船舶吃水深度的机器视觉检测

张望; 李瑛; 许文海

doi:10.3788/OPE.20162413.0649

您当前的位置：

首页 >

文章列表页 >

船舶吃水深度的机器视觉检测

更新时间：2020-08-13

- 船舶吃水深度的机器视觉检测
- Machine visual measurement of ship draft
- 光学精密工程 2016年24卷第10s期页码：649-656
- 作者机构：
  
  大连海事大学信息科学技术学院,辽宁大连,中国,116026
- 作者简介：
- 基金信息：
  
  国家科技支撑计划课题资助项目（No.2014BAB12B03）();交通运输部建设科技项目（No.2013328225080）();中央高校基本科研业务费专项资金资助项
- DOI：10.3788/OPE.20162413.0649
  中图分类号： TP242.6;TP391.4
- 收稿日期：2016-04-15，
  
  修回日期：2016-06-05，
  
  纸质出版日期：2016-11-14
- 稿件说明：
移动端阅览
张望, 李瑛, 许文海. 船舶吃水深度的机器视觉检测[J]. 光学精密工程, 2016,24(10s): 649-656

ZHANG Wang, LI Ying, XU Wen-hai. Machine visual measurement of ship draft[J]. Editorial Office of Optics and Precision Engineering, 2016,24(10s): 649-656
张望, 李瑛, 许文海. 船舶吃水深度的机器视觉检测[J]. 光学精密工程, 2016,24(10s): 649-656 DOI： 10.3788/OPE.20162413.0649.

ZHANG Wang, LI Ying, XU Wen-hai. Machine visual measurement of ship draft[J]. Editorial Office of Optics and Precision Engineering, 2016,24(10s): 649-656 DOI： 10.3788/OPE.20162413.0649.

摘要

为了克服人工观测法中风浪及主观因素的不利影响，提出了以图像采集和分析为核心的船舶吃水深度检测方法。设计实现了以爬壁机器人为载体携带网络摄像机的水尺图像采集的系统，该系统能在平板电脑的控制下游走于复杂面型的船侧板完成水尺拍摄，且可连续采集涵盖多个波浪周期的高清图像（1600 pixel1200 pixel）。基于形态学和神经网络算法对图像中的水尺字符进行预处理和判别，有效提高了6、8、9几个相似字符的区分度。同时基于彩色图像分割算法对图像中的吃水线进行识别，通过对比吃水线在数值化水尺上的相对位置来确定船舶吃水深度，成功消除了波浪浸润所导致的假水线的干扰，从而实现了吃水线位置的自动判定。实验表明，该方法的最终识别精度可达1 mm，明显高于人工目测法所能达到的5 mm。此外，还特别利用现场测量数据对比证明了综合运用多幅图像数据来降低风浪干扰的必要。

Abstract

A measurement method of ship draft based on image capture and analysis is put forward to overcome adverse effect of storm and subjective factors in manual observation method. Water gauge image capture system by taking wall-climbing robot as carrier with internet protocol camera. The system can complete water gauge photographing by going across side plate with complex surface under the control of panel personal computer. High-definition image with several wave periods can be collected successively(1600 pixel1200 pixel). Pre-treatment and distinction to water-gauge character is implemented in image based on morphology and neural network algorithm

which effectively improves distinction degree of several similar characters:"6"

"8" and "9". At the same time

it can distinguish waterline in image by color image segmentation algorithm. Ship draft can be confirmed by comparing relative location of waterline on quantization water gauge and thus successfully eliminate interference of false waterline caused by wave infiltration and realize self-motion determination of location of waterline. Experiment shows that final distinguishing accuracy of this method can reach 1 mm

which is obviously higher than 5 mm that can be reached by artificial visual observation method. Besides

the necessity to reduce storm interference through applying comprehensively multiple image data is proved by making use of data comparison of field measurement.

关键词

Keywords

references

刘春雷, 张秀凤, 孙霄峰, 等. 基于加密型值表的改进水尺计重方法[J]. 交通运输工程学报, 2014, 14(3):58-64. LIU CH L, ZHANG X F, SUN X F,et al.. Improved draft survey method based on densified table of offsets[J]. Journal of Traffic and Transportation Engineering, 2014, 14(3):58-64.(in Chinese)

李洪星, 包彦夫, 徐兆阳. 水尺计重风险评价研究[J]. 检验检疫学刊, 2012, 22(4):4-7. LI H X, BAO Y F, XU ZH Y. The research on the risk evaluation and management system for draft survey[J].Journal of Inspection and Quarantine, 2012, 22(4):4-7.(in Chinese)

RENATE I, IRENA J, ROBERT M. Determining weight of cargo onboard ship by means of optical fibre technology draft reading[J].Promet-Traffic & Transportation, 2011, 23(6):421-429.

