Speckle noise is an inherent but annoying property in the synthetic aperture radar (SAR) imaging. In this paper we investigate the influence of speckle on the classical convolutional neural network (CNN) for SAR target classification. Then a dual stage coupled CNN architecture, named despeckling and classification coupled CNNs (DCC-CNNs), is proposed to distinguish multiple categories of ground targets in SAR images with strong and varying speckle. It first applies the despeckling sub-network for noise reduction. After that, residual speckle features as well as target information would be learned by the classification sub-network in order to solve the noise robustness problem of CNN. Besides, a new quantitative measure is developed for the quality assessment of SAR target images. It takes into account structural properties of the speckled SAR image of the target of interest and consistency with visual perception. Finally, a series of comparative experiments and discussions are carried out to validate the proposed assessment criterion and DCC-CNNs. Using synthetic SAR images based on the public MSTAR datasets, results show that the overall classification accuracy for ten ground target classes could be higher than 82% at a variety of speckle noise levels.

A priori knowledge of target detection probability is of critical importance in the Gaussian mixture probability hypothesis density (PHD) and cardinalized PHD (CPHD) filters. In addition, these two filters require that the process noise and measurement noise of the state propagated in the recursion be Gaussian. These limitations may restrict the two filters' application in real problems. To accommodate unknown target detection probability and nonnegative non-Gaussian parameters, this paper proposes a new implementation based on inverse gamma Gaussian mixtures, introducing a location independent feature whose posterior probability density and likelihood function are nonnegative non-Gaussian inverse gamma and gamma functions to determine detection probability incorporated into the recursions. The derivation of the merging inverse gamma components is also presented to prevent the unbounded increase of mixture components by minimizing the Kullback-Leibler divergence. First, a real heavy-clutter scenario is used to validate the effectiveness of the proposed filters in track initiation and target tracking without known detection probability. Then, simulations are presented to demonstrate that the proposed CPHD and PHD filters can achieve multitarget tracking performance similar to the standard counterparts with known target detection probability, and that they outperform the standard counterparts in scenarios with unknown and dynamically changing detection probability. The robustness of the proposed filters is tested in both real and simulation scenarios. It is also shown that the analytical and empirical computational complexities of the proposed filters are similar to those of their standard counterparts. Response: They have been cited, and we have discussed them in the introduction in page 1 line 65-78.

Salient object ranking (SOR) aims to segment salient objects in an image and simultaneously predict their saliency rankings, according to the shifted human attention over different objects. The existing SOR approaches mainly focus on object-based attention, e.g., the semantic and appearance of object. However, we find that the scene context plays a vital role in SOR, in which the saliency ranking of the same object varies a lot at different scenes. In this paper, we thus make the first attempt towards explicitly learning scene context for SOR. Specifically, we establish a large-scale SOR dataset of 24,373 images with rich context annotations, i.e., scene graphs, segmentation, and saliency rankings. Inspired by the data analysis on our dataset, we propose a novel graph hypernetwork, named HyperSOR, for context-aware SOR. In HyperSOR, an initial graph module is developed to segment objects and construct an initial graph by considering both geometry and semantic information. Then, a scene graph generation module with multi-path graph attention mechanism is designed to learn semantic relationships among objects based on the initial graph. Finally, a saliency ranking prediction module dynamically adopts the learned scene context through a novel graph hypernetwork, for inferring the saliency rankings. Experimental results show that our HyperSOR can significantly improve the performance of SOR.

Deep learning techniques have attracted much attention in the radar automatic target recognition. In the paper we investigate an acceleration method of convolutional neural network (CNN) on the field-programmable gate array (FPGA) for the embedded application of the millimeter-wave (mmW) radar based human activity classification. Considering the micro-Doppler effect caused by person’s body movements, the spectrogram of mmW radar echoes is adopted as the CNN input. After that, according to the CNN architecture and the properties of FPGA implementation, several parallel processing strategies are designed as well as data quantization and optimization of classification decision to accelerate the CNN execution. Finally, comparative experiments and discussions are carried out based on a measured dataset of 9 individuals with 4 different actions by using a 77 GHz mmW radar. Results show that the proposed method not only maintains the high classification accuracy, but also improve its execution speed, memory requirement and power consumption. Specifically, compared with the implementation of the same network model on a graphics processing unit, it could achieve the speedup of about 30.42% at the cost of the classification accuracy loss of only 0.27%.

The ghost phenomenon in synthetic aperture radar (SAR) imaging is primarily caused by azimuth or range ambiguities, which cause difficulties in SAR target detection application. To mitigate this influence, we propose a ship target detection method in spaceborne SAR imagery, using a hierarchical convolutional neural network (H-CNN). Based on the nature of ghost replicas and typical target classes, a two-stage CNN model is built to detect ship targets against sea clutter and the ghost. First, regions of interest (ROIs) were extracted from a large imaged scene during the coarse-detection stage. Unwanted ghost replicas represented major residual interference sources in ROIs, therefore, the other CNN process was executed during the fine-detection stage. Finally, comparative experiments and analyses, using Sentinel-1 SAR data and various assessment criteria, were conducted to validate H-CNN. Our results showed that the proposed method can outperform the conventional constant false-alarm rate technique and CNN-based models.