Search

Image-based ship monitoring technology has extensive applications, and is widely used in various aspects of port management, including illegal activity surveillance, vessel identification at entry and exit points, channel and berth management, unmanned vessel control, and incident warning and emergency response. However, most current ship identification technologies rely on a single information source, reducing detection accuracy in the complex and variable marine environment. To address this issue, this paper proposes a knowledge transfer-based ship identification system integrating three modules. The system enables synchronized monitoring of visible light coastal images, satellite cloud images, and infrared spectrum images, thereby mitigating problems such as low detection accuracy and poor adaptability of image recognition. Additionally, extensive supplementary experiments were conducted to evaluate the effectiveness of the preprocessing and data augmentation modules as well as the transfer learning module. The study also discusses the limitations of current deep learning-based ship monitoring models, particularly their poor adaptability to image recognition and inability to achieve all-weather, round-the-clock monitoring. Experimental results based on three ship monitoring datasets demonstrate that the proposed system, by integrating three distinct detection conditions, outperforms other models with an F1-score of 98.74%, approximately 10% higher than most existing ship detection systems. [ABSTRACT FROM AUTHOR]

Corner reflector, as a passive jammer, can generate a large radar cross section (RCS) to interfere with radar for target recognition. However, the impact of corner reflectors on passive millimetre-wave (PMMW) recognition is unclear. In this paper, based on ray tracing, the brightness temperature (TB) of corner reflectors is calculated. Ray tracing paths are used to analyze the impact of the sky, sea surface, and sun on the TB of corner reflectors. The antenna temperature of corner reflectors and their array at different distances is simulated and compared with that of a metal ship to evaluate their jamming performance. Four series of experiments measuring the antenna temperature of corner reflectors and the ship are conducted to verify the jamming performance. The results indicate that the contrast of corner reflectors is much smaller than that of ship target, causing little jamming for PMMW recognition. [ABSTRACT FROM AUTHOR]

The identification of ships in Synthetic Aperture Radar (SAR) imagery is critical for effective maritime surveillance. The advent of deep learning has significantly improved the accuracy of SAR ship classification and recognition. However, distinguishing features between different ship categories in SAR images remains a challenge, particularly as the number of categories increases. The key to achieving high recognition accuracy lies in effectively extracting and utilizing discriminative features. To address this, we propose DCN-MSFF-TR, a novel recognition model inspired by the Transformer encoder–decoder architecture. Our approach integrates a deformable convolutional module (DCN) within the backbone network to enhance feature extraction. Additionally, we introduce multi-scale self-attention processing from the Transformer into the feature hierarchy and fuse these representations at appropriate levels using a feature pyramid strategy. This enables each layer to leverage both its own information and synthesized features from other layers, enhancing feature representation. Extensive evaluations on the OpenSARShip-3-Complex and OpenSARShip-6-Complex datasets demonstrate the effectiveness of our method. DCN-MSFF-TR achieves average recognition accuracies of 78.1% and 66.7% on the three-class and six-class datasets, respectively, outperforming existing recognition models and showcasing its superior capability in accurately identifying ship categories in SAR images. [ABSTRACT FROM AUTHOR]

Real-time ship detection using SAR images is crucial for maritime operations but remains challenging due to issues such as sidelobes, complex background interferences, and target defocusing. Studies have shown that deep learning can address these problems, current deep learning algorithms often suffer from achieving the necessary accuracy due to complex noise and background characteristics. Additionally, advanced algorithms excelling in feature extraction usually require significant computational resources. This paper proposes a novel deep learning approach based on YOLOv8 to improve accuracy while reducing model complexity and computational burden. The approach innovatively integrates a knowledge distillation module into the YOLOv8. We further enhance the model by replacing the original YOLOv8 backbone, neck, and head with lightweight alternatives: HGNetv2, SlimNeck, and a newly designed decoupled head. The enhanced model, YOLOSAR-Lite, demonstrated exceptional performance on both accuracy and model complexity metrics. Rigorous evaluation on the Official-SSDD dataset and the SAR-Ship-Dataset revealed recognition accuracies of 95.32% and 96.06%, respectively. Furthermore, YOLOSAR-Lite achieved significant reduction in complexity compared to the YOLOv8: 4.48G FLOPs (45.30% reduction), 2.05M parameters (31.89% reduction), and 3.91MB model size (31.76% reduction). These improvements demonstrate YOLOSAR-Lite achieves higher accuracy with minimal complexity. Consequently, YOLOSAR-Lite is a promising solution for real-time ship detection.

