Efficient Ship:A Hybrid Deep Learning Framework for Ship Detection in the River

Optical image-based ship detection can ensure the safety of ships and promote the orderly management of ships in offshore waters.Current deep learning researches on optical image-based ship detection mainly focus on improving one-stage detectors for real-time ship detection but sacrifices the accuracy of detection.To solve this problem,we present a hybrid ship detection framework which is named EfficientShip in this paper.The core parts of the EfficientShip are DLA-backboned object location(DBOL)and CascadeRCNN-guided object classification(CROC).The DBOL is responsible for finding potential ship objects,and the CROC is used to categorize the potential ship objects.We also design a pixel-spatial-level data augmentation(PSDA)to reduce the risk of detection model overfitting.We compare the proposed EfficientShip with state-of-the-art(SOTA)literature on a ship detection dataset called Seaships.Experiments show our ship detection framework achieves a result of 99.63%(mAP)at 45 fps,which is much better than 8 SOTA approaches on detection accuracy and can also meet the requirements of real-time application scenarios.

SAR-LtYOLOv8:A Lightweight YOLOv8 Model for Small Object Detection in SAR Ship Images

The high coverage and all-weather capabilities of Synthetic Aperture Radar(SAR)image ship detection make it a widely accepted method for maritime ship positioning and identification.However,SAR ship detection faces challenges such as indistinct ship contours,low resolution,multi-scale features,noise,and complex background interference.This paper proposes a lightweight YOLOv8 model for small object detection in SAR ship images,incorporating key structures to enhance performance.The YOLOv8 backbone is replaced by the Slim Backbone(SB),and the Delete Medium-sized Detection Head(DMDH)structure is eliminated to concentrate on shallow features.Dynamically adjusting the convolution kernel weights of the Omni-Dimensional Dynamic Convolution(ODConv)module can result in a reduction in computation and enhanced accuracy.Adjusting the model’s receptive field is done by the Large Selective Kernel Network(LSKNet)module,which captures shallow features.Additionally,a Multi-scale Spatial-Channel Attention(MSCA)module addresses multi-scale ship feature differences,enhancing feature fusion and local region focus.Experimental results on the HRSID and SSDD datasets demonstrate the model’s effectiveness,with a 67.8%reduction in parameters,a 3.4%improvement in AP(average precision)@0.5,and a 5.4%improvement in AP@0.5:0.95 on the HRSID dataset,and a 0.5%improvement in AP@0.5 and 1.7%in AP@0.5:0.95 on the SSDD dataset,surpassing other state-of-the-art methods.

Lira-YOLO: a lightweight model for ship detection in radar images

For the detection of marine ship objects in radar images, large-scale networks based on deep learning are difficult to be deployed on existing radar-equipped devices. This paper proposes a lightweight convolutional neural network, LiraNet, which combines the idea of dense connections, residual connections and group convolution, including stem blocks and extractor modules.The designed stem block uses a series of small convolutions to extract the input image features, and the extractor network adopts the designed two-way dense connection module, which further reduces the network operation complexity. Mounting LiraNet on the object detection framework Darknet, this paper proposes Lira-you only look once(Lira-YOLO), a lightweight model for ship detection in radar images, which can easily be deployed on the mobile devices. Lira-YOLO's prediction module uses a two-layer YOLO prediction layer and adds a residual module for better feature delivery. At the same time, in order to fully verify the performance of the model, mini-RD, a lightweight distance Doppler domain radar images dataset, is constructed. Experiments show that the network complexity of Lira-YOLO is low, being only 2.980 Bflops, and the parameter quantity is smaller, which is only 4.3 MB. The mean average precision(mAP) indicators on the mini-RD and SAR ship detection dataset(SSDD) reach 83.21% and 85.46%, respectively,which is comparable to the tiny-YOLOv3. Lira-YOLO has achieved a good detection accuracy with less memory and computational cost.