郭秀艳. 船舶水尺吃水值检测方法研究[D]. 大连:大连海事大学信息科学技术学院, 2014. GUO X Y. Research on detection method of ship draft [D]. Dalian:Information Science and Technology College of Dalian Maritime University, 2014.(in Chinese)

焦宇, 康与涛, 尹小贝, 等. 港口交通资源承载力预测预警模型[J]. 交通运输工程学报, 2012, 12(2):84-92. JIAO Y, KANG Y T, YIN X B,et al.. Forecasting and early-warning model of port traffic resource carrying capacity[J]. Journal of Traffic and Transportation Engineering, 2012, 12(2):84-92.(in Chinese)

GU H W, ZHANG W, XU W H, et al.. Digital measurement system for ship draft survey[J]. Applied Mechanics and Materials, 2013, 333-335:312-316.

KOLHALKAR N R, PATIL S M. Wall climbing robots:a review[J].International Journal of Engineering and Innovative Technology, 2012, 1(5):227-229.

吴善强, 陈晓东, 李满天, 等. 爬壁机器人的力学分析与实验[J]. 光学精密工程, 2008, 16(3):478-483. WU SH Q, CHEN X D, LI M T,et al.. Dynamic pressure analysis and experimental research of a wall-climbing robot[J]. Opt. Precision Eng., 2008, 16(3):478-483. (in Chinese)

SALMAN H, TARIQ S, ENER S. Parameter analysis and design framework for magnetic adhesion wall climbing wheeled robot[J].International Journal of Intelligent Systems Technologies and Applications, 2012, 11(1-2):102-116.

MAHMOUND T, CARLOS V,LINO M,et al.. OmniClimbers:Omni-directional magnetic wheeled climbing robots for inspection of ferromagnetic structures[J]. Robotics and Autonomous Systems, 2013, 61(9):997-1007.

吴伟,张康康. 基于智能算法的轮式移动机器人控制系统优化设计[J]. 电气工程学报, 2015, 10(12):21-26. WU W, ZHANG K K. Optimization design of wheeled mobile robot control system based on intelligent algorithm[J]. Journal of Electrical Engineering, 2015, 10(12):21-26.(in Chinese)

王跃勇,于海业,刘媛媛. 基于形态学图像检测的机械手移栽穴苗识别技术[J]. 光学精密工程, 2016, 24(3):651-658. WANG Y Y, YU H Y, LIU Y Y. Recognition of seedlings in mechanical transplanting processing by Morphological image detection[J]. Opt. Precision Eng., 2016, 24(3):651-658. (in Chinese)

冉鑫,彭将辉. 基于图像处理的船舶水尺刻度识别[J]. 上海海事大学学报, 2012, 33(2):6-9. RAN X, PENG J H. Ship draft mark recognition based on image processing[J]. Journal of Shanghai Maritime University, 2012, 33(2):6-9.(in Chinese)

KIM I J, XIE X H. Handwritten Hangul recognition using deep convolutional neural networks[J]. International Journal on Document Analysis and Recognition, 2015, 8(1):1-13.

杨钊, 陶大鹏, 张树业, 等. 大数据下的基于深度神经网的相似汉字识别[J]. 通信学报, 2014, 35(9):184-189. YANG ZH, TAO D P, ZHANG SH Y,et al.. Similar handwritten Chinese character recognition based on deep neural networks with big data[J]. Journal on Communications, 2014, 35(9):184-189. (in Chinese)

师文, 朱学芳, 朱光. 基于形态学的MRI图像自适应边缘检测算法[J]. 仪器仪表学报, 2013, 34(2):408-414. SHI W, ZHU X F, ZHU G. Adaptive edge detection algorithm of MRI image based on morphology[J].Chinese Journal of Scientific and Instrument, 2013, 34(2):408-414.(in Chinese)

余金栋, 张宪民. 用于线纹显微图像的边缘检测算法[J]. 光学精密工程, 2015, 23(1):271-281. YU J D, ZHANG X M. Edge detection algorithm for lines on microscopic image[J]. Opt. Precision Eng., 2015, 23(1):271-281. (in Chinese)

RAN X, SHI C J, CHEN J B,et al.. Draft line detection based on image processing for ship draft survey[C]. Proceeding of the 20112nd International Congress CACS, Berlin, Germany:Springer Berlin Heidelberg, 2011:39-44.

浏览量

721

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于圆卷积神经网络的粘连导电粒子检测

电力巡检中的偏振图像特征融合

基于神经网络的全斯托克斯光电探测器

基于机器视觉的透明软管内微量液体体积测量

融合多尺度特征的蜗杆表面缺陷检测