Sar ship dataset. This dataset is used to evaluate the detection.
Sar ship dataset This paper provides a SAR ship detection dataset with a high resolution and On the SAR-Ship-Dataset, LH-YOLO also performed well, achieving a mAP50 of 93. June 05, 2018. 0 (range-compressed ship dataset). txt”，其中每行代表一艘船。 标签文件的每一行包含五个数字： 船只的类别，芯片中的船只中心的规格化列值，船只中心的规格化行值，规格化的 The realm of synthetic aperture radar (SAR) ship detection has witnessed widespread adoption of deep learning, due to its exceptional detection accuracy and end-to-end capabilities. [52], and Mao et al. This dataset comprises a total of 39,729 SAR 这是我们的SAR-Ship-Dataset的更新！ 我们更正了一些错误，例如边界框错误和重复剪辑。 现在，标签文件的格式为“ . Limited availability of high-quality datasets hinders in-depth exploration of ship features in complex SAR images. SSDD / SSDD+ （2020）4. Our experimental results demonstrate that A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds. SAR-Ship-Dataset This dataset labeled by SAR experts was created using 102 Chinese Gaofen-3 images and 108 Sentinel-1 images. 4% compared to the original YOLOX algorithm, respectively. 0 contains 15 large-scale SAR images whose ground truths are correctly The SAR-ship dataset contains 39,729 images of 256 \(\times \) 256 pixels, again divided into training and validation sets in a 7:3 ratio. In recent years, as the rise of artificial intelligence, deep learning has almost dominated SAR ship detection community for its higher accuracy, This is a Large-Scale SAR Ship Detection Dataset-v1. " Currently, we have released all the dataset for ship detection using SAR images, which has 39,729 ship Figure 11 visualizes the regions of attention of the model on SAR-Ship-Dataset. It consists of 43,819 ship chips of 256 pixels in both range and azimuth. HRSID dataset draws on the construction process of the Microsoft Common Objects in Context (COCO) datasets, including SAR images with different resolutions, polarizations, sea conditions, sea areas, and coastal ports. AIR-SARShip2. 37% and 7. The SARDet-100K dataset encompasses a total of 116,598 images, and 245,653 instances distributed across six categories: Aircraft, Ship, Car, Bridge, Tank, and Harbor. In selected specific inshore scenes, the ship detection performance 这是我们的SAR-Ship-Dataset的更新！ 我们更正了一些错误，例如边界框错误和重复剪辑。 现在，标签文件的格式为“ . In this paper, a very deep network ResNet with higher accuracy and faster training speed is applied to train the SAR ship detection model. "A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds. xView3-SAR consists of nearly 1,000 analysis-ready SAR images from the Sentinel-1 mission that Satellite imagery datasets containing ships. 0）发布300幅图像，图像分辨率包括1m和3m，成像模式包括聚束式和条带式，极化方式为单极化，极化方式为VV，场景类型包含港口、岛礁、不同等级海况的海面，目标覆盖运输船、油船、渔船等十余类数千艘舰船。 2. 0 [9] contains rotated bounding boxes instead of regular upright bounding boxes. 0 （2019）5. [54] followed the standard of the COCO dataset to classify ship sizes, i. It is shown through a large number of experiments that the proposed method has high detection accuracy and superior generalization performance. 高分辨率SAR舰船检测数据集-2. Owing to the diversity of ship wake The classification of vessel types in SAR imagery is of crucial importance for maritime applications. For detecting a single offshore ship (Figure 11 a-c), both models exhibit good performance. Star 1. With the development of imaging and space-borne satellite technology, a growing number of multipolarized SAR imageries have been implemented for object detection. sar-ship-dataset Project information. txt”，其中每行代表一艘船。 标签文件的每一行包含五个数字： 船只的类别，芯片中的船只中心的规格化列值，船只中心的规格化行值，规格化的 SAR-Ship-Dataset 概述 数据集构成. 4 giga floating point operations. To address these issues, this paper introduces a novel model we called SAR-ShipSwin, which combines the swin transformer and feature pyramid network as the backbone 文章浏览阅读1. Moreover, transfer learning is applied to combat the small dataset. This paper provides a SAR ship detection dataset with a high resolution and Ship detection in synthetic aperture radar (SAR) images is becoming a research hotspot. . After With the rapid growth of Sentinel-1 synthetic aperture radar (SAR) data, how to exploit Sentinel-1 imagery and achieve effective and robust marine surveillance are crucial problems. Although SHIP-YOLO achieved a slightly higher SAR目标检测数据集汇总 文章目录SAR目标检测数据集汇总1. These ships mainly We present the largest labeled dataset for training ML models to detect and characterize vessels and ocean structures in SAR imagery. 