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security. Currently, with the emergence of massive high-resolution multimodality images, the use of multi-modality images for fine-grained recognition has become a promising technology. Fine-grained recognition of multi-modality images imposes higher requirements on the dataset samples. The key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion features. The attention mechanism helps the model to pinpoint the key information in the image, resulting in a significant improvement in the model's performance. In this paper, a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first, named Dataset for Multimodal Fine-grained Recognition of Ships (DMFGRS). It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories, collated from digital orthophotos model provided by commercial remote sensing satellites. DMFGRS provides two types of annotation format files, as well as segmentation mask images corresponding to the ship targets. Then, a Multimodal Information Cross- Enhancement Network (MICE-Net) fusing features of visible and near-infrared remote sensing images, has been proposed. In the network, a dual-branch feature extraction and fusion module has been designed to obtain more expressive features. The Feature Cross Enhancement Module (FCEM) achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map. A benchmark is established by evaluating state-of-the-art object recognition algorithms on DMFGRS. MICE-Net conducted experiments on DMFGRS, and the precision, recall, mAP0.5 and mAP0.5:0.95 reached 87%, 77.1%, 83.8% and 63.9%, respectively. Extensive experiments demonstrate that the proposed MICE-Net has more excellent performance on DMFGRS. Built on lightweight network YOLO, the model has excellent generalizability, and thus has good potential for application in real-life scenarios. [ABSTRACT FROM AUTHOR]

Image-based ship monitoring technology has extensive applications, and is widely used in various aspects of port management, including illegal activity surveillance, vessel identification at entry and exit points, channel and berth management, unmanned vessel control, and incident warning and emergency response. However, most current ship identification technologies rely on a single information source, reducing detection accuracy in the complex and variable marine environment. To address this issue, this paper proposes a knowledge transfer-based ship identification system integrating three modules. The system enables synchronized monitoring of visible light coastal images, satellite cloud images, and infrared spectrum images, thereby mitigating problems such as low detection accuracy and poor adaptability of image recognition. Additionally, extensive supplementary experiments were conducted to evaluate the effectiveness of the preprocessing and data augmentation modules as well as the transfer learning module. The study also discusses the limitations of current deep learning-based ship monitoring models, particularly their poor adaptability to image recognition and inability to achieve all-weather, round-the-clock monitoring. Experimental results based on three ship monitoring datasets demonstrate that the proposed system, by integrating three distinct detection conditions, outperforms other models with an F1-score of 98.74%, approximately 10% higher than most existing ship detection systems.

This paper investigates remote sensing data recognition and classification with multimodal data fusion. Aiming at the problems of low recognition and classification accuracy and the difficulty in integrating multimodal features in existing methods, a multimodal remote sensing data recognition and classification model based on a heatmap and Hirschfeld–Gebelein–Rényi (HGR) correlation pooling fusion operation is proposed. A novel HGR correlation pooling fusion algorithm is developed by combining a feature fusion method and an HGR maximum correlation algorithm. This method enables the restoration of the original signal without changing the value of transmitted information by performing reverse operations on the sample data. This enhances feature learning for images and improves performance in specific tasks of interpretation by efficiently using multi-modal information with varying degrees of relevance. Ship recognition experiments conducted on the QXS-SROPT dataset demonstrate that the proposed method surpasses existing remote sensing data recognition methods. Furthermore, land cover classification experiments conducted on the Houston 2013 and MUUFL datasets confirm the generalizability of the proposed method. The experimental results fully validate the effectiveness and significant superiority of the proposed method in the recognition and classification of multimodal remote sensing data. [ABSTRACT FROM AUTHOR]

Due to the more parameters and higher energy-consumption in the traditional methods for the synthetic aperture radar (SAR) image target recognition, this paper proposes a lightweight ship recognition algorithm based on the spiking neural network (SNN) in SAR images. Firsty, the visual attention mechanism is adopted to extract the visual saliency map from SAR images, and the Poisson encoder is adopted for the spike train encode, which can suppress the background noise interference. Then, combined with the leaky integrate-and-fire (LIF) spiking neuron and convolutional neural network, the SNN model integrating the time series information is constructed, which can realize the ship recognition in SAR images. Finally, the SNN model is optimized by using the arctangent function as the surrogate gradient function of the spiking emission function during the backpropagation, which can solve the problem that the SNN model is difficult to train. The experiment results show that the proposed algorithm has higher accuracy, fewer parameters, higher efficiency, and lower energy-consumption, which can achieve efficient and accurate ship recognition in SAR images. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Deep learning has offered new ideas in SAR ship target recognition. Although many methods improve the recognition performance through the improvement of loss function and migration of deep networks, scattering features as the important intrinsic features of SAR targets, need to be considered in the SAR ship recognition tasks. To introduce the scattering features into the deep network and characterize the features of ship targets more comprehensively, a multiscale global scattering feature association network (MGSFA-Net) for SAR ship target recognition is proposed in this article. In the network, the SAR ship target is first separated from the background by fine target segmentation. Then, the scattering centers (SCs) of ship targets are extracted and converted to local graph structures based on the $k$-nearest neighbors algorithm. The local graph structures are associated by the scattering center feature association module and enhanced by the multiscale feature enhancement module to produce the multiscale global scattering features. Moreover, the deep features of the targets are extracted by the multikernel deep feature extraction module to characterize the high-dimensional information. Finally, the scattering features and deep features are fused by weighted integration to enrich the diversity of features. The experimental results on the FUSAR-Ship and OpenSARShip dataset show that the MGSFA-Net can significantly improve the recognition performance, even on a few-shot condition with the accuracy increasing over 2%–3%. The feature distribution and visualization show the effectiveness of the MGSFA-Net to characterize the multiscale global scattering association features.

