• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1858-1872
• /
• 2023

With the advance of radar technologies, the availability of synthetic aperture radar (SAR) images increases. To improve application of SAR images, a management system for SAR images is proposed in this paper. The system provides trainable land cover classification module and display of SAR images on the map. Users of the system can create their own classifier with their data, and obtain the classified results of newly captured SAR images by applying the classifier to the images. The classifier is based on convolutional neural network structure. Since there are differences among SAR images depending on capturing method and devices, a fixed classifier cannot cover all types of SAR land cover classification problems. Thus, it is adopted to create each user's classifier. In our experiments, it is shown that the module works well with two different SAR datasets. With this system, SAR data and land cover classification results are managed and easily displayed.

• 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.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.11
• /
• pp.1092-1100
• /
• 2011

A C-band ground-based rotational SAR system is presented in this paper. The rotaional SAR system is a test-bed for future rotational SAR systems which can be deployed in space and on a tower. The test-bed system is designed for imaging the electromagnetic scattering from earth surfaces and buried targets. This paper also presents the examination results of the generated SAR images. This rotational SAR system is basically consisted of the network-analyzer based HPS(Hongik Polarimetric Scatterometer) and a horizontally rotating arm. Several SAR images were obtained using the rotational SAR system for various target areas. To verify this system, we simulated the SAR images for the rotational SAR using the FDTD algorithm and compared between the measured and simulated SAR images. The rotational SAR system is operated at the center frequency of 5 GHz and various frequency bandwidth within 0.5~2 GHz to change the resolution of SAR images.

• 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 Korean Society for Geospatial Information Science
• /
• v.21 no.4
• /
• pp.109-116
• /
• 2013

To extract the 3D geometric information from SAR(Synthetic Aperture Radar) images, two different techniques, interferometric SAR and radargrammetry, have been widely used. InSAR is most widely used for the generation of precise DEM(Digital Elevation Model) until now. But, Interferometric SAR requires severe temporal correlation over areas covered with vegetation and high relief areas. Because radargrammetry is less sensible to temporal correlation, it can provide better results than interferometric SAR in certain, especially X-band SAR. In this paper, we assess the properties of DEMs generated by radargrammetry using stereo C-band RADARSAT-1 images and X-band TerraSAR-X images.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.692-694
• /
• 2006

X-SAR images taken on the coastal waters of Hwanghe province in Korea during SIR-C/X-SAR campaign in April and October 1994 are analysed. The SAR images show the peculiar signatures like nail marks, curved long string, and vortex streets patterns and they all seem to be produced by strong interactions between the topography in the coastal waters and tidal currents. The nail mark signatures are located at the same position of small scaled sand banks and the curved line patterns are almost identical to the outer boundary of large sand banks. Based on the tidal record, all the three images are taken at the almost same phase of tidal cycles, which are close to the low tide. It seems that bottom shapes are more strongly appeared on the SAR images when the tidal currents are slow. The front between two different current velocities caused by the flows along the steep boundaries of sandbanks is also the main factors imprinting the bottom features to the sea surface SAR images

• Korean Journal of Remote Sensing
• /
• v.22 no.5
• /
• pp.415-419
• /
• 2006

X-SAR images taken on the coastal waters of Hwanghe province in Korea during SIR-C/X-SAR campaign in April and October 1994 are analysed. The SAR images show the peculiar signatures like nail marks, curved long string, and vortex street patterns and they all seem to be produced by strong interactions between the topography in the coastal waters and tidal currents. The nail mark signatures are located at the same position of small scaled sand banks and the curved line patterns are almost identical to the outer boundary of large sand banks. Based on the tidal records, all the three images are taken at the almost same phase of tidal cycles, which are close to the low tide. It seems that bottom shapes are more strongly appeared on the SAR images when the tidal currents are slow. The front between two different current velocities caused by the flows along the steep boundaries of sandbanks is also the main factors imprinting the bottom features to the sea surface SAR images.

• Aerospace Engineering and Technology
• /
• v.11 no.2
• /
• pp.164-170
• /
• 2012

This paper presents that the comparison results of AT (Active Transponder) positions obtained from different measurements: the result of GPS device and evaluated position from the SAR (Synthetic Aperture Radar) image, and active transponders can be useful as GCPs(Ground Control Points) in SAR images. The X-band AT are installed on the wide-and-flat area to improve SCR(signal-to-clutter ration), and activated to represent impulse response function in order to operate as one point target in SAR images. Cosmo-SkyMed operating at X-band frequency are used to provide SAR images of AT. The comparison of AT position is performed by using the result of GPS device field measurement and AT SAR images. ENVI-SARscape S/W is used to evaluate AT position in the SAR images. From the comparison, it is shown that AT are useful as GCPs for SAR images.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.207-212
• /
• 1998

It is not easy to identify a ground control point (GCP) or even locate its vicinity from a SAR image. Although simulated SAR images may be useful to interpret mountain areas, they are not useful in flat areas because they do not show ground coverage or key features such as rivers, lakes and roads. In this study, we developed a method to simulate SAR images integrating geographical features to DEM to facilitate to locate ground control features from SAR images.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.1-9
• /
• 2022

Ship detection in synthetic aperture radar (SAR) images is an important application in marine monitoring for the military and civilian domains. Over the past decade, object detection has achieved significant progress with the development of convolutional neural networks (CNNs) and lot of labeled databases. However, due to difficulty in collecting and labeling SAR images, it is still a challenging task to solve SAR ship detection CNNs. To overcome the problem, some methods have employed conventional data augmentation techniques such as flipping, cropping, and affine transformation, but it is insufficient to achieve robust performance to handle a wide variety of types of ships. In this paper, we present a novel and effective approach for deep SAR ship detection, that exploits label-rich Electro-Optical (EO) images. The proposed method consists of two components: a data augmentation network and a ship detection network. First, we train the data augmentation network based on conditional generative adversarial network (cGAN), which aims to generate additional SAR images from EO images. Since it is trained using unpaired EO and SAR images, we impose the cycle-consistency loss to preserve the structural information while translating the characteristics of the images. After training the data augmentation network, we leverage the augmented dataset constituted with real and translated SAR images to train the ship detection network. The experimental results include qualitative evaluation of the translated SAR images and the comparison of detection performance of the networks, trained with non-augmented and augmented dataset, which demonstrates the effectiveness of the proposed framework.