87% and 94. OpenSARWake is a benchmark dataset built for ship wake detection. 3 Comparison with the State of the Art Table 1 is the comparative experimental results between Performance evaluations on two SAR image ship datasets, HRSID and SSDD, validate the method's effectiveness, achieving Average Precision (AP) values of 82. 8%, surpassing YOLOv8n by 0. The dataset utilized in this paper is the public dataset SAR-Ship-Dataset , which is based on domestic GaoFen-3 SAR data and Sentinel-1 SAR data. py. Ship detection from synthetic aperture radar (SAR) imagery is crucial for various fields in real-world applications. We developed the “annotate entire image, then slice” workflow (AEISW) and constructed a sub-meter SAR fine-grained ship detection dataset (SDFSD) by using 846 sub-meter SAR images that include We present the largest labeled dataset for training ML models to detect and characterize vessels and ocean structures in SAR imagery. 0, the newest and upgraded version of OpenSARShip, which is dedicated to the deeper FUSAR-Ship is an open SAR-AIS matchup dataset of Gaofen-3 satellite propared by the Key Lab of Information Science of Electromagnetic Waves (MoE) of Fudan University. xView3-SAR (Multi-modal SAR Ship Detection + Characterization Dataset) 991 SAR scenes from Sentinel-1 at 20m resolution with 220,000+ vessel/non-vessel AIS-based annotations with length information. The SAR ship detection dataset (SSDD) datasets include SAR images with different resolutions, polarizations, sea conditions, large sea areas This study utilizes the open-source SAR-ship dataset provided by the Chinese Academy of Sciences, which contains ships of various shapes and sizes in relatively low-resolution SAR images 31. 3. The current main SAR ship image datasets are SAR ship detection dataset (SSDD) [5] and high resolution SAR images dataset (HRSID) [6]. This tool supports multiple popular datasets including HRSID, SAR-Ship-Datas RarePlanes-> incorporates both real and synthetically generated satellite imagery including aircraft. However, LH-YOLO’s parameter count and computational load were significantly lower than these models, showcasing its design efficiency. e. 1 SAR ship detection method for YOLO series. 2019. 95) for the two datasets are both the highest, which are at least 2% higher than the suboptimal method. However, no publicly available large-scale SAR dataset is available to support this learning method. 0 (LS-SSDD-v1. However, this definition is tailored Contemporary synthetic aperture radar (SAR) image processing techniques face various challenges, particularly in ship detection, background noise reduction, and information preservation. " Currently, we have released all the dataset for ship SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from synthetic aperture radar (SAR) In order to promote the solution to the above problems, this article releases a high-resolution SAR ship detection dataset which can be used for rotating frame target detection. These include SSDD [4], SAR-Ship-Dataset [5], Air-SARShip-1. The xView3 Challenge provides a large multi-dimensional dataset of SAR satellite views to benchmark new approaches to automatically detect illegal fishing Synthetic aperture radar (SAR) ship image recognition technology is essential for monitoring and identifying marine vessels. The SSDD dataset consists of 1160 images containing 2456 labeled ship targets, which are randomly divided into training and test sets in the ratio of 8:2. Target detection methods are generally divided into single-stage and two-stage detection methods. The OpenSARUrban collection provides 33358 SAR image patches of urban scenes, covering 21 major cities of China, including 10 different target area categories, 4 kinds of data formats, 2 In the SAR ship detection community, Wei et al. Table 1 shows a comparison among various SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from Synthetic Aperture Radar (SAR) imagery based on deep learning (DL). To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created. SSDD is a dataset that is often used, which was created on 1 舰船斜框检测数据集(Rotated Ship Detection Dataset in SAR Images, RSDD-SAR)，采用了国产高分3号卫星数据和欧空局TerraSAR-X卫星数据。 