical for military and national defense. In this paper, we propose YOLOv4-Attention architecture which adds attention modules to YOLOv4 backbone architecture to complement the feature extraction ability for SAR target detection with high accuracy. For training and testing our framework, we present new SAR embedding datasets based on MSTAR SAR public datasets which are about poor environments for target detection such as various clutter, crowded objects, various object size, close to buildings, and weakness of signal-to-clutter ratio. Experiments show that our Attention YOLOv4 architecture outperforms original YOLOv4 architecture in SAR image target detection tasks in poor environments for target detection.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.5
• /
• pp.462-475
• /
• 2022

Different from the field of electro-optical(EO) image analysis, there has been less interest in similarity metrics between synthetic aperture radar(SAR) target images. A reliable and objective similarity analysis for SAR target images is expected to enable the verification of the SAR measurement process or provide the guidelines of target CAD modeling that can be used for simulating realistic SAR target images. For this purpose, this paper presents a similarity analysis method based on the siamese network that quantifies the subjective assessment through the distance learning of similar and dissimilar SAR target image pairs. The proposed method is applied to MSTAR SAR target images of slightly different depression angles and the resultant metrics are compared and analyzed with qualitative evaluation. Since the image similarity is somewhat related to recognition performance, the capacity of the proposed method for target recognition is further checked experimentally with the confusion matrix.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.444-444
• /
• 2023

하천 및 저수지와 같은 공간의 수체 탐지는 수자원 관리에서 매우 중요하며, 유역의 수문학적 과정을 이해하는데 도움을 준다. 수문학적 데이터 수집은 우량계, 수위계와 같은 물리적 인프라의 배치가 필요하다. 그러나 상대적으로 저개발된 국가는 수문학적 측정을 위한 인프라가 매우 미흡한 것이 현실이며, 북한과 같은 비접근 지역에 대한 수문학적 과정을 분석하는데는 한계가 있다. 인공위성 원격탐사 센서 중 SAR영상은 지표면에 직접 전파를 방사하고 산란되어 돌아오는 신호를 수신하여 영상을 만들기 때문에 일반적인 광학영상과는 달리 햇빛의 유무와 강우, 구름여부 등의 기상 조건의 영향을 거의 받지 않는 장점이 있다. 또한 국내와 같이 계절적인 요인과 인간활동에 의해 변화되는 물 순환을 SAR 영상은 지표수의 계절적 및 연간 변동성을 모니터링하는데 매우 유용한 자료로 평가되고 있다. 본 연구는 SAR영상을 이용하여 국내의 검증 가능한 지역의 저수지 수면적 변화를 모니터링하고 저수지 수면적과 저수량 분석을 수행하는 것을 목적으로 하였다. 분석자료인 SAR영상은 ESA의 Sentinel-1영상을 2022년 4월부터 2022년 11월의 자료를 수집하여 소양강댐 저수지 수면적과 저수량과의 관계식을 도출하였다. 수체 추출을 위한 SAR 영상은 특히 수로의 일부 가장자리와 홍수터의 식물 존재로 인한 제외지의 매핑에 부정확성을 포함하여 처리에 몇 가지 단점을 갖는 한계도 존재하지만 악천후의 기상 조건에서도 작동할 수 있는 SAR 영상의 능력 덕분에 규칙적인 시간 간격으로 수체면적의 변화에 대한 정보를 제공할 수 있다. 향후 북한 지역의 주요 댐 저수지 수면적에 대한 연간변화와 장기간의 추세를 분석하는 연구를 진행할 계획이다.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.3
• /
• pp.319-328
• /
• 2024

Semi-supervised learning is a good way to train a classification model using a small number of labeled and large number of unlabeled data. We applied semi-supervised learning to a synthetic aperture radar(SAR) image classification model with a limited number of datasets that are difficult to create. To address the previous difficulties, semi-supervised learning uses a model trained with a small amount of labeled data to generate and learn pseudo labels. Besides, a lot of number of papers use a single fixed threshold to create pseudo labels. In this paper, we present a semi-supervised synthetic aperture radar(SAR) image classification method that applies different thresholds for each class instead of all classes sharing a fixed threshold to improve SAR classification performance with a small number of labeled datasets.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.15 no.3
• /
• pp.208-218
• /
• 2012

