[1]顾嘉陆,申燚,姜 烽,等.基于边缘重心模板的水中机器鱼阈值分割算法研究[J].机械与电子,2018,(06):25-28.
　GU Jialu,SHEN Yi,JIANG Feng,et al.Research on Threshold Segmentation Algorithm of Underwater Robotic Fish Based on Edge Gravity Center Template[J].Machinery & Electronics,2018,(06):25-28.
点击复制

基于边缘重心模板的水中机器鱼阈值分割算法研究()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2018年06期
页码:
25-28
栏目:
设计与研究
出版日期:
2018-06-24

文章信息/Info

Title:
Research on Threshold Segmentation Algorithm of Underwater Robotic Fish Based on Edge Gravity Center Template
文章编号:
1001-2257（2018）06-0025-04
作者:
顾嘉陆1; 申燚1; 2; 姜 烽1; 陈柄钱1; 袁明新1; 2
1.江苏科技大学张家港校区 机电与工程学院,张家港 2156002.张家港香樟树众创空间,江苏 张家港 215600)
Author(s):
GU Jialu1;  SHEN Yi1; 2;  JIANG Feng1;  CHEN Binqian1;  YUAN Mingxin1; 2
(1. School of Mechanical and Power Engineering, Zhangjiagang Campus, Jiangsu University of Science and Technology, Zhangjiagang 215600, China; 2. Zhangjiagang Camphor Tree Makerspace,?Zhangjiagang?215600, China)
关键词:
HSV颜色空间; 边缘重心模板; 阈值分割; 机器鱼
Keywords:
HSV color space;  edge center of gravity template;  threshold segmentation;  robotic fish
分类号:
TP391.41
文献标志码:
A
摘要:
为了实现不同光照条件下水中机器鱼的准确视觉分割，提出了一种基于边缘重心模板的阈值分割新算法。RGB颜色空间转化至HSV颜色空间，利用图像H分量直方图来确定机器鱼像素H分量值的极差；然后基于Sobel算子进行边缘提取来获取边缘重心坐标，并计算以边缘重心为中心的n×n模板的H分量平均值；最后利用机器鱼像素H分量值的极差和平均值来确定边缘重心模板阈值，从而实现机器鱼的阈值分割。3种光照环境的实验结果表明，与其他算法相比，基于边缘重心模板的阈值分割法不仅保证了平均96%的高检出率，其平均误检率也控制在0.4%，从而验证了此算法的有效性。
Abstract:
To achieve accurate visual segmentation of an underwater robotic fish in different lighting conditions, this paper proposes a novel segmentation algorithm based on edge gravity center template.?Firstly, the image of robotic fish was converted from RGB color space to HSV color space, and the H-component histogram was used to determine the extreme difference of the H component value of the robotic fish. Then, the edge center coordinates were obtained through the Sobel operator-based edge extraction, and the average H-component value of n×n edge gravity center template was calculated.?Finally, the extreme difference and average value?of H-component were used to determine the threshold value of edge gravity center template, and thus the robotic fish was segmented. The experimental results of three kinds of lighting conditions show that, compared with other algorithms, the proposed algorithm not only guarantees the high average detection rate of 96%, but also controls the average false detection rate at 0.4%

参考文献/References:

[1]Marrazza G, Ravalli A, Rossi C. Fish robot based on chemical sensors for water monitoring [C]// Proceedings of 19th AISEM National Conference on Sensors and Microsystems, 2017: 59-64.
[2]Cui Z, Jiang H Z. Design and implementation of thunniform robotic fish with variable body stiffness[J]. International Journal of Robotics and Automation, 2017,32(2):109-116.
[3]刘敦浩,张彦铎,李迅,等.动态环境下自适应阈值分割方法[J].计算机应用,2016,36(增刊2):152-156.
[4]雷俊,王立辉,何芸倩,等.适用于机器人视觉的图像分割方法[J].系统工程与电子技术,2017,39(7):1653-1659.
[5]Yuan M X,Zhao R,Hua X B,et al.Research on visual segmentation and localization of multi-robots under different lighting conditions[J].Journal of Systems and Control Engineering, 2015,229(9):838-850.
[6]巨志勇, 苏春美.非均匀光照下的车牌图像分割算法[J].信息技术,2015(10):34-37.
[7]杨康叶,邬春学.基于RGB模型颜色相似性的彩色图像分割[J].计算机系统应用,2013,22(3):128-131,160.
[8]沈志忠,王硕,曹志强,等.基于边缘检测的图像分割方法及其在机器鱼中的应用[J].机器人,2006,28(4):361-366.
[9]Sabzi S, Abbaspour-Gilandeh Y, Javadikia H.Machine vision system for the automatic segmentation of plants under different lighting conditions[J].Biosystems Engineering, 2017,161(9):157-173
[10]赵来刚，陈道炯.一种基于Sobel算子的新型边缘提取技术[J].机械与电子,2011(2):59-61.

备注/Memo

备注/Memo:
收稿日期：2018--03-03
基金项目：国家自然科学基金资助项目(61105071)；张家港香樟树众创空间项目(509914003);大学生本科创新项目(2018zjg06)

作者简介：龙迎春（1970—），男，湖南邵阳人，博士、副教授。研究方向为机电系统控制及智能化技术。




更新日期/Last Update: 2019-10-30