基于图像处理的水下海参识别和定位方法

张韫峰; 李 娟; 黎 明

doi:10.11993/j.issn.2096-3920.2021.01.016

基于图像处理的水下海参识别和定位方法

doi: 10.11993/j.issn.2096-3920.2021.01.016

张韫峰^1,2,
李娟²,
黎明¹

1.
中国海洋大学工程学院, 山东青岛, 266100
2.
青岛农业大学机电工程学院, 山东青岛, 266109

基金项目: 国家自然科学基金项目(32073029; 41674037); 山东省自然科学基金重点项目(ZR202010310016); 山东省研究生教育质量提升计划项目(SDYJG19134); 山东省大数据驱动的复杂系统安全控制技术重点实验室(筹)开放基金(SKDK 202002).

详细信息

作者简介:
张韫峰(1996-), 男, 在读硕士, 主要研究方向为智能检测与智能控制.

中图分类号: TP391.41 S979
计量
- 文章访问数: 221
- HTML全文浏览量: 23
- PDF下载量: 367
- 被引次数: 0
出版历程
- 收稿日期: 2020-01-07
- 修回日期: 2020-04-24
- 刊出日期: 2021-03-01

Underwater Sea Cucumber Identification and Localization Method Based on Image Processing

1.
College of Engineering, Ocean University of China, Qingdao 266100, China
2.
College of Mechanical and Electrical Engineering, Qingdao Agricultural University, Qingdao 266109, China

摘要

摘要: 为解决复杂环境下海参识别和定位的难题, 文章提出了一种基于图像处理的海参识别和定位算法。首先, 在图像预处理基础上设计基于模糊增强的融合RGB海参刺和海参主干突出特征算法, 以突出海参目标特征, 通过改进的图像分割方法提取海参轮廓, 利用链表法去伪边缘和形态学轮廓优化实现海参目标的识别。对海参目标的定位分为2种情况: 对形状规则的海参目标通过椭圆一次拟合来初步定位; 对形状不规则的海参目标通过提取海参目标方向特征进而设计基于最小外接矩形方向椭圆二次拟合算法来定位。仿真结果表明该算法可以有效识别和定位海参目标, 判断海参体积大小, 为海参可持续自动捕捞提供了一种有效方法。
- 海参 /
- 图像处理 /
- 识别定位 /
- 方向特征
Abstract: An image processing algorithm for sea cucumber identification and localization is proposed to solve the problem of sea cucumber identification and localization in complex environment. First, based on image preprocessing, a fuzzy enhanced fusion RGB sea cucumber thorn and sea cucumber trunk prominent feature algorithm is designed to highlight sea cucumber target features. The outline of a sea cucumber is extracted using an improved image segmentation method, and the linked list method is used to remove false edges and morphological outline optimization, which is necessary to identify the sea cucumber target. The localization of sea cucumber target can be divided into two cases: a sea cucumber target with a regular shape that is located by one-time ellipse fitting, and a sea cucumber target with an irregular shape that is located by extracting the target direction feature of the sea cucumber and designing a quadratic fitting algorithm based on the least external rectangle direction ellipse. Simulation results reveal that the algorithm can effectively identify and locate sea cucumber target, determine the volume of sea cucumber, and ultimately provide an effective method for sustainable and automatic fishing of sea cucumbers.
- sea cucumber /
- image processing /
- identification and localization /
- direction feature

HTML全文

参考文献(18)