Numerical simulation technique has been developed to calculate microwave backscattering from water surface. The simulation plays a role of a substitute for experiments. Validation of the simulation was shown by comparing with experimental results. Water area observations by microwave radar have been simulated to evaluate algorithms and systems. Furthermore, the simulation can be used to understand microwave scattering mechanism on the water surface. The simulation has applied to the various methods for water area observations, and the utilizations of the simulation are introduced in this paper. In the case of fixed radar, we show following examples, 1. Radar image with a pulse Doppler radar, 2. Effect of microwave irradiation width and 3. River observation (Water level observation). In addition, another application (4.Synthetic aperture radar image) is also described. The details of the applications are as follows. 1. Radar image with a pulse Doppler radar: A new system for the sea surface observation is suggested by the simulation. A pulse Doppler radar is assumed to obtain radar images that display amplitude and frequency modulation of backscattered microwaves. The simulation results show that the radar images of the frequency modulation is useful to measure sea surface waves. 2. Effect of microwave irradiation width: It is reported (Rheem[2008]) that microwave irradiation width on the sea surface affects Doppler spectra measured by a CW (Continuous wave) Doppler radar. Therefore the relation between the microwave irradiation width and the Doppler spectra is evaluated numerically. We have shown the suitable condition for wave height estimation by a Doppler radar. 3. River observation (Water level observation): We have also evaluated algorithms to estimate water current and water level of river. The same algorithms to estimate sea surface current and sea surface level are applied to the river observation. The simulation is conducted to confirm the accuracy of the river observation by using a pulse Doppler radar. 4. Synthetic aperture radar (SAR) image: SAR images are helpful to observe the global sea surface. However, imaging mechanisms are complicated and validation of analytical algorithms by SAR images is quite difficult. In order to deal with the problems, SAR images in oceanic scenes are simulated.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.21 no.9
• /
• pp.979-986
• /
• 2010

This paper presents an algorithm for retrieving precise radar cross sections(RCS) of various trihedral corner reflectors (TCR) which are external calibrators of synthetic aperture radar(SAR) systems. The theoretical RCSs of the TCRs are computed based on the physical optics(PO), geometrical optics(GO), and physical theory of diffraction(PTD) techniques; that is, the RCS computation includes the single reflections(PO), double reflections(GO-PO), triple reflections(GO-GO-PO), and edge diffractions(PTD) from the TCR. At first, we acquire an SAR image of the area that five TCRs installed in, and then extract the RCS of the TCRs. The RCSs of the TCRs are extracted accurately from the SAR image by adding up the power spill, which is generated due to the radar IRF(Impulse Response Function), using a square window. We compare the extracted RCSs with the theoretical RCSs and analyze the difference between the theoretical and experimental RCSs of the TCR for various window sizes and various backscattering coefficient levels of the adjacent area. Finally, we propose the minimum size of the integration area and the maximum level of the backscattering coefficients for the adjacent area.

• 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.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.2
• /
• pp.103-112
• /
• 2012

We demonstrate the preliminary results of ship detection application using synthetic aperture radar (SAR) and automatic identification system (AIS) together. Multi-frequency and multi-temporal SAR images such as TerraSAR-X and Cosmo-SkyMed (X-band), and Radarsat-2 (C-band) are acquired over the West Sea in South Korea. In order to compare with SAR data, we also collected an AIS data. The SAR data are pre-processed considering by the characteristics of scattering mechanism as for sea surface. We proposed the "Adaptive Threshold Algorithm" for classification ship efficiently. The analyses using the combination of the SAR and AIS data with time series will be very useful to ship detection or tracing of the ship.