OCEANS 2019 MTS/IEEE SEATTLE最新文献_第6页

A Risk Retirement Pathway for Potential Effects of Underwater Noise and Electromagnetic Fields for Marine Renewable Energy 水下噪声和电磁场对海洋可再生能源潜在影响的风险退役路径

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962841

A. Copping, Mikaela C. Freeman, A. Gorton, L. Hemery

引用次数: 1

Intelligent Risk-Based Under-Ice Altitude Control for Autonomous Underwater Vehicles 基于智能风险的自主水下航行器冰下高度控制

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962532

J. E. Bremnes, Petter Norgren, A. Sørensen, Christoph A. Thieme, I. Utne

引用次数: 3

Automatic Identification of Rain-contaminated Regions in X-band Marine Radar Images x波段海洋雷达图像中雨污染区域的自动识别

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962617

Xinwei Chen, Weimin Huang

引用次数: 4

Weakly supervised learning of point-level annotation for coral image segmentation 珊瑚图像分割的弱监督点级标注

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962759

Xi Yu, B. Ouyang, J. Príncipe, S. Farrington, J. Reed, Yanjun Li

{"title":"Weakly supervised learning of point-level annotation for coral image segmentation","authors":"Xi Yu, B. Ouyang, J. Príncipe, S. Farrington, J. Reed, Yanjun Li","doi":"10.23919/OCEANS40490.2019.8962759","DOIUrl":"https://doi.org/10.23919/OCEANS40490.2019.8962759","url":null,"abstract":"Successful methods for image segmentation typically are based on a large number of annotated data sets. However, these large amount of good quality labels are highly expensive and tedious to obtain especially for marine plants data sets like corals. Therefore, the deficiency of labels is one of the main obstacles to image segmentation. To alleviate this problem, we propose a novel framework that generates labels iteratively only given a few point-level labels taken advantage of the local structure of real images. In our framework, we first train a Convolutional Neural Network (CNN) with initial sparse point-level labeled pixels, and then we use Latent Dirichlet Allocation (LDA) to generate labels based on the features extracted by CNN models, add these generated labels in the training set and train the CNN model again. Thus, our framework relies only on sparsely point-level labels and does not require any extra annotations. Experimental results on coral image data set collected in Pulley Ridge region from the Gulf of Mexico show that our iterative label augmentation method outperforms previous models trained by the same level of supervision.","PeriodicalId":208102,"journal":{"name":"OCEANS 2019 MTS/IEEE SEATTLE","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114289240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Underwater Object Recognition: A Domain-Adaption Methodology of Machine Learning Classifiers 水下目标识别:一种机器学习分类器的领域自适应方法

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962693

António Pedro Oliva Afonso, A. Pinto

引用次数: 1

High-Frequency Sonar Calibration Using Thin Wires as Standard Point Targets 用细导线作为标准点目标的高频声纳校准

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962782

Jinyun Ren, A. Barzegar, O. B. Gammelsæter

引用次数: 0

Fish Modeling and Bayesian Learning for the Lakshadweep Islands Lakshadweep群岛的鱼类建模和贝叶斯学习

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962892

Abhinav Gupta, P. Haley, D. Subramani, Pierre FJ Lermusiaux

{"title":"Fish Modeling and Bayesian Learning for the Lakshadweep Islands","authors":"Abhinav Gupta, P. Haley, D. Subramani, Pierre FJ Lermusiaux","doi":"10.23919/OCEANS40490.2019.8962892","DOIUrl":"https://doi.org/10.23919/OCEANS40490.2019.8962892","url":null,"abstract":"In fish modeling, a significant amount of uncertainty exists in the parameter values, parameterizations, functional form of model equations, and even the state variables themselves. This is due to the complexity and lack of understanding of the processes involved, as well as the measurement sparsity. These challenges motivate the present proof-of-concept study to simultaneously learn and estimate the state variables, parameters, and model equations from sparse observations. We employ a novel dynamics-based Bayesian learning framework for high-dimensional, coupled fish-biogeochemical-physical partial-differential equations (PDEs) models, allowing the simultaneous inference of the augmented state variables and parameters. After reviewing the status of ecosystem modeling in the coastal oceans, we first complete a series of PDE-based learning experiments that showcase capabilities for fish-biogeochemical-physical model equations and parameters, using nonhydrostatic Boussinesq flows past a seamount. We then showcase realistic ocean primitive-equation simulations and analyses, using fish catch data for the Lakshadweep islands in India. These modeling and learning efforts could improve fisheries management from a standpoint of sustainability and efficiency.","PeriodicalId":208102,"journal":{"name":"OCEANS 2019 MTS/IEEE SEATTLE","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123469881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 17