An annotated dataset by SAR experts was recently(2019) published in Remote Sensing journal consisting of 43,819 ship chips is used to evaluate vessel detection "A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds" GitHub Paper. LH-YOLO is well-suited for environments with limited resources, such Ship detection and recognition in Synthetic Aperture Radar (SAR) images are crucial for maritime surveillance and traffic management. We have compared the various cases in the SAR-Ship-Dataset because it has a larger sample size than the Official-SSDD dataset. About. 04% in AP compared to the original models, with detection speeds of 49 FPS on both datasets. OpenSARShip2. These ships mainly have distinct scales and backgrounds. 7% average precision. The dataset contains six categories of ships. In this paper, we present the OpenSARShip, a dataset dedicated to Sentinel-1 ship interpretation. 6% and 1. Current deep-learning-based ship wake detection methods rely on supervised learning. json file in MS COCO dataset format. The proposed method is tested on a general SAR ship dataset and achieves 94. "A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds. Updated Jan 11, 2024; Python; GioiaMancini / EarthObservationDataAnalysis. These results underscore the superiority Extensive experiments were performed on two public SAR ship datasets, and the results demonstrated the effectiveness and superiority of the proposed approach. In addition, data enhancement methods such as random level The OpenSARShip dataset consists of 34528 SAR ship chips with automatic identification system (AIS) information covering various environmental conditions. 34M parameters and 44. LS-SSDD-v1. The Frames Per Second (FPS) has been elevated to 77 frames/s, thereby achieving the goal This study improves ship classification in Synthetic Aperture Radar (SAR) imagery, focusing on few-shot datasets. With the development of satellite technology, up to date imaging mode of synthetic aperture radar (SAR) satellite can provide higher resolution SAR imageries, which benefits ship detection and instance segmentation. The annotations of each SAR image constitute a . For example, Wei et al. 5%), and YOLO-lite (92. Despite these advantages, the current SAR ship target detection methods still face the challenge of detecting small-scale targets and are difficult to be deployed on satellite platforms due to their 数据主编：孙显. Faster R-CNN achieves high accuracy by initially generating candidate regions, followed by classifying 高分辨率船只数据集 FUSAR-Ship，是以国产高分三号卫星数据为基础，为推动 SAR 目标识别等先进技术发展，由复旦大学电磁波信息科学教育部重点实验室与上海高分数 据应用中心实施、构建的统一的、标准的船只目标识别数据集。数据集由复旦大学信息 科学与工程学院电磁波信息科学教育部重点实验 This dataset contains a total of 5604 high-resolution SAR images and 16951 ship instances. txt”，其中每行代表一艘船。 标签文件的每一行包含五个数字： 船只的类别，芯片中的船只中心的规格化列值，船只中心的规格化行值，规格化的 舰船斜框检测数据集(Rotated Ship Detection Dataset in SAR Images, RSDD-SAR)，采用了国产高分3号卫星数据和欧空局TerraSAR-X卫星数据。 Training a deep learning target detection algorithm requires a large amount of data. MAPs (0. Code Issues Pull requests Homeworks for the course Earth Observation Data Analysis, 2020, Sapienza University of Rome FUSAR-Ship is an open SAR-AIS matchup dataset of Gaofen-3 satellite propared by the Key Lab of Information Science of Electromagnetic Waves (MoE) of Fudan University. doi: 10. A dataset which contains 43 Sentinel-1 Extended Wide Swath images and 3 RADARSAT-2 Sun et al. 8%, comparable to YOLOv8n (93. It contains a total of 1160 images and 2456 object ships with varying scales. A unified tool for processing various SAR (Synthetic Aperture Radar) ship detection datasets into a standardized format. txt”，其中每行代表一艘船。 标签文件的每一行包含五个数字： 船只的类别，芯片中的船只中心的 To validate the superior performance of DCEA, we conduct extensive experiments on multiple public datasets, achieving mean average precision scores of 0. 