A synthetic aperture radar sea surface distribution estimation by n-order Bézier curve and its application in ship detection

To dates,most ship detection approaches for single-pol synthetic aperture radar（SAR） imagery try to ensure a constant false-alarm rate（CFAR）.A high performance ship detector relies on two key components：an accurate estimation to a sea surface distribution and a fine designed CFAR algorithm.First,a novel nonparametric sea surface distribution estimation method is developed based on n-order Bézier curve.To estimate the sea surface distribution using n-order Bézier curve,an explicit analytical solution is derived based on a least square optimization,and the optimal selection also is presented to two essential parameters,the order n of Bézier curve and the number m of sample points.Next,to validate the ship detection performance of the estimated sea surface distribution,the estimated sea surface distribution by n-order Bézier curve is combined with a cell averaging CFAR（CA-CFAR）.To eliminate the possible interfering ship targets in background window,an improved automatic censoring method is applied.Comprehensive experiments prove that in terms of sea surface estimation performance,the proposed method is as good as a traditional nonparametric Parzen window kernel method,and in most cases,outperforms two widely used parametric methods,K and G0 models.In terms of computation speed,a major advantage of the proposed estimation method is the time consuming only depended on the number m of sample points while independent of imagery size,which makes it can achieve a significant speed improvement to the Parzen window kernel method,and in some cases,it is even faster than two parametric methods.In terms of ship detection performance,the experiments show that the ship detector which constructed by the proposed sea surface distribution model and the given CA-CFAR algorithm has wide adaptability to different SAR sensors,resolutions and sea surface homogeneities and obtains a leading performance on the test dataset.

Detection of weak ship signals with the optimization of polarimetric contrast enhancement

An optimization of polarimetric contrast enhancement method is proposed to detect ships with lowship-to-clutter power ratio.The received power is calculated with Kennaugh matrix and an iterative algo-rithm is adopted to get the optimal polarimetric states.The optimization method depresses the power of o-cean clutter and increases the power of ship signal.With the double effects,the contrast of ship to oceanis dramatically increased.Thus small ship or weak signals of low ship-to-ocean power ratio can easily bedetected.Ship signals can be distinguished from speckle noise using the different variation trend after op-timization,and thus the threshold problem can be avoided.Moreover,the analyses of different ship'sKennaugh matrices give two implications.One is that the results are affected little by choosing differentKennaugh matrices of ships with strong intensity from Synthetic Aperture Radar(SAR)images.The otheris that ship's Kennaugh matrix chosen from real SAR images is more favorable than that of ideal scatter-ing.Finally,the optimization results are confirmed by polarimetric scattering angle and co-polarizationphase difference.

Ship Detection and Recognition Based on Improved YOLOv7

In this paper,an advanced YOLOv7 model is proposed to tackle the challenges associated with ship detection and recognition tasks,such as the irregular shapes and varying sizes of ships.The improved model replaces the fixed anchor boxes utilized in conventional YOLOv7 models with a set of more suitable anchor boxes specifically designed based on the size distribution of ships in the dataset.This paper also introduces a novel multi-scale feature fusion module,which comprises Path Aggregation Network(PAN)modules,enabling the efficient capture of ship features across different scales.Furthermore,data preprocessing is enhanced through the application of data augmentation techniques,including random rotation,scaling,and cropping,which serve to bolster data diversity and robustness.The distribution of positive and negative samples in the dataset is balanced using random sampling,ensuring a more accurate representation of real-world scenarios.Comprehensive experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches in terms of both detection accuracy and robustness,highlighting the potential of the improved YOLOv7 model for practical applications in the maritime domain.

A new scattering similarity based metric for ship detection in polarimetric synthetic aperture radar image

A new paradigm for ship detection in polarimetric synthetic aperture radar(Pol-SAR)image is presented.We firstly utilize the scattering similarity parameters to investigate the differences of scattering mechanism between ships and sea clutter.Based on these differences,we propose a novel ship detection metric,denoted as the scattering similarity based metric(SSM),to conduct ship detection task.The distribution model of SSM metric is investigated and modeled by kernel density estimation(KDE).Based on the statistical distribution,an adaptive constant false alarm rate(CFAR)detection scheme is implemented.We compare the proposed SSM with two classic polarimetric metrics,i.e.,the polarimetric cross-entropy(PCE)and the reflection symmetry metric(RSM).The experimental results conducted on C-band RADARSAT-2 Pol-SAR data demonstrate the feasibility and advantage of the proposed SSM metric both in sea clutter modeling and in ship detection.

