Compared with optical images, polarimetric synthetic aperture radar (PolSAR) images usually maintain lower resolution. Ship targets in PolSAR images have fewer pixels than those in optical images. Therefore, architectures such as Faster R-CNN and its variations that focus more on target pixels may fail for PolSAR images. Due to limited data and the simple geometric structures of small ship targets, the R-CNN framework with a large neural network as its backbone easily overfits the training set. In this article, we propose a novel lightweight patch-to-pixel convolutional neural network (P2P-CNN) for ship detection via PolSAR images. P2P-CNN focuses on both the target and its surroundings. A patch of proper size that contains both a target and its surroundings is used as the input of the neural network to determine whether the pixel in the center of the patch belongs to the target. To utilize contextual semantic information at all scales, all feature maps from the top down are combined to improve the final result. Instead of conventional convolution, dilated convolutions are used in the proposed neural network to exponentially expand receptive fields without adding any model parameters. The proposed approach and comparative methods are tested and compared on PolSAR images in various environments under varying image resolution, target size, sea condition, sensor type, etc. The experimental results demonstrate that the proposed approach outperforms all the compared methods.

In this letter, we propose a novel ship detection method in high-resolution synthetic aperture radar (SAR) images. In the proposed method, the superpixel is utilized as the basic processing cell. We propose a superpixel-level Fisher vector to characterize the difference between the target and clutter superpixel due to the strong discriminating ability of the Fisher vector. Besides feature extraction, the threshold determination is another key step in the detection scheme. We determine the threshold in a semisupervised way, which combines the advantages of both supervised and unsupervised methods. Based on the threshold, the target superpixels are discriminated and we obtain the final detection result. Compared with existing methods, the proposed method shows robust performance under low signal-to-clutter ratio (SCR) conditions. Experiments performed on both synthetic data and a TerraSAR-X image demonstrate the effectiveness of the proposed method.

The hyperbolic frequency-modulated (HFM) waveform has an inherent Doppler-invariant property. It is more conducive than the conventional linear frequency-modulated (LFM) waveform to high speed moving target imaging. In order to apply the HFM waveform to existing inverse synthetic aperture radar (ISAR) imaging systems, a new pulse compression algorithm is proposed. First, the received HFM echoes are demodulated with the transmitted signal, which is called “decurve” in this paper. By this operation, the bandwidth of the demodulated echoes is effectively reduced and can be processed by the existing narrow-band receiver. Then, the phase of the decurved HFM echoes is analyzed, and thus, the pulse compression is accomplished by space-variant phase compensation. In addition, the space-variant phase compensation is realized by resampling and fast Fourier transform (FFT) with high computational efficiency. Finally, numerical results illustrate the effectiveness of the proposed method.

In a frequency modulation continuous wave and inverse synthetic aperture radar (FMCW–ISAR) system, imaging a target beyond the maximum unambiguous range causes the ambiguity in the range domain. This ambiguity phenomenon greatly reduces resolution and degrades image quality, and limits the application of long‐distance imaging of an FMCW–ISAR system. In this study, ambiguity correction method, based on mutual‐coherence processing, is proposed for long‐distance imaging in an FMCW–ISAR system. In the process, the singularity point of the beat signal caused by the ambiguity phenomenon is determined by the wavelet transform modulus maxima method. All‐pole models are used to fit the beat signal subbands of different Doppler frequencies, and then adjust the models until they optimally match. The simulation results validate the effectiveness of the proposed correction method. This study shows the promising prospect of long‐distance imaging using an FMCW–ISAR system.