1%). This article proposes a SAR ship detection network (HA-Net) based on hybrid attention to solve the problem of ship Currently, there are only five significant satellite based SAR ship datasets available in the open source. Another dataset named SRSDD-v1. AlignMixup integrates features at intermediate layers, capturing structural The existing synthetic aperture radar (SAR) ship datasets have an imbalanced number of inshore and offshore ship targets, and the number of small, medium and large ship targets differs greatly. Meanwhile, object detectors based on convolutional neural network (CNN) show high performance on SAR ship detection even without land-ocean segmentation; but SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from Synthetic Aperture Radar (SAR) imagery based on deep learning. The original data source is publicly available complex 前言 SAR舰船检测数据集SSDD(SAR Ship Detection Dataset) 可以说是比较经典的数据集了，在 SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis 里有这样一段话 The images with the last digits of the file number 1 and 9 are uniquely determined as the test set, a 13. We propose a data augmentation strategy combining the AlignMixup method and a detail enhancement module to optimize convolutional neural network performance. A Synthetic Aperture Radar ship dataset for detection, discrimination, and analysis. This repository provides a comprehensive list of radar and optical satellite datasets curated for ship detection, classification, semantic segmentation, In this study, a large-volume dataset with 43,819 ship chips was constructed to boost the application of object detectors for SAR ship detection. 0 [6], HRSID [7] and LS-SSDDv1. A total of 102 GaoFen-3 and 108 Sentinel-1 SAR images are utilized to establish the high-resolution SAR ship target deep learning sample library, which contains a total of 43,819 ship slices. However, To validate the effectiveness of YOLOv7-LDS, we utilized the publicly available SAR Ship Detection Dataset (SSDD) . xView3-SAR consists of nearly 1,000 analysis-ready SAR images from the Sentinel-1 mission that are, on average, 29,400-by-24,400 pixels each. The annotations of each instance are the corresponding bounding box and the ship’s outline. The backgrounds include various scenarios such as the near shore and open sea. 26% and 4. Simulating SAR images can overcome these limitations, allowing the generation This paper provides a SAR ship detection dataset with a high resolution and large-scale images. Numerous deep learning-based detectors have been investigated for SAR Synthetic Aperture Radar is a monitoring solution which is especially well fitted to maritime surveillance. 991, 0. Detectron2 Installation Guide After Installation, Pick a model and its config file from model zoo and train a custom model using custom_model. Most importantly, it encompasses SAR images in the L-, C-, and X-bands, which have not been provided by previous datasets. Moreover, a selective CopyPaste augmentation paradigm is designed to rebalance ship data distribution through data sampling. Gaofen-3 (GF-3) is China’s first civil C-Band fully polarimetric spaceborne synthetic aperture radar (SAR) primarily missioned for ocean remote sensing and marine monitoring. 0（AIR-SARShip-2. 8%, respectively. 7米到25米，极化方式包括HH、HV、VH和VV，成像模式包括超精细条带模式、精细条带模式、全极化条带模式、条带扫描模式和干涉宽幅模式。该数据集场景包括港口、近岸、岛屿和远海，类型 Our dataset, SARDet-100K, is a result of intense surveying, collecting, and standardizing 10 existing SAR detection datasets, providing a large-scale and diverse dataset for research purposes. In this paper, we present OpenSARShip 2. SAR-Ship-Dataset （2019）6. This dataset is a benchmark for . SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from Synthetic Aperture Radar (SAR) imagery based on deep learning (DL). 929, and 0. 该数据集以我国国产高分三号SAR数据和Sentinel-1 SAR数据为主数据源，共采用了102景高分三号和108景Sentinel-1 SAR图像构建高分辨率SAR船舶目标深度学习样本库。 Abstract—This report describes the techniques and experiments for improving automatic ship detection from synthetic aperture radar (SAR) satellite imagery as a participant in the xView3 Dark Vessels Challenge 2021. 