Swin-PAFF: A SAR Ship Detection Network with Contextual Cross-Information Fusion

Synthetic Aperture Radar(SAR)image target detection has widespread applications in both military and civil domains.However,SAR images pose challenges due to strong scattering,indistinct edge contours,multi-scale representation,sparsity,and severe background interference,which make the existing target detection methods in low accuracy.To address this issue,this paper proposes a multi-scale fusion framework(Swin-PAFF)for SAR target detection that utilizes the global context perception capability of the Transformer and the multi-layer feature fusion learning ability of the feature pyramid structure(FPN).Firstly,to tackle the issue of inadequate perceptual image context information in SAR target detection,we propose an end-to-end SAR target detection network with the Transformer structure as the backbone.Furthermore,we enhance the ability of the Swin Transformer to acquire contextual features and cross-information by incorporating a Swin-CC backbone network model that combines the Spatial Depthwise Pooling(SDP)module and the self-attentive mechanism.Finally,we design a cross-layer fusion neck module(PAFF)that better handles multi-scale variations and complex situations(such as sparsity,background interference,etc.).Our devised approach yields a noteworthy AP@0.5:0.95 performance of 91.3%when assessed on the HRSID dataset.The application of our proposed technique has resulted in a noteworthy advancement of 8%in the AP@0.5:0.95 scores on the HRSID dataset.

A Hybrid Features Based Detection Method for Inshore Ship Targets in SAR Imagery

Convolutional Neural Networks(CNNs)have recently attracted much attention in the ship detection from Synthetic Aperture Radar(SAR)images.However,compared with optical images,SAR ones are hard to understand.Moreover,due to the high similarity between the man-made targets near shore and inshore ships,the classical methods are unable to achieve effective detection of inshore ships.To mitigate the influence of onshore ship-like objects,this paper proposes an inshore ship detection method in SAR images by using hybrid features.Firstly,the sea-land segmentation is applied in the pre-processing to exclude obvious land regions from SAR images.Then,a CNN model is designed to extract deep features for identifying potential ship targets in both inshore and offshore water.On this basis,the high-energy point number of amplitude spectrum is further introduced as an important and delicate feature to suppress false alarms left.Finally,to verify the effectiveness of the proposed method,numerical and comparative studies are carried out in experiments on Sentinel-1 SAR images.

Improved Ship Target Detection Accuracy in SAR Image Based on Modified CFAR Algorithm

A novel algorithm for the detection of ship target with high accuracy in the synthetic aperture radar(SAR) with high spatial resolution image is proposed. The SAR image may include not only the ship targets but also the interferences such as the sea clutter,the strong reflection target,the sidelobe and so on.The conventional constant false alarm rate(CFAR) algorithm has some disadvantages,and it has not enough prior information about the size of the ships. Hence,it cannot separate the adjacent ships correctly. A comprehensive algorithm based on the modified CFAR algorithm and opening operation is presented to solve the problem,and the detection accuracy can be improved consequently. The results of SAR image illustrate the effectiveness of the method in this paper.

A Novel SAR Image Ship Small Targets Detection Method

To satisfy practical requirements of high real-time accuracy and low computational complexity of synthetic aperture radar (SAR) image ship small target detection, this paper proposes a small ship target detection method based on the improved You Only Look Once Version 3 (YOLOv3). The main contributions of this study are threefold. First, the feature extraction network of the original YOLOV3 algorithm is replaced with the VGG16 network convolution layer. Second, general convolution is transformed into depthwise separable convolution, thereby reducing the computational cost of the algorithm. Third, a residual network structure is introduced into the feature extraction network to reuse the shallow target feature information, which enhances the detailed features of the target and ensures the improvement in accuracy of small target detection performance. To evaluate the performance of the proposed method, many experiments are conducted on public SAR image datasets. For ship targets with complex backgrounds and small ship targets in the SAR image, the effectiveness of the proposed algorithm is verified. Results show that the accuracy and recall rate improved by 5.31% and 2.77%, respectively, compared with the original YOLOV3. Furthermore, the proposed model not only significantly reduces the computational effort, but also improves the detection accuracy of ship small target.