Target recognition from remote sensing images is commonly challenging because of large-scale variations and small objects, and these challenges are more prominent in satellite video images. The current object detection algorithms have some difficulties in fine-grained feature extraction and classification for multiscale and small objects. We propose a novel model called the SVSDet method based on YOLOv5 improvement to address the above-mentioned issues. In this method, we have introduced the space-to-depth module into the backbone of the network, which enhances the network's ability to extract fine-grained features. The neck structure is improved by using the bidirectional feature pyramid network to enhance the network's ability to extract features at multiple scales, thereby improving its overall multiscale feature extraction ability. Subsequently, we have replaced the C3 module in the original network's neck with the C2f module to obtain more abundant gradient flow information. This helps to improve the network's performance further. Finally, the coordinate attention module is introduced into the cross-scale feature connection path, which effectively enhances the network's target detection and recognition performance. We have conducted extensive comparative experiments and ablation experiments on the publicly available datasets ShipRSImageNet and SAT-MTB to confirm the effectiveness of our proposed SVSDet method. The performance of this approach is then evaluated using Jilin 1 satellite video data, and it outperforms the main YOLO series algorithms currently used.

The identification of ships in Synthetic Aperture Radar (SAR) imagery is critical for effective maritime surveillance. The advent of deep learning has significantly improved the accuracy of SAR ship classification and recognition. However, distinguishing features between different ship categories in SAR images remains a challenge, particularly as the number of categories increases. The key to achieving high recognition accuracy lies in effectively extracting and utilizing discriminative features. To address this, we propose DCN-MSFF-TR, a novel recognition model inspired by the Transformer encoder–decoder architecture. Our approach integrates a deformable convolutional module (DCN) within the backbone network to enhance feature extraction. Additionally, we introduce multi-scale self-attention processing from the Transformer into the feature hierarchy and fuse these representations at appropriate levels using a feature pyramid strategy. This enables each layer to leverage both its own information and synthesized features from other layers, enhancing feature representation. Extensive evaluations on the OpenSARShip-3-Complex and OpenSARShip-6-Complex datasets demonstrate the effectiveness of our method. DCN-MSFF-TR achieves average recognition accuracies of 78.1% and 66.7% on the three-class and six-class datasets, respectively, outperforming existing recognition models and showcasing its superior capability in accurately identifying ship categories in SAR images.

Deep learning is the major technique used to identify objects in images captured by the synthetic aperture radar (SAR). While SAR images can be used to identify ships in general, detecting multiple ships or small vessels in these images in complex contexts remains an outstanding challenge. This study proposes a model of detection based on the improved PP-YOLO deep convolutional neural network that can identify multiple ships as well as small vessels in complex scenarios from SAR images. The histogram equalization algorithm is first used to preprocess the SAR images, and then the initial anchor box is optimized by using the shape similarity distance-based K-means clustering algorithm. Following this, the accuracy of the training network is improved based on the feature pyramid network and an attention mechanism. The experimental results show that the average accuracy (average precision) of the model was 94.25% at 41.63 frames per second on the GF-3 and the Sentinel-1 SAR datasets, superior to those of YOLOv3 (Darknet), YOLOv7, FPN (VGG), SSD, Faster R-CNN, and PP-YOLO (RestNet50-vd). The model also satisfies the demands of real-time detection. [ABSTRACT FROM AUTHOR]