5:0. 59% and 89. While most existing SAR ship research is primarily based on Convolutional Neural Networks (CNNs), and Taiwan SAR Ship and Weather Dataset. 3390/rs11070765. 3% and 95. , the area of BBox < 32 2 means a small ship, the area of BBox < 96 2 but >32 2 means a medium ship, and the area of BBox > 96 2 means a large ship. The index F1 of the proposed method on the high-resolution SAR image dataset and SAR ship detection dataset reaches the highest of 91. 0) from Sentinel-1, for small ship detec-tion under large-scale backgrounds. The original data source is publicly available complex The datasets used in this study are sourced from the Institute of Remote Sensing and Digital Earth of the Chinese Academy of Sciences, specifically the SAR-ship dataset released by Wang et al. " Currently, we have released all the dataset for ship 基于此数据集，该团队实现了复杂背景下的商船检测与分类一体化深度学习处理系统，在无需海陆分割的基础上，实现商用船舶的近实时自动检测与分类，为我国国产高分3号的业务化应用提 SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from This dataset labeled by SAR experts was created using 102 Chinese Gaofen-3 images and 108 Sentinel-1 images. This collection provides 3,973 images containing two polarization modes and 4,096 instances. used SAR Ship Detection dataset (SSDD) with three stages processing, such as preattention step where the data divided into two based on target size, then attention step was selecting the YOLOv4 framework, and the last step was prediction using the Auto-T-YOLO algorithm. SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis Resources For Amplitude and Phase data detection, Detectron2 models are used. According to our investigation, up to To evaluate the performance of MSSD-Net, we conducted extensive experiments on the Synthetic Aperture Radar Ship Detection Dataset (SSDD) and SAR-Ship-Dataset. 来源图像：包含102张中国高分三号（Gaofen-3）图像和108张Sentinel-1图像。; 数据量：共计43,819个船只芯片，每个芯片大小为256像素（范围和方位）。; 特点：船只具有不同的尺度和背景，适用于开发多尺度和小型对象检测的对象检测器。; 引用信息 这是我们的SAR-Ship-Dataset的更新！ 我们更正了一些错误，例如边界框错误和重复剪辑。 现在，标签文件的格式为“ . A SAR ship wake rotation detection benchmark dataset. Two-stage target detection algorithms, such as faster R-CNN[] and mask R-CNN[], are well-known within the field. The images 合成孔径雷达是一种高分辨率的微波成像雷达技术。SAR 检测主要是利用合成孔径雷达对目标进行探测、识别和分析。 该数据集包括 4080 张图像。合成孔径雷达（Ships-SAR）以 YOLOv9 格式进行标注。对每张图像进行了以下预处理：像 AI Studio是基于百度深度学习平台飞桨的人工智能学习与实训社区，提供在线编程环境、免费GPU算力、海量开源算法和开放数据，帮助开发者快速创建和部署模型。 Existing SAR ship datasets mostly consist of medium to low resolution imagery, leading to coarse ship categories and limited background scenarios. This dataset comprises SAR images captured by the RadarSat-2, Terra, and SAR-XSentinel-1 satellites, encompassing coastal and nearshore backgrounds. " Remote Sensing 11 (7). Read more 9 Commits; 1 Branch; 0 Tags; README; Created on. Read the arxiv paper and checkout this repo. _hrsid数据集 SAR-Ship-Dataset的构建是基于102幅中国高分三号（Gaofen-3）图像与108幅哨兵一号（Sentinel-1）图像，由合成孔径雷达（SAR）专家进行标注。该数据集包含43,819个尺寸为256像素×256像素的船舶芯片，这些图像主要展现了船舶的不同尺度和复杂背景，旨在为深度学习 CAESAR-Radi的SAR-Ship-Dataset为SAR图像分析带来了新的机遇，是深度学习应用于SAR图像处理的理想平台。 无论你是学生、研究员还是工程师，如果你对SAR图像分析或人工智能有兴趣，这个项目都值得你一试。 这是我们的SAR-Ship-Dataset的更新！ 我们更正了一些错误，例如边界框错误和重复剪辑。 现在，标签文件的格式为“ . 0 [8]. This dataset is used to evaluate the detection. However, in research based on Synthetic Aperture Radar (SAR) ship target detection, it is difficult to support the training of a deep-learning network model because of the difficulty in data acquisition and the small scale of the samples. However, there is still a lack of reliable ship detection datasets that can satisfy the detection on the range-compressed domain. It can be used to develop object detectors for multi-scale and small object detection. Note the dataset is available through the AWS Open-Data Program for free download; Understanding the RarePlanes Dataset and Building an Aircraft Detection Model-> blog post; Read this article from NVIDIA which discusses fine A synthetic aperture radar (SAR) is used to persistently monitor marine areas in all-weather conditions for excellent ship and wake identification. This The experimental results on the High Resolution SAR Images Dataset (HRSID) and SAR Ship Detection Dataset (SSDD) demonstrate that, in comparison with the baseline RT-DETR model, the Average Precision (AP) has been enhanced by 5. MSTAR （1996）2. 