Deep Neural Network Based Detection and Segmentation of Ships for Maritime Surveillance

In recent years,computer visionfinds wide applications in maritime surveillance with its sophisticated algorithms and advanced architecture.Auto-matic ship detection with computer vision techniques provide an efficient means to monitor as well as track ships in water bodies.Waterways being an important medium of transport require continuous monitoring for protection of national security.The remote sensing satellite images of ships in harbours and water bodies are the image data that aid the neural network models to localize ships and to facilitate early identification of possible threats at sea.This paper proposes a deep learning based model capable enough to classify between ships and no-ships as well as to localize ships in the original images using bounding box tech-nique.Furthermore,classified ships are again segmented with deep learning based auto-encoder model.The proposed model,in terms of classification,provides suc-cessful results generating 99.5%and 99.2%validation and training accuracy respectively.The auto-encoder model also produces 85.1%and 84.2%validation and training accuracies.Moreover the IoU metric of the segmented images is found to be of 0.77 value.The experimental results reveal that the model is accu-rate and can be implemented for automatic ship detection in water bodies consid-ering remote sensing satellite images as input to the computer vision system.

A NOVEL SHIP WAKE DETECTION METHOD OF SAR IMAGES BASED ON FREQUENCY DOMAIN

Moving ships produce a set of waves of "V' pattern on the ocean. These waves can often be seen by Synthetic Aperture Radar (SAR). The detection of these wakes can provide important information for surveillance of shipping, such as ship traveling direction and speed. A novel approach to the detection of ship wakes in SAR images based on frequency domain is provided in this letter. Compared with traditional Radon-based approaches, computation is reduced by 20%-40% without losing nearly any of detection performance. The testing results using real data and simulation of synthetic SAR images test the algorithm's feasibility and robustness.

SSE-Ship: A SAR Image Ship Detection Model with Expanded Detection Field of View and Enhanced Effective Feature Information

In this paper, we propose a SAR image ship detection model SSE-Ship that combines image context to extend the detection field of view domain and effectively enhance feature extraction information. This method aims to solve the problem of low detection rate in SAR images with ship combination and ship fusion scenes. Firstly, we propose STCSPB network to solve the problem of ship and non-ship object fusion by combining image contextual feature information to distinguish ship and non-ship objects. Secondly, we combine SE Attention to enhance the effective feature information and effectively improve the detection accuracy in combined ship driving scenes. Finally, we conducted extensive experiments on two standard base datasets, SAR-Ship and SSDD, to verify the effectiveness and stability of our proposed method. The experimental results show that the SSE-Ship model has P = 0.950, R = 0.946, mAP_0.5:0.95 = 0.656 and FPS = 50 on the SAR-Ship dataset and mAP_0.5 = 0.964 and R = 0.940 on the SSDD dataset.

Compatible Design of the System to Detect Ships and Airplanes with a Ground Wave Over-the-horizon Radar

This paper provides a design method based on a time-shared form, which obtains the compatibility of signal and the system for detecting both ships and airplanes. Then, it gives the structure diagram of the system and the chart diagram of signal processing. Finally, the continuity problem of signal modulation for ship detection is discussed.

AIR-SARShip-1.0：高分辨率SAR舰船检测数据集

近年来,深度学习技术得到广泛应用,然而在合成孔径雷达(SAR)舰船目标检测研究中,由于数据获取难、样本规模小,尚难以支撑深度网络模型的训练。该文公开了一个面向高分辨率、大尺寸场景的SAR舰船检测数据集,该数据集包含31景高分三号SAR图像,场景类型包含港口、岛礁、不同级别海况的海面等,背景涵盖近岸和远海等多样场景。同时,该文使用经典舰船检测算法和深度学习算法进行了实验,其中基于密集连接端到端网络方法效果最佳,平均精度达到88.1%。通过实验对比分析形成指标基准,方便其他学者在此数据集基础上进一步展开SAR舰船检测相关研究。

Density-based ship detection in SAR images:Extension to a self-similarity perspective