Quickly identifying ships in the dock with remote sensing images enables more effective management of the dock. This paper briefly introduced the detection of ship targets in remote sensing images and used the Faster-regional convolutional neural network (RCNN) algorithm to identify ships in remote sensing images. The Faster-RCNN algorithm was improved to improve its performance of target detection. When using a regional proposal network (RPN) to calculate the candidate target frame, the improved algorithm selected it from feature maps of convolution layers at different scales. The improved Faster-RCNN algorithm was compared with traditional Faster-RCNN and support vector machine (SVM) algorithms in the simulation experiment. The results showed that the improved Faster-RCNN detection algorithm was more accurate in positioning and recognizing categories; the improved Faster-RCNN detection algorithm had higher accuracy in identifying ships and showed a smaller decrease with the increase of the threshold value of IOU. [ABSTRACT FROM AUTHOR]

Maritime surveillance is extensively concerned by worldwide authorities, in which ship recognition in synthetic aperture radar (SAR) images is a significant and fundamental component. Though some development has been achieved in the SAR ship recognition task, two areas remain inadequately explored, which are the comprehensive utilization of multiscale features and the deployment of the prior knowledge of the ship shape. In this article, a novel ship augmented attention network (SA$^{2}$Net) for ship recognition is proposed, which comprehensively utilizes the multiscale features and integrates the ship shape prior to the end-to-end network. On one hand, due to the unequal effects of different scales, a scale attention module is proposed to adaptively select and assign weights to desired feature scales while disregarding irrelevant scales. Moreover, a feature weaving module (FWM) is constructed to merge semantic and detailed features produced by the high-to-low backbone, enriching representations across all scales of ship targets. On the other hand, in order to incorporate the priory knowledge of the ship shape into the network, we develop a feature augmentation module (FAM) to further boost the ship recognition accuracy. This module can provide rectangular receptive fields that align with the shape of ships, wherein a limitation encountered with traditional square convolutions. Comprehensive experiments on representative three- and six-category OpenSARShip tasks and seven-category FUSAR-Ship tasks show that our SA$^{2}$Net demonstrates superior performance when compared to the current state-of-the-art methods.

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

SAR ship detection and recognition are important components of the application of SAR data interpretation, allowing for the continuous, reliable, and efficient monitoring of maritime ship targets, in view of the present situation of SAR interpretation applications. On the one hand, because of the lack of high-quality datasets, most existing research on SAR ships is focused on target detection. Additionally, there have been few studies on integrated ship detection and recognition in complex SAR images. On the other hand, the development of deep learning technology promotes research on the SAR image intelligent interpretation algorithm to some extent. However, most existing algorithms only focus on target recognition performance and ignore the model's size and computational efficiency. Aiming to solve the above problems, a lightweight model for ship detection and recognition in complex-scene SAR images is proposed in this paper. Firstly, in order to comprehensively improve the detection performance and deployment capability, this paper applies the YOLOv5-n lightweight model as the baseline algorithm. Secondly, we redesign and optimize the pyramid pooling structure to effectively enhance the target feature extraction efficiency and improve the algorithm's operation speed. Meanwhile, to suppress the influence of complex background interference and ships' distribution, we integrate different attention mechanism into the target feature extraction layer. In addition, to improve the detection and recognition performance of densely parallel ships, we optimize the structure of the model's prediction layer by adding an angular classification module. Finally, we conducted extensive experiments on the newly released complex-scene SAR image ship detection and recognition dataset, named the SRSDDv1.0 dataset. The experimental results show that the minimum size of the model proposed in this paper is only 1.92 M parameters and 4.52 MB of model memory, which can achieve an excellent F1-Score performance of 61.26 and an FPS performance of 68.02 on the SRSDDv1.0 dataset. [ABSTRACT FROM AUTHOR]

For the traditional deep learning cannot solve the fog, coastal background interference, and the difficulty of small ships recognition, a multi-scale deep learning training model is proposed in this paper. Based on Faster R-CNN, this paper uses guided filtering to remove fog, as well as combined with negative sample enhancement learning to train the model, thus solving recognition of ship in complex sea conditions. And with multi-scale training strategy, the multi-scale ship samples are produced and sent to the network for training, so as to solve the problem of small target recognition. The experimental results show that compared with the Faster R-CNN, the precision and recall of our method increase by 6.43% and by 4.68% respectively. It solves the difficulty of ships recognition under complex sea conditions and small ship recognition that cannot be solved by traditional deep learning methods, the trained model has good generalization ability and robustness. [ABSTRACT FROM AUTHOR]

