No abstract

In this paper, we propose a data augmentation method for ship detection. Inshore ship detection using optical remote sensing imaging is a challenging task owing to an insufficient number of training samples. Although the multilayered neural network method has achieved excellent results in recent research, a large number of training samples is indispensable to guarantee the accuracy and robustness of ship detection. The majority of researchers adopt such strategies as clipping, scaling, color transformation, and flipping to enhance the samples. Nevertheless, these methods do not essentially increase the quality of the dataset. A novel data augmentation strategy was thus proposed in this study by using simulated remote sensing ship images to augment the positive training samples. The simulated images are generated by true background images and three-dimensional models on the same scale as real ships. A faster region-based convolutional neural network (Faster R-CNN) based on Res101netwok was trained by the dataset, which is composed of both simulated and true images. A series of experiments is designed under small sample conditions; the experimental results show that better detection is obtained with our data augmentation strategy.

Ship detection based on synthetic aperture radar (SAR) images has made a breakthrough in recent years. However, small ships, which may be regarded as speckle noise, pose enormous challenges to the accurate detection of SAR images. In order to enhance the detection performance of small ships in SAR images, a novel detection method named a spatial information integration network (SII-Net) is proposed in this paper. First, a channel-location attention mechanism (CLAM) module which extracts position information along with two spatial directions is proposed to enhance the detection ability of the backbone network. Second, a high-level features enhancement module (HLEM) is customized to reduce the loss of small target location information in high-level features via using multiple pooling layers. Third, in the feature fusion stage, a refined branch is presented to distinguish the location information between the target and the surrounding region by highlighting the feature representation of the target. The public datasets LS-SSDD-v1.0, SSDD and SAR-Ship-Dataset are used to conduct ship detection tests. Extensive experiments show that the SII-Net outperforms state-of-the-art small target detectors and achieves the highest detection accuracy, especially when the target size is less than 30 pixels by 30 pixels.

Anomaly target detection methods for hyperspectral images (HSI) often have the problems of potential anomalies and noise contamination when representing background. Therefore, a spectral-spatial hyperspectral anomaly detection method is proposed in this article, which is based on fractional Fourier transform (FrFT) and saliency weighted collaborative representation. First, hyperspectral pixels are projected to the fractional Fourier domain by the FrFT, which can enhance the capability of the detector to suppress the noise and make anomalies to be more distinctive. Then, a saliency weighted matrix is designed as the regularization matrix referring to context-aware saliency theory and combined with the FrFT-based collaborative representation detector. The saliencyweighted regularization matrix assigns different pixels with different weights by using both spectral and spatial information, which can reduce the influence of the potential anomalous pixels embedded in the background when applying collaborative representation theory. Finally, to further improve the performance of the proposed method, a spectral-spatial detection procedure is employed to calculate final anomaly scores by using both spectral information and spatial information. The proposed method is compared with nine state-of-the-art hyperspectral anomaly detection methods on six HSI datasets, including two synthetic HSI datasets and four real-world HSI datasets. Extensive experimental results illustrate that the proposed method's detection performance outperforms other nine well-known compared methods in terms of area under the receiver operating characteristic (ROC) curve values, visual detection characteristics, ROC curve, and separability.