[1]	房英春, 张慧, 陈曦. 海参资源及生物学特征[J]. 北京水产, 2017, 2(5): 25-27. Fang Ying-chun, Zhang Hui, Chen Xi. Resources and Bi-ological Characteristics of Sea Cucumber[J]. Beijing Aquatic Products, 2017, 2(5): 25-27.
[2]	王金龙. 海参市场总结报告[J]. 当代水产, 2017(1): 36-38. Wang Jin-long. Sea Cucumber Market Summary Report[J]. Modern Fisheries, 2017(1): 36-38.
[3]	卢昆, 刘慧迪, 包利民. “十三五”期间山东省海参养殖产量预测与发展前瞻[J]. 海洋开发与管理, 2018, 7(1): 94-100. Lu Kun, Liu Hui-di, Bao Li-min. Prediction and Development of Sea Cucumber Production in Shandong Province During the 13th Five Years Plan[J]. Ocean Development and Management, 2018, 7(1): 94-100.
[4]	唐旭东, 庞永杰, 张赫, 等. 基于单目视觉的水下机器人管道检测[J]. 机器人, 2010, 32(5): 592-600. Tang Xu-dong, Pang Yong-jie, Zhang He, et al. Underwater Pipeline Detection by AUV Based on Monocular Vision[J]. Robot, 2010, 32(5): 592-600.
[5]	曾文静, 徐玉如, 万磊, 等. 自主式水下机器人的光视觉管道探测跟踪系统[J]. 上海交通大学学报, 2012, 46 (2): 178-183, 189. Zeng Wen-jing, Xu Yu-ru, Wan Lei, et al. Robotics Vision Based System of Autonomous Underwater Vehicle for an Underwater Pipeline Tracker[J]. Journal of Shanghai Jiao tong University, 2012, 46(2): 178-183, 189.
[6]	Qiao X, Bao J H, Zhang H, et al. Underwater Image Quality Enhancement of Sea Cucumbers Based on Improved Histogram Equalization and Wavelet Transform[J]. Information Processing in Agriculture, 2017, 4(3): 206-213.
[7]	郭祥云, 王文胜, 刘亚辉, 等. 基于深度残差网络的水下海参自动识别研究[J]. 数学的实践与认识, 2019, 49 (13): 203-212. Guo Xiang-yun, Wang Wen-sheng, Liu Ya-hui, et al. Automatic Identification of Underwater Sea Cucumber Based on Depth Residual Network[J]. Practice and Understanding of Mathematics, 2019, 49(13): 203-212.
[8]	郭祥云, 胡敏, 王文胜, 等. 基于深度学习的非结构环境下海参实时识别算法[J]. 北京信息科技大学学报(自然科学版), 2019, 34(3): 27-31. Guo Xiang-yun, Hu Min, Wang Wen-sheng, et al. Real Time Recognition Algorithm of Sea Cucumber in Unstructured Environment Based on Deep Learning[J]. Journal of Beijing University of Information Technology(Natural Science Edition), 2019, 34(3): 27-31.
[9]	吴春阳. 基于卷积神经网络的水下海参目标检测系统设计与实现[D]. 哈尔滨: 哈尔滨工程大学, 2018.
[10]	Li J, Xu C, Jiang L, et al. Detection and Analysis of Behavior Trajectory for Sea Cucumbers Based on Deep Learning[J]. IEEE Access, 2020, 8: 18832-18840.
[11]	崔尚, 段志威, 李国平, 等. 基于Sobel改进算子的海参图像识别研究[J]. 电脑知识与技术, 2018, 14(22): 145-146. Cui Shang, Duan Zhi-wei, Li Guo-ping, et al. Sea Cucumber Image Recognition Based on Sobel Improved Operator[J]. Computer Knowledge and Technology, 2018, 14(22): 145-146.
[12]	皮志锋. 海参捕捞机器人技术研究[D]. 哈尔滨: 哈尔滨工程大学, 2017.
[13]	乔曦. 基于水下机器视觉的海参实时识别研究[D]. 北京: 中国农业大学, 2017.
[14]	李娟, 朱学岩, 葛凤丽, 等. 基于计算机视觉的水下海参识别方法研究[J]. 中国农机化学报, 2020, 41(7): 171-177. Li Juan, Zhu Xue-yan, Ge Feng-li, et al. Direction Ellipse Fitting of Sea Cucumber Contour Recognition Method of Underwater Sea Cucumber Based on Computer Vision[J]. China Agricultural Machinery Chemical Journal, 2020, 41(7): 171-177.
[15]	Qiao X, Bao J H, Zeng L H, et al. An Automatic Active Contour Method for Sea Cucumber Segmentation in Nat-ural Underwater Environments[J]. Computers and Electronics in Agriculture, 2017(135): 134-142.
[16]	郭传鑫, 李振波, 乔曦, 等. 基于融合显著图与Grab Cut算法的水下海参图像分割[J]. 农业机械学报, 2015, 46(S1): 147-152. Guo Chuan-xin, Li Zhen-bo, Qiao Xi, et al. Image Segmentation of Underwater Sea Cucumber Using Grab Cut with Saliency Map[J]. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(S1): 147-152.
[17]	刘吉伟, 魏鸿磊, 裴起潮, 等. 采用相关滤波的水下海参目标跟踪[J]. 智能系统学报, 2019, 14(3): 525-532. Liu Ji-wei, Wei Hong-lei, Pei Qi-chao, et al. Underwater Sea Cucumber Target Tracking Using Correlation Filtering[J]. Journal of Intelligent Systems, 2019, 14(3): 525-532.
[18]	彭丹妮. 海参自动捕捞中的目标跟踪技术研究[D]. 大连: 大连工业大学, 2017.