Maritime transportation plays a significant role in international trade and the global supply chain. To enhance maritime safety and reduce pollution to the marine environment, various regulations and conventions are proposed by international organizations. To ensure that shipping activities comply with the relevant regulations, more and more attention has been paid to maritime surveillance. Specifically, cameras have been widely equipped on the shore and drones to capture the videos of vessels. Then, computer vision (CV) methods are adopted to recognize the specific type of ships in the videos so as to identify illegal shipping activities. However, the complex marine environments may hinder the CV models from making accurate ship recognition. Therefore, this study proposes a novel approach of integrating the domain knowledge, such as the ship features and sailing speed, in CV for ship recognition of maritime transportation, which can better support maritime surveillance. We also give two specific examples to demonstrate the great potential of this method in future research on ship recognition. [ABSTRACT FROM AUTHOR]

ObjectiveThe aim of this paper is to proposes methods for better recognizing and positioning ships sailing in critical and wide-area waterways during monitoring operation.MethodsBased on video surveillance technology, the joint use of the motion and appearance features of ship target is carried out to realize a wide-area multi-dimensional recognition function via the combination of background subtraction based moving object detection algorithm and deep learning based target recognition algorithm. In addition, the improved approaches including water ripple noise reduction, hierarchical moving object detection and window segmentation of waterway monitoring image are put forward to further improve recognition accuracy.ResultsThe field demonstration results show that the improved methods proposed in this paper allow the accurate recognition of a ship of any type or size on the monitoring screen, and the use of conventional cameras can also achieve the recognition and position of a ship navigating a water area within a radius of 3 km. Conclusions The improved methods proposed in this study have a range of advantages including wide-area monitoring, complete coverage of ship types and sizes, automatic target recognition and robust anti-interference ability.

As artificial intelligence continues to advance, deep learning has greatly contributed to the advancement of ship recognition using synthetic aperture radar (SAR) images. Deep learning-based SAR ship recognition performance is largely dependent on the sample set used. SAR ship recognition datasets published in recent years, however, are most derived from a single SAR satellite sensor. It needs to be evaluated and analyzed carefully whether the model trained by a single satellite dataset can still achieve the same accuracy with different SAR satellites. This article focuses on the following research to address these issues. First, using multiple SAR satellite sensors, we create a new SAR ship dataset (named generalization performance evaluation dataset, GPED) containing multiresolution and multipolarization data to examine the generalization performance of the deep learning-based SAR ship recognition method. GPED and a marine target detection dataset (MTDD) are then used to evaluate and analyze the generalization performance of current mainstream deep learning methods. According to the the experiment results, the mean average accuracy of the ship recognition model trained on GPED is generally higher than that of MTDD, which proves that the GPED has a better generalization performance. Furthermore, SAR ship detection datasets have more samples than ship recognition datasets, which inspired us to use transfer learning to transfer knowledge from ship detection to ship recognition. In this article, a method for ship recognition based on transfer learning that utilizes the knowledge gained from the ship detection task is proposed. The method includes two modules: 1) pretraining module and 2) fine-tuning module. It can apply samples of unlabeled ship types to ship recognition, thus reducing the number of labeled samples that are required for ship recognition. The experimental results on GPED and MTDD show that our method can achieve good recognition performances.

Copyright of Journal of Dalian Ocean University is the property of Journal of Dalian Ocean University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The recognition of ships from chaff cloud jamming is challenging because they have similar dimensions and radar cross sections. In this paper, we propose a polarimetric recognition technique with sophisticated polarimetric target decomposition. Three sophisticated scattering models are integrated to constitute a seven-component model-based decomposition method so as to accurately characterize the dominant and local scattering of ships. Based on the concepts of contrast and suppression, a robust scattering contribution difference feature is designed according to the derived scattering contributions. The constructed feature vector, combined with the polarization scattering angle, is inputted into the support vector machine to fulfill the recognition process. Simulated and real polarimetric radar data are utilized to test the proposed method, and the results show that the proposed method outperforms state-of-the-art methods by achieving the highest recognition rate of over 98%.

In order to solve the problem of low recognition accuracy in fine-grained ship images with a single feature, a ship target recognition method based on the fusion of recurrent attention convolutional neural network (RA-CNN) and multi- feature regions is proposed. This method introduces the scale-dependent pooling (SDP) algorithm in the VGG-19 network to solve the problem of excessive pooling of small targets in the network, and improves the recognition performance of small ships. The attention proposal network (APN) introduces joint clustering algorithm to form multiple independent feature regions, so that the whole model can make full use of global information and improve the accuracy of ship recognition. At the same time, a feature region optimization method is designed to reduce the overlap rate of multiple feature region and solve the problem of overfitting. By defining a new loss function to crosstrain the VGG-19 and APN, the convergence is accelerated. The proposed method is tested by using the open optoelectronic ship database, the recognition accuracy is up to 90.2%. Both the recognition rate and the robustness of the model are greatly improved compared with the single feature. [ABSTRACT FROM AUTHOR]