Nonlocal self-similarity is an important property of Synthetic Aperture Radar(SAR)images to characterize the repetitiveness of features embodied by SAR images within nonlocal areas and has been used for enhancement of SAR images.Existing SAR ship detectors often independently handle small sub-images cropped from a large marine SAR image and do not exploit the nonlocal self-similarity therein.In this paper,we propose a new ship detector from the perspective of nonlocal self-similarity in SAR images to improve the ship detection performance,basically including three stages:prescreening,intra-cue calculation,and inter-cue calculation.In the prescreening stage,we design a new Histogram-based Density(HD)feature to rapidly select candidate sub-images potentially containing ship targets from a large SAR image.In the intra-cue calculation stage,target cues within a single candidate sub-image are extracted.In the inter-cue calculation stage,thanks to the nonlocal self-similarity among different candidate sub-images in terms of density features,we innovatively extract a weighted superpixel-HD map to obtain accumulated intracues across all the candidate sub-images.Finally,for each candidate sub-image,we fuse its inter-cue and intra-cue to obtain final detection results.Experimental results based on real SAR images show that our newly proposed method provides a better target-to-clutter contrast and ship detection performance than those of other state-of-the-art detection approaches.

MMShip:中分辨率多光谱卫星图像船舶数据集

针对现有遥感船舶数据集均为裁剪后的图像,用数据集训练的检测算法直接运用于卫星图像原始尺度时检测效果较差的问题,建立了可见光和近红外4个波段的多光谱卫星船舶数据集MMShip,数据集同时包含卫星图像的原始尺度数据和切割后的小尺度船舶数据。本数据集引入多波段信息,弥补现有数据集多为可见光图像,而可见光容易受到光照条件等影响的缺点。在全球海域内下载云量低于3的Sentinel-2卫星图像,进行大气校正后只选取10 m分辨率的红绿蓝和近红外4个波段,以景为单位筛选出包含有船舶的图像。把筛选后的图像按无重叠的方式切分为512×512,剔除其中不包含船舶目标的图像。然后,使用LabelImage软件对小尺度数据进行了水平框标注,再将标注数据反推至原始尺度得到原始尺度下的标注信息。最后,利用几种典型的检测算法在切割后的MMShip小尺度数据集上进行了可见光、近红外、多光谱对比实验。构建了一个涵盖不同场景的多光谱卫星船舶目标数据集,包含497景原始尺度标注数据和裁剪后的5 016组船舶目标图像。对比实验验证了近红外波段信息的补充有助于提高船舶目标检测算法的精度。多光谱船舶数据集MMShip可用于卫星图像尺度和普通图像尺度的多光谱船舶目标检测算法研究。

The Research of Ship Cabin Monitoring System on Single Chip Computer

The monitoring system of ship cabin based on single chip computer is introduced. The system can inspect the signal circulatively coming from sensors of all kinds, and give alarm when limit is broken. It demonstrated the working principles, hardware block diagram and software flow diagram of the system.

自注意力机制驱动的轻量化高鲁棒船舶目标检测方法

[目的]海岸监控与驾驶瞭望过程中,需要在远距离、多场景下对各种目标进行识别与跟踪。其中,船舶目标往往成像尺寸小、特征不明显,容易与其他目标混淆。为此,提出一种船舶检测方法ShipDet,通过设计专用骨干网络、改进特征提取过程、约束微观检测头,旨在改善上述问题。[方法]首先,通过融合自注意力模块Swin Transformer(STR)和经典CSPDarknet53网络,构造对微小目标高度敏感的特征融合提取网络,以增强小目标特征与环境的相关关系,关联船与航道、船与船、船与岸线,显著抑制不相关信息。考虑到数据集的船舶目标分布不均匀并且尺度变化较小的特点,保留2个检测层,减少模型参数并进一步提升模型性能。最后,使用SIoU损失函数(SCYLLA-IoU)来约束检测头,降低损失函数的回归自由度,提高检测的精度和抗干扰能力。[结果]在2023ships数据集上的验证结果表明,所提方法在船舶目标检测任务上表现较好,mAP@0.5达到92.9%,平均精度为92.1%,消耗参数量仅为35366310,整体检测性能优于其他算法。[结论]ShipDet方法将为海事监控、智能航行提供高效的支撑。