期刊
INTERNATIONAL JOURNAL OF NAVAL ARCHITECTURE AND OCEAN ENGINEERING
卷 11, 期 1, 页码 202-210出版社
SOC NAVAL ARCHITECTS KOREA
DOI: 10.1016/j.ijnaoe.2018.04.001
关键词
Obstacles model; Satellite images; Convex hull; Path planning; USV
资金
- Natural Science Foundation of Hubei Province [2016CFB502, 2015CFB586]
- Fundamental Research Funds for the Central Universities [163111005, 2017-YB-030]
The obstacles modeling is a fundamental and significant issue for path planning and automatic navigation of Unmanned Surface Vehicle (USV). In this study, we propose a novel obstacles modeling method based on high resolution satellite images. It involves two main steps: extraction of obstacle features and construction of convex hulls. To extract the obstacle features, a series of operations such as sea-land segmentation, obstacles details enhancement, and morphological transformations are applied. Further-more, an efficient algorithm is proposed to mask the obstacles into convex hulls, which mainly includes the cluster analysis of obstacles area and the determination rules of edge points. Experimental results demonstrate that the models achieved by the proposed method and the manual have high similarity. As an application, the model is used to find the optimal path for USV. The study shows that the obstacles modeling method is feasible, and it can be applied to USV path planning. (C) 2018 Society of Naval Architects of Korea. Production and hosting by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据