Maritime transportation plays a significant role in international trade and the global supply chain. To enhance maritime safety and reduce pollution to the marine environment, various regulations and conventions are proposed by international organizations. To ensure that shipping activities comply with the relevant regulations, more and more attention has been paid to maritime surveillance. Specifically, cameras have been widely equipped on the shore and drones to capture the videos of vessels. Then, computer vision (CV) methods are adopted to recognize the specific type of ships in the videos so as to identify illegal shipping activities. However, the complex marine environments may hinder the CV models from making accurate ship recognition. Therefore, this study proposes a novel approach of integrating the domain knowledge, such as the ship features and sailing speed, in CV for ship recognition of maritime transportation, which can better support maritime surveillance. We also give two specific examples to demonstrate the great potential of this method in future research on ship recognition.

Synthetic aperture radar (SAR) ship recognition can obtain location and class information from SAR scene images, which is important in military and civilian fields, and has turned into a very important research focus recently. Limited by data conditions, the current research mainly includes two aspects: ship detection in SAR scene images and ship classification in SAR slice images. These two parts are not yet integrated, but it is necessary to integrate detection and classification in practical applications, although it will cause an imbalance of training samples for different classes. To solve these problems, this paper proposes a ship recognition method on the basis of a deep network to detect and classify ship targets in SAR scene images under imbalance data. First, RetinaNet is used as the backbone network of the method in this paper for the integration of ship detection and classification in SAR scene images. Then, taking into account the issue that there are high similarities among various SAR ship classes, the squeeze-and-excitation (SE) module is introduced for amplifying the difference features as well as reducing the similarity features. Finally, considering the problem of class imbalance in ship target recognition in SAR scene images, a loss function, the central focal loss (CEFL), based on depth feature aggregation is constructed to reduce the differences within classes. Based on the dataset from OpenSARShip and Sentinel-1, the results of the experiment suggest that the the proposed method is feasible and the accuracy of the proposed method is improved by 3.9 percentage points compared with the traditional RetinaNet.

To solve the issue with automatic recognition of ship images in video surveillance system, this study proposes a ship recognition approach based on Hu invariant moments and Convolutional Neural Network (CNN). Ship image is firstly denoised using improved threshold function of Wavelet Transform (WT) and then segmented via iterative auto-threshold segmentation algorithm to extract the ship area in the image. After that improved CNN is applied to further extract features of ship images. At the same time the image is divided into sub-images horizontally where Hu invariant moments is extracted. The Hu invariant moments of each sub-image are concatenated into a composite vector as the Hu invariant moments of the whole image, which are integrated with spatial location information. The last step is to fuse the CNN features and Hu invariant moments to obtain discriminative feature representation. Hu invariant moments which are invariant to translation, rotation and scaling are used to supplement the shape and contour information of the ship images. And Softmax function is applied to automatically recognize ship images in the output layer. Two fusion methods have been applied to verify the effectiveness of the proposed approach based on feature extraction at different levels. Experimental results show that the first fusion method achieves highest recognition accuracy in self-built dataset and visible and infrared spectrums (VAIS) dataset, up to 98.28% and 92.80% respectively. Recognition accuracy of the second fusion method is also higher than existing methods. Moreover, results obtained from F1-score and confusion matrix further validate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

To solve the problem of ship recognition in video images, a ship recognition method based on Morphological Watershed image segmentation and Zemike moment is proposed. Firstly, the video frame image is pre-processed by gray algorithm, and then the gray image is filtered by wavelet transform to remove noise. After denoising, the Morphological Watershed algorithm is used to segment the image and extract the ship area in the image. Next, the feature of ship image is extracted based on deep learning convolution neural network (CNN) and Zemike moment method. Finally, the KNN-SVM classifier is trained according to the image features and class labels to realize the automatic recognition of ships. Experimental results show that the method can effectively identify 3 types of ships, with an average detection accuracy of 87%. [ABSTRACT FROM AUTHOR]

As a data-driven approach, deep learning requires a large amount of annotated data for training to obtain a sufficiently accurate and generalized model, especially in the field of computer vision. However, when compared with generic object recognition datasets, aerial image datasets are more challenging to acquire and more expensive to label. Obtaining a large amount of high-quality aerial image data for object recognition and image understanding is an urgent problem. Existing studies show that synthetic data can effectively reduce the amount of training data required. Therefore, in this paper, we propose the first synthetic aerial image dataset for ship recognition, called UnityShip. This dataset contains over 100,000 synthetic images and 194,054 ship instances, including 79 different ship models in ten categories and six different large virtual scenes with different time periods, weather environments, and altitudes. The annotations include environmental information, instance-level horizontal bounding boxes, oriented bounding boxes, and the type and ID of each ship. This provides the basis for object detection, oriented object detection, fine-grained recognition, and scene recognition. To investigate the applications of UnityShip, the synthetic data were validated for model pre-training and data augmentation using three different object detection algorithms and six existing real-world ship detection datasets. Our experimental results show that for small-sized and medium-sized real-world datasets, the synthetic data achieve an improvement in model pre-training and data augmentation, showing the value and potential of synthetic data in aerial image recognition and understanding tasks.

