Marine object detection has gained prominence in marine research, driven by the pressing need to unravel oceanic mysteries and enhance our understanding of invaluable marine ecosystems. There is a profound requirement to efficiently and accurately identify and localize diverse and unseen marine entities within underwater imagery. The open-marine object detection (OMOD for short) is required to detect diverse and unseen marine objects, performing categorization and localization simultaneously. To achieve OMOD, we present \textbf{MarineDet}. We formulate a joint visual-text semantic space through pre-training and then perform marine-specific training to achieve in-air-to-marine knowledge transfer. Considering there is no specific dataset designed for OMOD, we construct a \textbf{MarineDet dataset} consisting of 821 marine-relative object categories to promote and measure OMOD performance. The experimental results demonstrate the superior performance of MarineDet over existing generalist and specialist object detection algorithms. To the best of our knowledge, we are the first to present OMOD, which holds a more valuable and practical setting for marine ecosystem monitoring and management. Our research not only pushes the boundaries of marine understanding but also offers a standard pipeline for OMOD.
The Marine Debris Dataset for Forward-Looking Sonar Semantic Segmentation
Netaji Subhas Institute Of Technology(Netaji Subhas理工学院);German Research Center for Artificial Intelligence(德国人工智能研究中心)
海洋废弃物的准确检测和分割对于保持水体清洁至关重要。本文提出了一种新的数据集海洋垃圾分割收集使用前视声纳(FLS)。该数据集由使用ARIS Explorer 3000传感器捕获的1868幅FLS图像组成。用于生成该数据集的对象包括典型的家用海洋废弃物和干扰海洋对象(轮胎,钩子,阀门等),分为11类加上一个背景类。性能的最先进的语义分割架构与各种编码器已在此数据集上进行了分析,并作为基线结果。由于图像是灰度的,因此没有使用预训练的权重。使用Intersection over Union(IoU)进行比较。性能最好的模型是具有ResNet34主干的Unet,其容量为0.7481 mIoU。该数据集可在www.example.com上获得
Marine life through You Only Look Once's perspective
Norweigan University of Science and Technology(挪威科技大学);SINTEF Digital(挪威科技工业研究院数字部);Oklahoma State University(俄克拉荷马州立大学);Kongsberg Maritime(康士伯海事公司)
随着人们对人类对地球和野生动物的改变的关注,越来越多的人强调可持续和负责任的资源收集。为了保护海洋野生动物,挪威政府决定有必要对挪威峡湾和海洋中各种野生动物的存在和丰富程度进行概述。在本文中,我们应用和分析的目标检测计划,检测相机图像中的鱼。这些数据是从挪威Fulehuk的水下数据站采集的。我们实施了You Only Look Once(YOLO)第3版,并创建了一个由99,961张图像组成的数据集,其mAP为$\sim 0.88$。我们还研究了YOLO中的中间结果,深入了解它如何执行目标检测。
Towards More Efficient EfficientDets and Low-Light Real-Time Marine Debris Detection
Queen’s University Belfast(贝尔法斯特女王大学);National Chiao Tung University(国立交通大学);National Yang Ming Chiao Tung University(国立阳明交通大学);Central Queensland University(中央昆士兰大学)
Detecting Endangered Marine Species in Autonomous Underwater Vehicle Imagery Using Point Annotations and Few-Shot Learning
Australian Centre for Robotics, University of Sydney(悉尼大学澳大利亚机器人中心);Marine Technology Department, Norwegian University of Science and Technology(挪威科技大学海洋技术系);Institute for Marine and Antarctic Studies, University of Tasmania(塔斯马尼亚大学海洋与南极研究所)
University of Groningen(格罗宁根大学);Bonn-Rhein-Sieg University of Applied Sciences(波恩-莱茵-锡格应用科学大学);Worcester Polytechnic Institute(伍斯特理工学院);Heriot-Watt University(赫瑞瓦特大学);German Research Center for Artificial Intelligence(德国人工智能研究中心)
Automatized marine vessel monitoring from sentinel-1 data using convolution neural network
Center for Environment & Water, Research Institute, King Fahd University of Petroleum & Minerals(法赫德国王石油与矿产大学环境与水研究中心);University of Petroleum and Energy Studies(石油与能源研究大学);Dr. B.C. Roy Engineering College(B.C.罗伊博士工程学院);CubicX
针对传统 CFAR 船舶检测缺乏决策能力的问题,提出基于小波变换的卷积神经网络,利用 Sentinel-1 双极化 SAR 数据实现印度西海岸繁忙交通场景下的船舶自动识别,检测准确率达 95.46%。
Unlocking the potential of deep learning for marine ecology: overview, applications, and outlook
