节点文献

基于单目视觉的水下机器人管道检测

Underwater Pipeline Detection by AUV Based on Monocular Vision

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 唐旭东庞永杰张赫曾文静李晔

【Author】 TANG Xudong,PANG Yongjie,ZHANG He,ZENG Wenjing,LI Ye (National Key Laboratory of Science and Technology on Autonomous Underwater Vehicle,Harbin Engineering University,Harbin 150001,China)

【机构】 哈尔滨工程大学水下机器人技术国防科技重点实验室

【摘要】 以单目CCD摄像机为视觉传感器,利用视觉系统测量方法获得水下管道的导航信息,并在此基础上建立了一个用于水下机器人的水下管道检测系统.按照数据结构的抽象程度,将系统中传递的数据信息分为由低至高4个层次,描述了各层次内容,详细介绍了水下机器人管道检测方法.为了提高系统的准确性和实时性,采用了动态窗口管道检测方法.在室内实验水池中,以某型号水下机器人为试验载体,进行了多次管道跟踪试验,验证了系统的可行性和有效性.

【Abstract】 Taking monocular CCD(charge coupled device) camera as a vision sensor,the navigation information of underwater pipelines can be acquired by vision-measuring method.On this basis,an underwater pipeline detection system for AUV(autonomous underwater vehicle) is constructed.According to the abstract degree of data structure,the data information transferred in this system can be divided into four hierarchies from low to high.Information in each hierarchy is described, and the underwater pipeline detection method for AUV is introduced in detail.In order to improve the accuracy and real-time performance of this system,the detection method based on dynamic window is applied.Finally,taking an AUV as carrier in indoor experimental pool,several underwater pipeline tracking experiments are carried out.The experiment results validate the feasibility and validity of this system.

【基金】 国家863计划资助项目(2008AA092301);国家自然科学基金资助项目(50909025/E091002);中国博士后科学基金资助项目(20080440838);黑龙江省博士后基金资助项目;哈尔滨工程大学基础研究基金资助项目(HEUFT08001,HEUFT08017);水下智能机器人技术国防科技重点实验室开放课题研究基金资助项目(2007001,2008003).
  • 【分类号】TP242
  • 【被引频次】42
  • 【下载频次】986
节点文献中: 

本文链接的文献网络图示:

本文的引文网络