This study develops a robust method for ship target recognition, based on inverse synthetic aperture radar (ISAR) image matching with the template of 3D model. To deal with the difficulty of building template lib, the authors develop to use CAD model instead of the live radar data, which can be projected to the range–Doppler plane at any angle. In the study, the method of matching between the observed ISAR image and candidate target image of model is also proposed, including feature extraction and scoring for recognition. In addition, influences of estimation accuracy for projection are analysed and simulated. Finally, recognition results obtained with simulated data are provided to verify the effectiveness of the proposed approach.

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This study develops a robust method for ship target recognition, based on inverse synthetic aperture radar (ISAR) image matching with the template of 3D model. To deal with the difficulty of building template lib, the authors develop to use CAD model instead of the live radar data, which can be projected to the range–Doppler plane at any angle. In the study, the method of matching between the observed ISAR image and candidate target image of model is also proposed, including feature extraction and scoring for recognition. In addition, influences of estimation accuracy for projection are analysed and simulated. Finally, recognition results obtained with simulated data are provided to verify the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Fine-Grained ship classification is quite challenging because the visual differences between the subcategories are small. Due to the large intra-class similarity, it is very difficult to classify the ship objects without bounding box/part annotations. In this paper, we propose a model that combines multiple deep CNN features and use fusion strategies to explore of multi-scale features relationship. Because different levels/depths CNN features have different properties, so we combine multiple low-level local CNN features with high-level global CNN feature for object classification. The model shows a good way of tailoring pre-trained CNN models to fine-grained ship classification, which have lower cost in computation and storage compared with some state-of-the-art CNN methods and achieves the significant classification performances in FGVC-Aircraft and Stanford Cars datasets. [ABSTRACT FROM AUTHOR]

Ship recognition from chaff cloud jamming is challenging since they have similar dimensions and radar cross sections. In this paper, a polarimetric recognition technique with sophisticated polarimetric decomposition is proposed. To this end, a seven-component model-based decomposition is first put forward by integrating three sophisticated scattering models, thus the dominant and local scattering of ships can be characterized accurately. According to the derived scattering contributions, a robust discrimination feature is then designed based on the concept of contrast and suppression. Coupled with the average scattering angle estimated from eigen-based decomposition, the constructed feature vector is inputted into the support vector machine and the recognition is finally fulfilled. The proposed method is tested on simulated and real polarimetric radar data and the results demonstrate that the proposed method achieves the highest recognition rate of over 98%, which outperforms the state-of-the-art methods.

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the requirements of effectively recognizing ships using optical remote sensing data, a ship recognition method of probability generative model based on variational inference is proposed. Firstly, according to the principle of region partition by pixel gray level, the feature extraction based on local spatial gray information of pixels is built, which can efficiently measure similarity degree between the current pixel and its neighborhood structure in a search window, and can be able to provide ship recognition feature stably and accurately. In addition, theoretical analysis shows that the feature extraction method has greatly reduced time complexity of the algorithm. Secondly, a classification method of probability generative model based on variational inference is presented, in this model, manifold similarity based on local reverse entropy operator is used to measure the discrepancy of samples, and the neighborhood samples are selected from top of defined dominant set. Finally, experimental results on real data demonstrate that the proposed method can be obtained a higher recognition performance than k-nearest-neighbor (KNN), support vector machine (SVM), hierarchical discriminant regression (HDR), probability generative model (PGM), dynamic probability generative model (DPGM), it satisfies the time efficiency requirements of ship recognition in projects. [ABSTRACT FROM AUTHOR]

