A Fast and Lightweight Detection Network for Multi-Scale SAR Ship Detection under Complex Backgrounds

It is very difficult to detect multi-scale synthetic aperture radar (SAR) ships, especially under complex backgrounds. Traditional constant false alarm rate methods are cumbersome in manual design and weak in migration capabilities. Based on deep learning, researchers have introduced methods that have shown good performance in order to get better detection results. However, the majority of these methods have a huge network structure and many parameters which greatly restrict the application and promotion. In this paper, a fast and lightweight detection network, namely FASC-Net, is proposed for multi-scale SAR ship detection under complex backgrounds. The proposed FASC-Net is mainly composed of ASIR-Block, Focus-Block, SPP-Block, and CAPE-Block. Specifically, without losing information, Focus-Block is placed at the forefront of FASC-Net for the first down-sampling of input SAR images at first. Then, ASIR-Block continues to down-sample the feature maps and use a small number of parameters for feature extraction. After that, the receptive field of the feature maps is increased by SPP-Block, and then CAPE-Block is used to perform feature fusion and predict targets of different scales on different feature maps. Based on this, a novel loss function is designed in the present paper in order to train the FASC-Net. The detection performance and generalization ability of FASC-Net have been demonstrated by a series of comparative experiments on the SSDD dataset, SAR-Ship-Dataset, and HRSID dataset, from which it is obvious that FASC-Net has outstanding detection performance on the three datasets and is superior to the existing excellent ship detection methods.

Incoherent Integration Detection Method of Airborne Phased Array Radar in a Multipath Environment

Airborne phased array radar (PAR) suffers from multipath problems when flying over a calm sea surface. The existence of a multipath phenomenon will cause the electromagnetic echo of the same target to be reflected back to the airborne PAR from two paths, namely, direct path (DP) and multipath. Compared with the ground-based radar, the target echo received by airborne PAR in the multipath environment has two important characteristics: one is that the DP signal and the multipath signal exist in different range bins, and the other is that the radar cross section (RCS) in the DP direction may be smaller than that in the multipath direction. Considering these two characteristics, this paper first proposes a target pairing algorithm for matching the DP range and multipath range of the same target in signal detection, and then, combined with the cell-averaging constant false alarm rate (CA-CFAR) detection model, an incoherent integration detection method for airborne PAR in the multipath environment is proposed. In the target pairing process, the geometric structure relationship of the airborne PAR model can be fully utilized. After a successful target pairing process, the energy of the multipath signal will be incoherently accumulated into the corresponding DP range bin, so as to improve the probability of DP range bin data passing the detection threshold. In essence, the proposed method makes full use of multipath energy to improve the detection capability of airborne PAR in the multipath environment. Finally, the detection probability of the proposed method is given, and the detection performance is analyzed.

Fishing boat detection using Sentinel-1 validated with VIIRS Data

Detecting fishing boat activity is still a challenge for the biggest archipelago countries, such as Indonesia, to monitor the huge marine area. Space technology using sensors SAR to detect ships has been developed since 1985. However, the cost of using SAR images is one of the barriers to operational aspects, mainly for detecting fishing boats to deter IUU fishing activities. This research aims to evaluate the use of Sentinel 1-SAR imagery for identifying fishing boats from space. We used VIIRS data for validating the purposes. Both data sources could be accessed freely. The object detection process can be derived into three steps: pre-processing, object detection and object validation. We used the constant false alarm rate (CFAR) method to discriminate against objects at sea. To identify fishing vessels, we used the size of the vessels and the intensity of light captured by VIIRS. According to the findings, 21 boats were discovered using sentinel 1-SAR imagery and four boats using VIIRS data based on the the area of interest.

Accurate detection method of moving target based on sequential SAR images with multiple azimuth squint angles

In this paper, a novel moving target detection method for sequential Synthetic Aperture Radar (SAR) images with different azimuth-squint angles is proposed. In sequential SAR images, due to the movement of the target, the imaging position of moving targets among different frames differs. The method proposed in this paper uses this kind of motion characteristics to achieve the detection of moving targets in multi-frame SAR images. This algorithm can be divided into two parts: block-level detection and pixel-level detection. Block-level detection is achieved by stacked denoising autoencoders to extract the high-dimensional features of the moving target. Pixel-level detection consists of Local Binary Similarity Patterns (LBSP) coding as well as grayscale background subtraction. Pixel-level detection only needs to consider the pixels of foreground image pieces which contain moving targets. This method can not only increase the detection speed, but also suppress the false alarm problem caused by clutter. Experiments are carried out for verifying the validation of the method and the comparison are made between the proposed method and the traditional Constant False Alarm Rate (CFAR) algorithm.

Target Detection in High-Resolution SAR Image via Iterating Outliers and Recursing Saliency Depth

In dealing with the problem of target detection in high-resolution Synthetic Aperture Radar (SAR) images, segmenting before detecting is the most commonly used approach. After the image is segmented by the superpixel method, the segmented area is usually a mixture of target and background, but the existing regional feature model does not take this into account, and cannot accurately reflect the features of the SAR image. Therefore, we propose a target detection method based on iterative outliers and recursive saliency depth. At first, we use the conditional entropy to model the features of the superpixel region, which is more in line with the actual SAR image features. Then, through iterative anomaly detection, we achieve effective background selection and detection threshold design. After that, recursing saliency depth is used to enhance the effective outliers and suppress the background false alarm to realize the correction of superpixel saliency value. Finally, the local graph model is used to optimize the detection results. Compared with Constant False Alarm Rate (CFAR) and Weighted Information Entropy (WIE) methods, the results show that our method has better performance and is more in line with the actual situation.

