IEEE Asia-Pacific Conference on Synthetic Aperture Radar 

Abstract: This paper summarizes the calibration and validation results of the JAXA's new airborne polarimetric interferometric L-band synthetic aperture radar, i.e., Pi-SAR-L2, developed in 2011-2012 and started the operation in April of 2012. Pi-SAR-L2 is enhanced for the radiometric and geometric performances with 85MHz bandwidth and the accurate Inertial Navigation System. Polarimetric and geometric calibration has been conducted using the corner reflectors and the forest at Tomakomai-forest in Hokkaido. Statistical evaluation of the data acquired at the various test sites determined the noise equivalent sigma-zero as -54dB, which is significantly low enough value to apply the Pi-SAR-L2 at the various research areas.

Abstract: As for the problem of too long training time of convolution neural network (CNN), this paper proposes a fast training method for CNN in SAR automatic target recognition (ATR). The CNN is divided into two parts: one that contains all the convolution layers and sub-sampling layers is considered as convolutional auto-encoder (CAE) for unsupervised training to extract high-level features; the other that contains fully connected layers is regarded as shallow neural network (SNN) to work as a classifier. The experiment based on MSATR database shows that the proposed method can tremendously reduce the training time with little loss of recognition rate.

Abstract: In this paper, we demonstrate target classification using the proposed features in previously reported research under measurement uncertainty conditions. The MSTAR dataset is widely used real target measurements in automatic target recognition society. Extremely high classification results of the dataset, which are over 90% correct classification, have been reported from some literatures. However, this high classification results could be acquired not only by the classification system, but also the cleanness of the dataset. Therefore, in this paper, more realistic target classification scenarios including target aspect angle estimation error, strong white Gaussian noise, and different combination of test and training targets are applied for classification and its corresponding results are examined. The proposed target feature extraction techniques show the robustness of the measurement uncertainties and excellent classification results.

Abstract: The azimuth multichannel is incorporated into BS-SAR (spotlight SAR, sliding spotlight SAR or TOPS SAR) The signal reconstruction algorithm used for multichannel stripmap SAR may not be effective for multichannel BS-SAR (MC-BS-SAR) In this paper, a multichannel full-aperture azimuth processing algorithm is proposed for a BS-SAR With this method, the azimuth spectrum of multichannel signal can be recovered without aliasing With the recovered signal, further imaging processing can be utilized to focus the multichannel signal

Abstract: In this paper, a design scheme for isoflux pattern antenna suitable for SAR data transmission is presented. An isoflux pattern is suitable for SAR data transmission of LEO satellite requiring wide angle coverage of the earth for the longer time visibility. Also, it is advantageous to provide uniform power density over the earth and constant power transmission to the ground station during the passage on the orbit. Based on the principle of generating isoflux pattern, we design basic isoflux pattern antenna which shows required isoflux characteristics. For improved performance, the basic antenna is optimized with genetic algorithm. The optimized isoflux pattern antenna is designed and implemented and shows rapid skirt characteristics, low side lobe, and low back lobe level.