Ship-radiated underwater noises are essential in marine target identification. However, it is very difficult to extract valuable target information from ocean ambient noises. Here, a combined classification method is proposed based on the improved empirical mode decomposition to process the underwater signals of offshore ships. The signals are separated into a series of samples with a signal duration of 100 ms and a set of intrinsic mode functions (IMFs) is generated for each sample. The feature extraction of each IMF is realized by defining and calculating its central frequency and energy intensity. Then, the central frequency of each IMF is projected into a three-dimensional space according to the three top-ranked IMFs based on energy intensity, and the K nearest neighbor (KNN) algorithm is employed to identify the different offshore ships. It was observed that the proposed method can efficiently distinguish the three ships when 80 % of the samples are randomly selected as the training set and the remaining 20 % are used as the test set. The overall recognition rate after 1000 random tests was greater than 95 % for the short-time signals of approximately 100 ms and completely unknown types of ships, which indicates that the proposed method is applicable to offshore ship classification and identification. [ABSTRACT FROM AUTHOR]

Ship target recognition has always been a hot issue in the field of ocean surveillance. Due to the serious shortage of samples in ship target recognition for synthetic aperture radar (SAR) images, the template-based method is still one of the most effective ways to solve the problem. In this letter, we put forward a novel ship recognition method based on the projection shape template (PST), aiming at increasing both the accuracy and the robustness of the recognition. The PST of each category is calculated by projecting the 3-D model obtained from the two-view images of the target to the 2-D slant-plane image according to the SAR imaging model. Then, we propose a contour extraction method to detect the profile of ships, which served as the feature. Finally, the identity of the query ship is obtained through contour matching. Experimental results indicate that the proposed method is effective even when the number of samples is extremely small, consequently providing a promising way for the automatic interpretation of ship targets in the SAR images. [ABSTRACT FROM PUBLISHER]

During remote image classification, accurately classifying ships with insufficient label data is a well-known challenge. In this paper, we propose an intelligent, semi-supervised learning algorithm called active deep network based on BvSB (BvSB-ADN). BvSB-ADN is initially constructed based on the structure of restricted Boltzmann machines (RBM), then active learning is used to identify samples which can be labeled as training data. In the sample-identification phase, the best versus second-best (BvSB) rule is applied to determine the most useful samples; the labeled samples as-selected and all unlabeled samples are then combined to train the BvSB-ADN architecture. The BvSB and classifier are based on the same architecture, which makes selecting the most important samples relatively very simple. We applied BvSB-ADN to a ship classification task to verify its effectiveness and feasibility, and found that it outperforms other classification methods. BvSB-ADN also showed impressive performance on the MNIST dataset. [ABSTRACT FROM AUTHOR]

Aiming at detecting sea targets reliably and timely, a discriminative ship recognition method using optical remote sensing data based on variational methods probability generative model is presented. First, an improved Hough transformation is utilized for pretreatment of the target candidate region, which reduces the amount of computation by filterring the edge points, our experiments indicate the targets (ships) can be detected quickly and accurately. Second, based on rough set theory, the common discernibility degree is used to compute the significance weight of each candidate feature and select valid recognition features automatically. Finally, for each node, its neighbor nodes are sorted by their manifold similarity to the node. Using the classes of the selected nodes from top of sorted neighbor nodes list, a dynamic probability generative model is built to recognize ships in data from optical remote sensing system. Experimental results on real data show that the proposed approach can get better classification rates at a higher speed than the k -nearest neighbor (KNN), support vector machines (SVM) and traditional hierarchical discriminant regression (HDR) method. [ABSTRACT FROM AUTHOR]

Aiming at recognizing the battlefield's ship targets on the sea reliably and timely, a discriminative method for ship recognition using optical remote sensing data entropy-based hierarchical discriminant regression (E-HDR) is presented. First, target features including size, texture, shape, and moment invariants features, as well as area ratio codes are extracted as candidate features, and then information entropy is used to choose the attributes in target recognition, which can reduce the interference of redundant attributes to target recognition, and the valid recognition features are selected automatically. Next, entropy is also used to realize the sub nodes splitting adaptively and automatically, which avoids manual intervention well. Ultimately, according to entropy, a decision tree based on hierarchical discriminant regression (HDR) theory is built to recognize ships in data from optical remote sensing systems. Experimental results on real data show that the proposed approach can get better classification rates at a higher speed than k -nearest neighbor (KNN), support vector machines (SVM), affinity propagation (AP) and traditional hierarchical discriminant regression (HDR) methods. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for ship recognition and classification using sound produced and radiated underwater. To do so, a three-step procedure is proposed. First, the preprocessing operations are utilized to reduce noise effects and provide signal for feature extraction. Second, a binary image, made from frequency spectrum of signal segmentation, is formed to extract effective features. Third, a neural classifier is designed to classify the signals. Two approaches, the proposed method and the fractal-based method are compared and tested on real data. The comparative results indicated better recognition ability and more robust performance of the proposed method than the fractal-based method. Therefore, the proposed method could improve the recognition accuracy of underwater acoustic targets. [ABSTRACT FROM AUTHOR]