面向无人艇雷达图像的连通区域标记改进算法

潘选任; 王冬姣; 叶家玮

doi:10.11993/j.issn.2096-3920.2022.01.010

面向无人艇雷达图像的连通区域标记改进算法

doi: 10.11993/j.issn.2096-3920.2022.01.010

华南理工大学土木与交通学院, 广东广州, 510640

基金项目: 广东省科技项目(2015B010919006).

详细信息

作者简介:
潘选任(1995-), 男, 在读硕士, 主要研究方向为新型船舶与海洋结构物制造.

中图分类号: U674.91 U665.22
计量
- 文章访问数: 37
- HTML全文浏览量: 3
- PDF下载量: 15
- 被引次数: 0
出版历程
- 收稿日期: 2021-01-18
- 修回日期: 2021-03-19
- 刊出日期: 2022-02-28

Improved Algorithm of Connected Component Labeling for Unmanned Surface Vehicle Radar Images

College of Civil and Transportation Engineering, South China University of Technology, Guangzhou 510640, China

摘要

摘要: 搭载雷达的无人艇在水域中航行时, 通过雷达扫描水域附近的环境以识别无人艇周围的障碍物, 为了区分雷达图像中的障碍物, 通常采用连通区域标记算法对不同障碍物进行标记。由于杂波对雷达成像的干扰, 造成雷达图像中像素点增加, 使用常见的算法处理图像时效果不佳, 为此, 提出一种改进算法, 在常见算法的基础上增加去除杂波像素点的功能, 并标记出图像中的最大障碍物。经过实验分析后可知, 相比于改进前的算法, 改进后的算法减少了标记的区域数量, 处理后的雷达图像更加平滑, 便于无人艇对最大障碍物进行预警以及采取合理的避碰措施。
- 无人艇 /
- 雷达图像 /
- 障碍物 /
- 连通区域标记算法
Abstract: When an unmanned surface vehicle(USV) equipped with a boat-borne radar navigates the water, the radar scans the environment near the water, and the radar image is used to identify the obstacles around the USV. To distinguish different obstacles, a connected component labeling algorithm is used to mark different obstacles in the radar image. Owing to the interference from clutter on radar imaging, the pixels in the radar image increase; thus, the results obtained from traditional algorithms to process the image are inadequate. Therefore, an improved algorithm is proposed to improve the function of removing the clutter pixels based on conventional algorithms and mark the biggest obstacle in the image. Compared with the traditional algorithm, the improved algorithm reduced the number of marked areas, and the processed radar images are smoother, which is convenient for the USV to detect the largest obstacle early such that avoidance maneuvers can be performed.
- unmanned surface vehicle(USV) /
- radar image /
- obstacle /
- connected component labeling algorithm

HTML全文

参考文献(14)

[1]	郑烈心. 水面无人艇建模与运动控制系统设计[D]. 广州: 华南理工大学, 2016.
[2]	汪劲希, 燕肇一, 彭真明. 复杂背景下海天线的连通域检测法[J]. 舰船科学技术, 2016(8): 108-112. Wang Jin-xi, Yan Zhao-yi, Peng Zhen-ming. A Sea-Sky- Line Detection Algorithm Based on the Method of Connected Area Detection Under Complicated Background[J]. Ship Science and Technology, 2016, 38(8): 108-112.
[3]	田守东. 基于雷达图像的目标检测技术研究[D]. 哈尔滨: 哈尔滨工程大学, 2010.
[4]	王凯, 黄山, 赵瑜, 等. 面向图像目标提取的改进连通域标记算法[J]. 计算机工程与设计, 2014, 35(7): 2438- 2441. Wang Kai, Huang Shan, Zhao Yu, et al. Improved Algorithm of Connected Component Labeling for Image Targets Extraction[J]. Computer Engineering and Design, 2014, 35(7): 2438-2441.
[5]	谢宜壮, 谭许彬, 陈禾. 一种新的连通域标记算法[J]. 北京理工大学学报, 2012, 32(12): 1273-1278. Xie Yi-zhuang, Tan Xu-bin, Chen He. A New Algorithm for Connected Components Labeling[J]. Transaction of Beijing Institute of Technology, 2012, 32(12): 1273-1278.
[6]	左文明. 连通区域提取算法研究[J]. 计算机应用与软件, 2006, 23(1): 97-98. Zuo Wen-ming. Study on Connected Regions Extraction[J]. Computer Applications and Software, 2006, 23(1): 97-98.
[7]	左敏, 曾广平, 涂序彦, 等. 基于等价对的图像连通域标记算法[J]. 计算机仿真, 2011, 28(1): 14-16, 50. Zuo Min, Zeng Guang-ping, Tu Xu-yan, et al. A Connected Domain Labeling Algorithm Based on Equivalence Pair in Binary Image[J]. Computer Simulation, 2011, 28 (1): 14-16, 50.
[8]	张云哲, 赵海, 宋纯贺, 等. 一种新的连通区域标记算法[J]. 计算机应用研究, 2010, 27(11): 4335-4337, 4340. Zhang Yun-zhe, Zhao Hai, Song Chun-he, et al. New Me- thod for Component-Labeling in Binary Image[J]. Application Research of Computers, 2010, 27(11): 4335-4337, 4340.
[9]	Rosenfeld A. Sequential Operations in Digital Picture Processing[J]. Journal of the ACM, 1996, 13(4): 471-494.
[10]	沈夏炯, 段晓宇, 原万里, 等. 基于连通区域标记算法的圆检测算法的研究[J]. 计算机工程与应用, 2018, 54 (21): 95-98. Shen Xia-jiong, Duan Xiao-yu, Yuan Wan-li, et al. Research on Circle Detection Algorithm Based on Connected Region Labeling Algorithm[J]. Computer Engineering and Applications, 2018, 54(21): 95-98.
[11]	覃方涛, 房斌. GPU加速的二值图连通域标记并行算法[J]. 计算机应用, 2010, 30(10): 2774-2776. Qin Fang-tao, Fang Bin. GPU Accelerated Parallel Labeling Algorithm of Connected-Domains in Binary Images [J]. Journal Computer Applications, 2010, 30(10): 2774- 2776.
[12]	张国和, 徐快, 段国栋, 等. 一种适于硬件实现的快速连通域标记算法[J]. 西安交通大学学报, 2018, 52(6): 95-101. Zhang Guo-he, Xu Kuai, Duan Guo-dong, et al. A Fast Labeling Algorithm of Connected Components Applicable for Hardware Implementation[J]. Journal of Xi’an Jiaotong University, 2018, 52(8): 95-101.
[13]	Robert L. OpenCV 2 Computer Vision Application Programming Cookbook[M]. Birmingham: Packt Publishing, 2011.
[14]	雷建锋, 汪伟. 基于OpenCV的图像阈值分割研究与实现[J]. 现代电子技术, 2013, 36(24): 73-76. Lei Jian-feng, Wang Wei. Research and Implementa- tion of Image Threshold Segmentation Based on OpenCV[J]. Modern Electronics Technique, 2013, 36(24): 73-76.