基于高分辨率遥感影像的船舶航标漂移监测方法，可提升航标漂移监测效果。利用尺度不变特征变换算法，在高分辨率遥感影像内提取航标位置信息特征点，结合欧式距离，得到航标位置信息特征匹配点；利用相关系数编组的目标提取算法，在高分辨率遥感影像内，提取船舶航标目标区域；通过扩展凝聚点和网格的聚类算法，聚类处理船舶航标目标区域内的航标，获取航标编号与中心点坐标等信息；通过分析特征匹配点像素坐标与中心点坐标的关系，进行航标匹配；通过相位相关法，计算匹配成功航标的漂移量。实验证明，该方法可有效提取航标位置信息特征点，精准提取航标目标区域；该方法可有效成功匹配航标，并计算航标漂移量，实现航标漂移监测。
The method of ship drift monitoring based on high resolution remote sensing images is studied to improve the effect of drift monitoring. Using the scale-invariant feature transform algorithm, the feature points of the position information of the beacon are extracted from the high-resolution remote sensing image, and the matching points of the position information are obtained by combining the Euclidian distance. The object extraction algorithm of correlation coefficient grouping is used to extract the target area of ship's beacon in high-resolution remote sensing image. By extending the clustering algorithm of condensing point and grid, the navigation mark in the target area is processed by clustering, and the information of navigation mark number and center point coordinate is obtained. By analyzing the relationship between pixel coordinates and center coordinates of feature matching points, the navigation mark matching is carried out. The drift of the matched beacon is calculated by the phase correlation method. Experimental results show that this method can effectively extract the feature points of the location information of the beacon and accurately extract the target region of the beacon. This method can match the buoy effectively and calculate the drift of the buoy, and realize the monitoring of the buoy drift.
2023,45(16): 173-176 收稿日期：2023-4-19
DOI：10.3404/j.issn.1672-7649.2023.16.037
分类号：U644.1
作者简介：王晓晴(1992-),女,硕士,研究方向为航标管理
参考文献：
[1] 叶昊, 孙剑桥, 黄焱. 破冰型大型航标船线型开发设计及破冰阻力评估[J]. 船舶工程, 2020, 42(9): 1–5
[2] 宋忠浩, 谷雨, 陈旭, 等. 基于加权策略的高分辨率遥感图像目标检测[J]. 计算机工程与应用, 2021, 57(13): 199–206
[3] 周春辉, 赵俊男, 甘浪雄, 等. 潮流场作用下的航标漂移计算方法研究[J]. 安全与环境学报, 2021, 21(1): 217–223
[4] 倪汉杰, 初秀民, 张彬鹏, 等. 基于改进Cascade-RCNN的内河航标检测算法[J]. 中国航海, 2022, 45(3): 99–105
[5] 余伟, 尤红建, 胡玉新, 等. 基于多尺度双邻域显著性的高分四号遥感图像运动船舶检测方法[J]. 电子与信息学报, 2023, 45(01): 282–290
[6] 宋志娜, 眭海刚, 李永成. 高分辨率可见光遥感图像舰船目标检测综述[J]. 武汉大学学报(信息科学版), 2021, 46(11): 1703–1715
[7] 于野, 艾华, 贺小军, 等. A-FPN算法及其在遥感图像船舶检测中的应用[J]. 遥感学报, 2020, 24(2): 107–115
[8] 丁国绅, 乔延利, 易维宁, 等. 基于光谱图像空间的改进SIFT特征提取与匹配[J]. 北京理工大学学报, 2022, 42(2): 192–199