Centre for Artificial Intelligence Research, University of Agder(Agder大学人工智能研究中心);Institute of Marine Research(海洋研究所);Top Research Centre Mechatronics, University of Agder(Agder大学顶级机电一体化研究中心);Center for Coastal Research, University of Agder(Agder大学海岸研究中心);Center for Ecological and Evolutionary Synthesis, University of Oslo(奥斯陆大学生态与进化综合中心)
High-Resolution Underwater Camouflaged Object Detection: GBU-UCOD Dataset and Topology-Aware and Frequency-Decoupled Networks
College of Shipbuilding Engineering, Harbin Engineering University(哈尔滨工程大学船舶工程学院);School of Information Science and Technology, Great Bay University(广东工业大学信息科学与技术学院)
School of Computer Science, Wuhan University(武汉大学计算机学院);School of Computer Science, The University of Sydney(悉尼大学计算机学院);School of Computer Science and Engineering, Nanyang Technological University(南洋理工大学计算机科学与工程学院)
MARIS: Marine Open-Vocabulary Instance Segmentation with Geometric Enhancement and Semantic Alignment
University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence (TeleAI)(人工智能研究院(TeleAI));China Telecom(中国电信);Fudan University(复旦大学);Northwestern Polytechnical University(西北工业大学)
ORCA: Object Recognition and Comprehension for Archiving Marine Species
Hong Kong University of Science and Technology(香港科技大学);University of Electronic Science and Technology of China(电子科学与技术大学);Indo Ocean Foundation Project(印度洋基金会项目)
Deep Neural Networks for Marine Debris Detection in Sonar Images
Heriot-Watt University(赫瑞-瓦特大学)
垃圾和废物处理是人类目前面临的最大挑战之一。适当的废物处理和回收利用是任何可持续发展社区的必要条件,在许多沿海地区,漂浮或淹没的垃圾造成了严重的水污染。这就是所谓的海洋垃圾。淹没的海洋废弃物威胁海洋生物,对于浅水沿海地区,它还可能威胁渔船[Iñiguez et al. 2016,Renewable and Sustainable Energy Reviews]。淹没的海洋废弃物通常会在环境中停留很长时间(20年以上),并且由可以回收的材料组成,例如金属,塑料,玻璃等。本文对DNN在FLS图像海洋垃圾检测中的应用进行了综合评价,并对相关问题如图像分类、匹配和检测建议等进行了研究。我们这样做的2069 FLS图像的数据集,我们捕获的ARIS Explorer 3000传感器上的海洋垃圾物体躺在地板上的一个小水箱。我们用于生成此数据集的对象包含典型的家庭海洋垃圾和干扰海洋对象(轮胎,钩子,阀门等),分为10个类和一个背景类。我们的研究结果表明,对于评估的任务,DNN是一种优于相应的最先进技术的技术。特别是对于匹配和检测建议任务,DNN有很大的收益。我们还研究了样本复杂性和对象大小在许多任务中的影响,这对从业者来说是有价值的信息。我们希望我们的研究结果将推进使用自主水下航行器自动调查,检测和收集水下环境中的海洋垃圾的目标。
SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehicles
Department of Computer Science, Dartmouth College(达特茅斯学院计算机科学系);IQT Labs(IQT实验室);Department of Computer Science, Columbia University(哥伦比亚大学计算机科学系);Department of Computer Science, University of Maryland College Park(马里兰大学计算机科学系);The Institute for Human and Machine Cognition and The University of West Florida(人机认知研究所与西佛罗里达大学);School of Computing, Binghamton University(宾夕法尼亚州立大学计算学院)
Expose Camouflage in the Water: Underwater Camouflaged Instance Segmentation and Dataset
School of Information and Communication Engineering, Hainan University(海南大学信息与通信工程学院);School of Electronic and Information Engineering, Guangdong Ocean University(广东海洋大学电子与信息工程学院);School of Computer Science and Technology, Hainan University(海南大学计算机科学与技术学院);School of Computer Science, Nankai University(南开大学计算机科学学院);Institute of Software, Chinese Academy of Science(中国科学院软件研究所);School of Data Science, Lingnan University(岭南大学数据科学学院)
Adaptive Enhancement and Dual-Pooling Sequential Attention for Lightweight Underwater Object Detection with YOLOv10
1,2Department of Computer Science;Engineering, Dhaka University of Engineering \& Technology Gazipur, 1707, Bangladesh 3Department of Computer Science;Engineering, BRAC University Dhaka, Bangladesh
UniV2D: Bridging Visual Restoration and Semantic Perception for Underwater Salient Object Detection
School of Computer Science, Wuhan University(武汉大学计算机学院);School of Computer Science, The University of Sydney(悉尼大学计算机学院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院)
Zero-shot Shark Tracking and Biometrics from Aerial Imagery
Stanford University(斯坦福大学);Flinders University(弗林德斯大学);Centro de Investigación en Ciencias del Mar y Limnología, Universidad de Costa Rica(哥斯达黎加大学海洋与湖沼科学研究中心)