基于视频跟踪的水下裂缝缺陷智能标注系统  被引量:3

Underwater crack defect intelligent annotation system based on video tracking

在线阅读下载全文

作  者:谢迎娟 吴宁馨 张卓 XIE Yingjuan;WU Ningxin;ZHANG Zhuo(College of Internet of Things Engineering,Hohai University,Changzhou 213022,China;Jiangsu Key Laboratory of Power Transmission&Distribution Equipment Technology,Changzhou 213022,China)

机构地区:[1]河海大学物联网工程学院,江苏常州213022 [2]江苏省输配电装备技术重点实验室,江苏常州213022

出  处:《现代电子技术》2020年第12期155-160,共6页Modern Electronics Technique

基  金:国家重点研发计划(2016YFC0401606);国家自然科学基金(61701169);国家自然科学基金(61671202);国家重点研发计划(2018YFC0407101)。

摘  要:当前水下裂缝缺陷检测中存在误检率高、漏检率高、实时性不强等问题,需要大量准确地标注数据集对识别模型进行训练。针对大量标注数据集的需求问题,提出一种目标智能标注系统,利用基于通道和空间可靠性理论改进的核相关滤波跟踪算法(CSR-KCF),对水下裂缝进行目标跟踪,结合标注系统功能需求,展开对该系统的设计与实现。实验结果表示,提出的目标智能标注系统符合设计需求,能够实现对水下裂缝缺陷准确、快速、可靠的智能标注。At present,there are some problems in the detection of underwater crack defects,such as high error detection rate,high missed detection rate and weak real-time performance,which requires a large number of accurate annotated datasets to train the recognition model. In allusion to the requirement of a large number of annotated datasets,a target intelligent annotation system is proposed. The target tracking of underwater crack is performed by means of the improved kernel correlation filter tracking algorithm based on channel and spatial reliability theory(CSR-KCF),and the design and implementation of the system are carried out according to the function requirements of the annotation system. The experimental results show that the intelligent annotation system proposed in this paper conforms to the design requirements and can achieve accurate,fast and reliable intelligent annotation of underwater crack defects.

关 键 词:水下裂缝缺陷 智能标注 模型训练 目标跟踪 系统设计 仿真实验 

分 类 号:TN915.5-34[电子电信—通信与信息系统]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象