SAR-ShipNet: SAR-Ship Detection Neural Network via Bidirectional Coordinate Attention and Multi-resolution Feature Fusion
Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Collaborative Innovation Center of Novel Software Technology and Industrialization(新型软件技术与产业化协同创新中心)
This paper studies a practically meaningful ship detection problem from synthetic aperture radar (SAR) images by the neural network. We broadly extract different types of SAR image features and raise the intriguing question that whether these extracted features are beneficial to (1) suppress data variations (e.g., complex land-sea backgrounds, scattered noise) of real-world SAR images, and (2) enhance the features of ships that are small objects and have different aspect (length-width) ratios, therefore resulting in the improvement of ship detection. To answer this question, we propose a SAR-ship detection neural network (call SAR-ShipNet for short), by newly developing Bidirectional Coordinate Attention (BCA) and Multi-resolution Feature Fusion (MRF) based on CenterNet. Moreover, considering the varying length-width ratio of arbitrary ships, we adopt elliptical Gaussian probability distribution in CenterNet to improve the performance of base detector models. Experimental results on the public SAR-Ship dataset show that our SAR-ShipNet achieves competitive advantages in both speed and accuracy.
Cross-modal Ship Re-Identification via Optical and SAR Imagery: A Novel Dataset and Method
Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences(中国科学院空间利用技术与工程中心);University of Chinese Academy of Sciences(中国科学院大学)
Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images
School of Electronic and Information Engineering, Beihang University(北京航空航天大学电子与信息工程学院);Edinburgh Napier University(爱丁堡龙比亚大学);Taibah University(塔伊巴大学);University of Strathclyde(斯特拉斯克莱德大学);University of Leicester(莱斯特大学)
常用的水平限界框(HBB)方法不能准确定位合成孔径雷达(SAR)图像中任意方位的细长舰船目标。因此,近年来,基于有向限界框(OBB)的方法逐渐受到研究者的关注。然而,最近提出的大多数基于深度学习的OBB检测方法都会遇到角度或关键点回归中的边界不连续问题。为了缓解这个问题,研究人员提出引入一些手动设置的参数或额外的网络分支来区分边界情况,这使得训练更加困难,导致性能下降。为了解决OBB回归中的边界不连续问题,本文提出了通过学习极坐标编码来检测SAR舰船。该编码方案使用一组从目标中心指向边界点的矢量来表示OBB。直接根据极坐标编码进行训练和推理,避免了边界不连续问题。此外,我们提出了一个Intersect over Union(IOU)加权回归损失,通过IOU度量进一步指导极性编码的训练,提高检测性能。在旋转SAR舰船检测数据集(RSSDD)上的实验结果表明,该方法的检测性能优于其他算法和OBB编码方案,证明了该方法的有效性。
MOS: Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification
School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院)
Boosting ship detection in SAR images with complementary pretraining techniques
Qian Xuesen Laboratory of Space Technology, China Academy of Space Technology(中国空间技术研究院钱学森空间技术实验室);School of Information and Electronics Engineering, Beijing Institute of Technology(北京理工大学信息与电子工程学院);School of Mathematics and Computational Science, Xiangtan University(湘潭大学数学与计算科学学院)
SDF-Net: Structure-Aware Disentangled Feature Learning for Opticall-SAR Ship Re-identification
Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences(中国科学院空间利用技术与工程中心);Key Laboratory of Space Utilization, Chinese Academy of Sciences(中国科学院空间利用重点实验室);University of Chinese Academy of Sciences(中国科学院大学);School of Software, Beihang University(北航软件学院)
OSSDD - a New Open Dataset for Sentinel-1 Ship Detection
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation - IOSB(弗劳恩霍夫光学技术、系统技术与图像利用研究所);Karlsruhe Institute of Technology - KIT(卡尔斯鲁厄理工学院);HENSOLDT Sensors GmbH(亨索尔特传感器有限公司)
A Survey on SAR ship classification using Deep Learning
PhD School in Computer Science, University of Pisa(计算机科学博士学院,比萨大学);Institute of Information Science and Technologies, National Research Council of Italy(意大利国家研究委员会信息科学与技术研究所);National Biodiversity Future Center - NBFC(国家生物多样性未来中心 - NBFC)
Seg-CycleGAN : SAR-to-optical image translation guided by a downstream task
Gina Cody School of Engineering and Computer Science, Concordia University(康考迪亚大学吉娜·科迪工程与计算机科学学院);School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);School of Cybersecurity, Northwestern Polytechnical University(西北工业大学网络空间安全学院)
Domain Adaptive SAR Wake Detection: Leveraging Similarity Filtering and Memory Guidance
College of Computer Science and Technology, Qingdao University(青岛大学计算机科学与技术学院);Laboratory for Regional Oceanography and Numerical Modeling, Qingdao Marine Science and Technology Center(青岛海洋科学与技术中心区域海洋学与数值模拟实验室);School of Computer Science and Information Technology, The University of Nottingham(诺丁汉大学计算机科学与信息学院);State Key Laboratory of Physical Oceanography, Department of Marine Technology, Ocean University of China(中国海洋大学物理海洋学国家重点实验室,海洋技术系)
Bridging Modalities and Tasks: A Unified Hierarchical ViT for SAR-to-Optical Translation and Semantic Segmentation
School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);School of Cybersecurity, Northwestern Polytechnical University(西北工业大学网络空间安全学院)
xView3-SAR: Detecting Dark Fishing Activity Using Synthetic Aperture Radar Imagery
Global Fishing Watch(全球渔业观察);Cambrio;Defense Innovation Unit(国防创新单元);UC Berkeley(加州大学伯克利分校)
全世界不可持续的捕捞做法对海洋资源和生态系统构成重大威胁。识别在传统监测系统中没有出现的船只-被称为"黑暗船只"-是管理和保障海洋环境健康的关键。随着基于卫星的合成孔径雷达(SAR)成像和现代机器学习(ML)的兴起,现在可以在全天候条件下白天或晚上自动检测黑暗船只。然而,SAR图像需要特定领域的处理,并且ML社区无法广泛访问。海洋物体(船舶和海上基础设施)相对较小且稀疏,这对传统的计算机视觉方法构成了挑战。我们提出了用于训练ML模型的最大标记数据集,以检测和表征SAR图像中的船只和海洋结构。xView3-SAR由来自Sentinel-1任务的近1,000张可供分析的SAR图像组成,平均每张图像为29,400 x 24,400像素。使用自动和手动分析的组合对图像进行注释。每一幅SAR图像都附有同地测深和风态栅格。我们还提供了一个概述的xView3计算机视觉挑战赛,一个国际竞争使用xView3-SAR船舶检测和表征在大规模。我们发布数据(\href{https://iuu.xview.us/}{https://iuu.xview.us/})和代码(\href{https://github.com/DIUx-xView}{https://github.com/DIUx-xView}),以支持这一重要应用的ML方法的持续开发和评估。