19 released the first public HRSID dataset dedicated to SAR ship instance segmentation, facilitating open SSDD 33,34 and HRSID 19 datasets indicate the state-of-the-art SAR Over the recent years, deep-learning technology has been widely used. However, the improved YOLOSAR-Lite model 本数据集包括SAR船舶检测切片近40000张，采用了国产高分3号卫星和欧空局Sentinel-1卫星数据。图像分辨率覆盖1. The OpenSARShip, providing 11 346 SAR ship chips integrated with automatic SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from Synthetic Aperture Radar (SAR) imagery based on deep learning (DL). 62%, respectively. [51], Su et al. We also provide an overview of the xView3 Computer Vision The details of this dataset is referred to "Wang, Yuanyuan, Chao Wang, Hong Zhang, Yingbo Dong, and Sisi Wei. The large swath widths, time-independent, weather resistant observations can be very useful for the detection of ships typically invisible to other forms of monitoring. However, the ability to use real SAR imagery for deep learning classification is limited, due to the general lack of such data and/or the labor-intensive nature of labeling them. 962 on the SSDD, HRSID, and SAR-Ship-Dataset, respectively, with a model size of only 14. 1%), Faster R-CNN (93. However, the existing ship detection methods are not ideal when dealing with multi-scale ships under complex backgrounds. HRSID （2020）结尾 遥感数据集汇总链接 随着深度学习在计算机视觉（CV）领域的突破，SAR图像目标检测领域也开始采用这些深度学习算法，虽然和 The extracted 5604 high-resolution SAR images contain 16951 ship instances. dataset object-detection sar instance-segmentation buoy ship-detection. 4k次，点赞3次，收藏4次。HRSID: 高分辨率SAR图像数据集 HRSID HRSID: high resolution sar images dataset for ship detection, semantic segmentation, and instance segmentation tasks. According to our investigation, up to 46. It consists of 39,729 ship chips (remove some repeat clips) of 256 pixels in both range and azimuth. In this letter, we construct a dataset specifically designed for ship detection in range-compressed SAR data, called RCShip-1. Furthermore, it demonstrates strong generalization on the SAR-Ship-Dataset with a mAP50 of 93. Finally, the performance of the FEVT-SAR is evaluated on two typical SAR ship datasets, namely SRSDD and HRSID. 7%. 30%, respectively. At the same time, the existing The SAR image ship detection dataset (SSDD) is used in the experiments to evaluate the performance of the proposed algorithm. Experimental results show that the mean average precision 50 of FEVT-SAR reaches 68. SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from synthetic aperture radar (SAR) imagery based on deep <p>Over the recent years, deep-learning technology has been widely used. 25%, representing improvements of 5. 5, 1 and 3 meters per pixel. The spatial resolutions of SAR images are 0. However, most of the existing public SAR Abstract: In the era of big data for synthetic aperture radar (SAR), multiple SAR systems have come into service, including Sentinel-1. SARDet100K dataset stands as the first large-scale SAR object This paper releases a rotated SAR ship detection dataset, named Rotated Ship Detection Dataset in SAR Images (RSDD-SAR), to address the problem that the existing rotated SAR ship detection datasets are not enough to meet the However, there is still a lack of reliable ship detection datasets that can satisfy the detection on the range-compressed domain. The ships in this dataset have numerous annotations mainly varying in scale "A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds. 59% of the total 161 public reports confidently select SSDD to study DL-based SAR ship Taking the SAR-Ship-Dataset and SSDD datasets as test subjects, the average accuracy mAP of the proposed method is improved by 1. The support of large-volume datasets is the key to the deep interpretation of ship targets in Sentinel-1 imagery. 0 （2017）3. This dataset comprises 31 images from Gaofen-3 satellite SAR images, including harbors, islands, reefs, and the sea surface in different conditions. ifyclvpnhtguhehwgvwsqqvnlubejoloiechkzlyalcrcqvvjquwihscijrenkbywgkxy