Depthwise Separable Convolution Neural Network for High-Speed SAR Ship Detection

Abstract

As an active microwave imaging sensor for the high-resolution earth observation, synthetic aperture radar (SAR) has been extensively applied in military, agriculture, geology, ecology, oceanography, etc., due to its prominent advantages of all-weather and all-time working capacity. Especially, in the marine field, SAR can provide numerous high-quality services for fishery management, traffic control, sea-ice monitoring, marine environmental protection, etc. Among them, ship detection in SAR images has attracted more and more attention on account of the urgent requirements of maritime rescue and military strategy formulation. Nowadays, most researches are focusing on improving the ship detection accuracy, while the detection speed is frequently neglected, regardless of traditional feature extraction methods or modern deep learning (DL) methods. However, the high-speed SAR ship detection is of great practical value, because it can provide real-time maritime disaster rescue and emergency military planning. Therefore, in order to address this problem, we proposed a novel high-speed SAR ship detection approach by mainly using depthwise separable convolution neural network (DS-CNN). In this approach, we integrated multi-scale detection mechanism, concatenation mechanism and anchor box mechanism to establish a brand-new light-weight network architecture for the high-speed SAR ship detection. We used DS-CNN, which consists of a depthwise convolution (D-Conv2D) and a pointwise convolution (P-Conv2D), to substitute for the conventional convolution neural network (C-CNN). In this way, the number of network parameters gets obviously decreased, and the ship detection speed gets dramatically improved. We experimented on an open SAR ship detection dataset (SSDD) to validate the correctness and feasibility of the proposed method. To verify the strong migration capacity of our method, we also carried out actual ship detection on a wide-region large-size Sentinel-1 SAR image. Ultimately, under the same hardware platform with NVIDIA RTX2080Ti GPU, the experimental results indicated that the ship detection speed of our proposed method is faster than other methods, meanwhile the detection accuracy is only lightly sacrificed compared with the state-of-art object detectors. Our method has great application value in real-time maritime disaster rescue and emergency military planning.

An Efficient Algorithm for Cardiac Arrhythmia Classification Using Ensemble of Depthwise Separable Convolutional Neural Networks

“…In addition to the implementation of BN, the convolution part can also be further optimized, for example by using depthwise separable convolution (DSC) to reduce the computational costs by reducing the number of arithmetic operations while preserving the same final results [32,34,35]. This technique is applied with changes in filter sizes 3, 1, and 3, respectively.…”

Anchor-free Convolutional Network with Dense Attention Feature Aggregation for Ship Detection in SAR Images

“…, where σ a is the standard deviation that adaptively changes according to the target size [31]. When two Gaussian centers overlap, we take the larger value on every overlapped position.…”

“…Chen et al [30] embedded an attention module into the feature extraction process of DCNN to conduct ship detection in complex scenes of SAR images. Zhang et al [31] proposed a DCNN based on depth-wise separable convolution to realize high-speed SAR ship detection. Chang et al [32] presented an improved YOLOv3 to conduct real-time SAR ship detection.…”

LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images

“…Synthetic aperture radar (SAR) is an active microwave imaging sensor whose all-day and all-weather working capacity give it an important place in marine exploration [1][2][3][4][5][6][7]. Since the United States launched the first SAR satellite, SAR has received much attention in marine remote sensing, e.g., geological exploration, topographic mapping, disaster forecast, traffic monitoring, etc.…”

“…So far, many traditional SAR ship detection methods have been proposed, e.g., global thresholdbased [36][37][38], constant false alarm ratio (CFAR)-based [39][40][41], generalized likelihood ratio test (GLRT)-based [42][43][44], transformation domain-based [45][46][47], visual saliency-based [48][49][50], super-pixel segmentation-based [51][52][53], and auxiliary feature-based (e.g., ship-wake) [54][55][56], all of which obtained modest results in specific backgrounds, but these methods always extract ship features by hand-designed means, leading to complexity in computation, weakness in generalization, and trouble in manual feature extraction [1,4]. Moreover, as ship wakes do not exist all the time, and their features are not as obvious as ship targets, the research on the detection of ship wakes is not extensive [13].…”