首页|基于最近点迭代的水下三维声图增强算法

基于最近点迭代的水下三维声图增强算法

扫码查看
由于复杂的水下环境和声呐硬件的限制,三维成像声呐(3DIS)图像质量较差,表现为图像目标表面点的稀疏和缺失.为了提高图像质量,我们提出了一种基于配准和融合的目标增强方法.迭代最邻近点(ICP)算法是经典的点云配准算法,是一种用于配准2个或多个点云数据集的迭代优化方法.ICP方法可直接用于点云数据,具有实施简单、迭代速度快的优点.该算法通过对齐和融合的方法叠加多帧点云来增强点云,可以改善目标点云稀疏和缺失的问题.实验结果表明,我们提出的增强方法能有效增强声呐图像,提高三维声呐图像的质量和可理解性.
An Image Enhancement of Underwater Three-dimensional Sonar Image Based on ICP
The 3-D imaging sonar(3DIS)image quality is poor,manifested as sparse and missing of target surface points,owing to complex underwater environment and hardware limitation of sonar.To improve the quality of the image,we propose a target enhance-ment method based on registration and merge.The ICP(Iterative Closet Point)algorithm is a classical point cloud alignment algo-rithm,whose is an iterative optimization method for aligning two or more point cloud datasets.The ICP method can be used directly with point cloud data and has the advantage of being simple to implement and fast to iterate.The algorithm in the paper enhances the point cloud by superimposing multi-frame point clouds by means of alignment and fusion,which can improve the problem of sparse and missing target point clouds.Experimental results demonstrate that our proposed enhancement method can effectively enhance the object result,improve the quality and understandability of the 3DIS image.

image enhancement3D imaging sonarimage registrationpoint-cloudICP

曾腾、王朋、黄海宁、王冠群、张武

展开 >

中国科学院先进水下信息技术重点实验室 北京 100190

中国科学院声学研究所 水下信息技术实验室 北京 100190

图像增强 三维成像声呐 图像拼接 点云 最近点迭代

2024

网络新媒体技术
中国科学院声学研究所

网络新媒体技术

CSTPCD
影响因子:0.208
ISSN:2095-347X
年,卷(期):2024.13(3)
  • 4