A Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios

Chen, Chen; He, Chu; Hu, Changhua; Pei, Hong; Jiao, Licheng

doi:10.1109/access.2019.2930939

Cited by 86 publications

(53 citation statements)

References 37 publications

(65 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…SAR images in this dataset possess different satellite sensors, various polarization modes, multiple resolutions, different scenes, and abundant ship sizes, so it can verify the robustness of methods. Therefore, many scholars [10,21,35,[55][56][57][58][59][60][61][62][63] conducted research based on it for a better comparison.…”

Section: Datasetmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

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.

show abstract

Section: Datasetmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Through DHA, we obtain the high-resolution feature map F out enhanced with multiscale information. In addition, recent studies show that the attention mechanism is helpful for improving the performance of SAR ship detection [28][29][30]. Inspired by the idea, we embed an attention block, i.e., SCSE block into the upsampling process.…”

Section: Ideas Of Dense Attention Feature Aggregationmentioning

confidence: 99%

“…Gao et al [29] combined spatial attention blocks and split convolution blocks in RetinaNet for multiscale ship detection in SAR images. 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.…”

Section: Introductionmentioning

confidence: 99%

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

Gao

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

In recent years, with the improvement of synthetic aperture radar (SAR) imaging resolution, it is urgent to develop methods with higher accuracy and faster speed for ship detection in high-resolution SAR images. Among all kinds of methods, deep-learning-based algorithms bring promising performance due to end-to-end detection and automated feature extraction. However, several challenges still exist: (1) standard deep learning detectors based on anchors have certain unsolved problems, such as tuning of anchor-related parameters, scale-variation and high computational costs. (2) SAR data is huge but the labeled data is relatively small, which may lead to overfitting in training. (3) To improve detection speed, deep learning detectors generally detect targets based on low-resolution features, which may cause missed detections for small targets. In order to address the above problems, an anchor-free convolutional network with dense attention feature aggregation is proposed in this paper. Firstly, we use a lightweight feature extractor to extract multiscale ship features. The inverted residual blocks with depth-wise separable convolution reduce the network parameters and improve the detection speed. Secondly, a novel feature aggregation scheme called dense attention feature aggregation (DAFA) is proposed to obtain a high-resolution feature map with multiscale information. By combining the multiscale features through dense connections and iterative fusions, DAFA improves the generalization performance of the network. In addition, an attention block, namely spatial and channel squeeze and excitation (SCSE) block is embedded in the upsampling process of DAFA to enhance the salient features of the target and suppress the background clutters. Third, an anchor-free detector, which is a center-point-based ship predictor (CSP), is adopted in this paper. CSP regresses the ship centers and ship sizes simultaneously on the high-resolution feature map to implement anchor-free and nonmaximum suppression (NMS)-free ship detection. The experiments on the AirSARShip-1.0 dataset demonstrate the effectiveness of our method. The results show that the proposed method outperforms several mainstream detection algorithms in both accuracy and speed.

show abstract

“…The proposed method has good positioning effects for small targets and ships with dense arrangements [26]. Chen et al proposed an SAR ship detection network that integrates an attention mechanism, and this approach achieved satisfactory accuracy and speed performance [27]. However, there are still some obstacles in SAR ship detection.…”

Section: Introductionmentioning

confidence: 99%

“…Unlike previous detection models, the newly proposed model combines the precise positioning advantages of rotation detection with the speed advantage of a single-stage framework. Compared with the models in reference [11], [15], [16], and [27], the proposed model improves the detection performance in different complex scenes, can effectively distinguish among densely arranged targets, and reduces redundant detection areas. 2) A multiscale adaptive recalibration module is proposed to calibrate the features extracted by the CNN through global information to improve the sensitivity of the network to changes in angles.…”

Section: Introductionmentioning

confidence: 99%

MSARN: A Deep Neural Network Based on an Adaptive Recalibration Mechanism for Multiscale and Arbitrary-Oriented SAR Ship Detection

Chen

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Ship detection plays an important role in synthetic aperture radar (SAR) image interpretation. However, there are still some difficulties in SAR ship detection. First, ships often have a large aspect ratio and arbitrary directionality in SAR images. Traditional detection algorithms can cause the detection area to be redundant, which makes it difficult to accurately locate the target in complex scenes. Second, ships in ports are often densely arranged, and the effective identification of densely arranged ships is complicated. Finally, ships in SAR images exist at a variety of scales due to the multiresolution imaging modes used and ship shape variations, which pose a considerable challenge for ship detection. To solve the above problems, we propose a multiscale adaptive recalibration network (MSARN) to detect multiscale and arbitrarily oriented ships in complex scenarios. The recalibration of the extracted multiscale features through global information increases the sensitivity of the network to the target angle, thereby increasing the accuracy of positioning. In particular, we designed a pyramid anchor and a loss function to match the rotated target. In addition, we modified the rotation non-maximum suppression (RNMS) method to solve the problem of the large overlap ratio of the detection box. The proposed model combines the positioning advantage of rotation detection with the speed advantage of a single-stage framework. Experiments show that based on the SAR rotation ship detection (SRSD) data set, the proposed algorithm has a faster detection speed and higher accuracy than some state-of-the-art methods. INDEX TERMS Ship detection, synthetic aperture radar (SAR), adaptive recalibration, neural network.

show abstract

A Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios

Cited by 86 publications

References 37 publications

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

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

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

MSARN: A Deep Neural Network Based on an Adaptive Recalibration Mechanism for Multiscale and Arbitrary-Oriented SAR Ship Detection

Contact Info

Product

Resources

About