Preliminary results for glider localization in the Beaufort Duct using broadband acoustic sources at long range 利用宽带声源进行波弗特管道中滑翔机定位的初步结果

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962637

Cristian E. Graupe, Lora J. Van Uffelen, Sarah E. Webster, P. Worcester, M. Dzieciuch

引用次数: 8

Experimental study on collision avoidance procedures for plastic waste cleaner USV 塑料垃圾清扫器USV避碰程序试验研究

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962649

Kazumasa Harada, Keisuke Watanabe, Koshi Utsunomiya, Masatoshi Shimpo, R. Dzeng

{"title":"Experimental study on collision avoidance procedures for plastic waste cleaner USV","authors":"Kazumasa Harada, Keisuke Watanabe, Koshi Utsunomiya, Masatoshi Shimpo, R. Dzeng","doi":"10.23919/OCEANS40490.2019.8962649","DOIUrl":"https://doi.org/10.23919/OCEANS40490.2019.8962649","url":null,"abstract":"Sea plastic waste is a big issue and cleaning them is very important. We are developing a USV cleaner that collects plastic waste for cleaning at the port. There are many ships in the port and the USV needs to design a collision avoidance procedure appropriately. To develop a collision avoidance procedure, several experiments must be performed. In this paper, we will first introduce a low-cost tank experiment system to study USV collision avoidance procedures. This system consists of a ceiling camera and a robotic ship. The ceiling camera is installed above the tank and uses image processing to calculate the heading and COG coordinates of each ship. This is intended to emulate GNSS indoors. The catamaran was designed and manufactured using a 3D printer, taking into account the size of the tank and the capacity of the ship. The catamaran has a single board computer and a wireless communication device. Each ship receives coordinates via wireless communication from a computer that calculates the coordinates in the tank. Next, the results of tank experiments using the above system are introduced. When the experiment starts, the ceiling camera calculates the ship's position and sends the position data to each ship in increments of 10 [Hz]. When the ship receives the position, it moves forward while maintaining the bow and speed until a collision is detected. When each ship finds a possible collision, it changes the navigation mode from normal mode to collision avoidance mode. This experiment confirmed that the ceiling camera position detection, catamaran thrust, and wireless communication were all functioning properly. Finally, we introduce the conceptual design of the Catamaran USV used to clean plastic waste in port areas.","PeriodicalId":208102,"journal":{"name":"OCEANS 2019 MTS/IEEE SEATTLE","volume":"64 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126181986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Low Energy, Passive Acoustic Sensing for Wireless Underwater Monitoring Networks 用于无线水下监测网络的低能量被动声传感

OCEANS 2019 MTS/IEEE SEATTLE Pub Date : 2019-10-01 DOI: 10.23919/OCEANS40490.2019.8962399

G. Lowes, J. Neasham, R. Burnett, C. Tsimenidis

{"title":"Low Energy, Passive Acoustic Sensing for Wireless Underwater Monitoring Networks","authors":"G. Lowes, J. Neasham, R. Burnett, C. Tsimenidis","doi":"10.23919/OCEANS40490.2019.8962399","DOIUrl":"https://doi.org/10.23919/OCEANS40490.2019.8962399","url":null,"abstract":"This paper presents work towards developing a low-power, low-cost underwater passive acoustic monitoring network. The main aim is to accurately detect passing vessels by exploiting the acoustic signature emitted during propeller cavitation. To achieve this a novel combination of analogue signal processing and embedded programming has been created. The vessel detection system has been integrated with a very low power piece of hardware, developed by Newcastle University, capable of underwater acoustic communication. The vessel detector is based on the principles of the Detection of Envelope Modulation on Noise (DEMON) algorithm [1]. Using this method, along with statistical standard error of the estimate analysis, decisions are made as to whether or not a vessel is present. These decisions are then transmitted acoustically via an underwater wireless network to the end-user. In field trials carried out, the system demonstrated the ability to both detect vessels and communicate results reliably whilst maintaining the low-power, low-cost ethos of this project. Future research is planned to utilise the low-power vessel detection system developed to trigger a higher power mode. This mode will sample the raw audio as opposed to the current method which samples only the signal's envelope. This will allow for a full spectral analysis of the vessel's signature enabling feature extraction and individual vessel characterisation.","PeriodicalId":208102,"journal":{"name":"OCEANS 2019 MTS/IEEE SEATTLE","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130110682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4