A neural network framework for binary classification of radar detections

A desired objective in radar target detection is to satisfy two very contradictory requirements: offer a high probability of detection with a low false alarm rate. In this paper, we propose the utilization of artificial neural networks for binary classification of targets detected by a depreciated detection process. It is shown that trained neural networks are capable of identifying false detections with considerable accuracy and can to this extent utilize information present in guard cells and Doppler profiles. This allows for a reduction in the false alarm rate with only moderate loss in the probability of detection. With an appropriately designed neural network, an overall improved system performance can be achieved when compared against traditional constant false alarm rate detectors for the specific trained scenarios.

Multi-Dimensional Automatic Detection of Scanning Radar Images of Marine Targets Based on Radar PPInet

Traditional radar target detection algorithms are mostly based on statistical theory. They have weak generalization capabilities for complex sea clutter environments and diverse target characteristics, and their detection performance would be significantly reduced. In this paper, the range-azimuth-frame information obtained by scanning radar is converted into plain position indicator (PPI) images, and a novel Radar-PPInet is proposed and used for marine target detection. The model includes CSPDarknet53, SPP, PANet, power non-maximum suppression (P-NMS), and multi-frame fusion section. The prediction frame coordinates, target category, and corresponding confidence are directly given through the feature extraction network. The network structure strengthens the receptive field and attention distribution structure, and further improves the efficiency of network training. P-NMS can effectively improve the problem of missed detection of multi-targets. Moreover, the false alarms caused by strong sea clutter are reduced by the multi-frame fusion, which is also a benefit for weak target detection. The verification using the X-band navigation radar PPI image dataset shows that compared with the traditional cell-average constant false alarm rate detector (CA-CFAR) and the two-stage Faster R-CNN algorithm, the proposed method significantly improved the detection probability by 15% and 10% under certain false alarm probability conditions, which is more suitable for various environment and target characteristics. Moreover, the computational burden is discussed showing that the Radar-PPInet detection model is significantly lower than the Faster R-CNN in terms of parameters and calculations.

Analysis of Temporal and Spatial Variability of Fronts on the Amery Ice Shelf Automatically Detected Using Sentinel-1 SAR Data

The Amery Ice Shelf (AIS) dynamics and mass balance caused by iceberg calving and basal melting are significant in the ocean climate system. Using satellite imagery from Sentinel-1 SAR, we monitored the temporal and spatial variability of the frontal positions on the Amery Ice Shelf, Antarctica, from 2015 to 2021. In this paper, we propose an automatic algorithm based on the SO-CFAR strategy and a profile cumulative method for frontal line extraction. To improve the accuracy of the extracted frontal lines, we developed a framework combining the Constant False Alarm Rate (CFAR) and morphological image-processing strategies. A visual comparison between the proposed algorithm and state-of-the-art algorithm shows that our algorithm is effective in these cases including rifts, icebergs, and crevasses as well as ice-shelf surface structures. We present a detailed analysis of the temporal and spatial variability of fronts on AIS that we find, an advance of the AIS frontal line before the D28 calving event, and a continuous advance after the event. The study reveals that the AIS extent has been advanced at the rate of 1015 m/year. Studies have shown that the frontal location of AIS has continuously expanded. From March 2015 to May 2021, the frontal location of AIS expanded by 6.5 km; while the length of the AIS frontal line is relatively different after the D28 event, the length of the frontal line increased by about 7.5% during 2015 and 2021 (255.03 km increased to 273.5 km). We found a substantial increase in summer advance rates and a decrease in winter advance rates with the seasonal characteristics. We found this variability of the AIS frontal line to be in good agreement with the ice flow velocity.

DSDet: A Lightweight Densely Connected Sparsely Activated Detector for Ship Target Detection in High-Resolution SAR Images

Traditional constant false alarm rate (CFAR) based ship target detection methods do not work well in complex conditions, such as multi-scale situations or inshore ship detection. With the development of deep learning techniques, methods based on convolutional neural networks (CNN) have been applied to solve such issues and have demonstrated good performance. However, compared with optical datasets, the number of samples in SAR datasets is much smaller, thus limiting the detection performance. Moreover, most state-of-the-art CNN-based ship target detectors that focus on the detection performance ignore the computation complexity. To solve these issues, this paper proposes a lightweight densely connected sparsely activated detector (DSDet) for ship target detection. First, a style embedded ship sample data augmentation network (SEA) is constructed to augment the dataset. Then, a lightweight backbone utilizing a densely connected sparsely activated network (DSNet) is constructed, which achieves a balance between the performance and the computation complexity. Furthermore, based on the proposed backbone, a low-cost one-stage anchor-free detector is presented. Extensive experiments demonstrate that the proposed data augmentation approach can create hard SAR samples artificially. Moreover, utilizing the proposed data augmentation approach is shown to effectively improves the detection accuracy. Furthermore, the conducted experiments show that the proposed detector outperforms the state-of-the-art methods with the least parameters (0.7 M) and lowest computation complexity (3.7 GFLOPs).