摘要
作为地下空间信息测绘工作的一个重要部分,基于排水管道内部测绘信息的管道缺陷检测越来越受到人们的重视。CCTV技术是一种广泛使用的排水管道内部测绘与缺陷检测技术。近些年基于卷积神经网的人工智能技术在图像识别中取得了巨大成功,受此启发,提出了一种基于卷积神经网络的排水管道缺陷的检测方法,以提高CCTV视频中的管道缺陷检测的自动化和智能化。试验证明了该方法的有效性,其在缺陷识别的准确率和召回率及识别速度上均满足了排水管道缺陷智能检测的需要;同时该方法也已经在深圳市的排水管道检测中得到广泛的应用。
Sewer network is related to the public safety and environmental protection. The defect detection of sewer has received more attention. CCTV is a technology widely used in the sewer defect detection. Motivated by the success of the CNN( Convolutional Neural Network) in the image recognition,this paper proposes a CNN-based sewer defect detection to improve the intelligence and automation of the CCTV technology. Experimental results show that the proposed method is effective and the accuracy,recall and run-time meet the requirements of the sewer defect detection. Moreover,this method has been widely used in the city of Shenzhen.
作者
吕兵
刘玉贤
叶绍泽
闫臻
LV Bing;LIU Yuxian;YE Shaoze;YAN Zhen(Shenzhen Survey and Research Institute Co.,Ltd.,Shenzhen 518026,China)
出处
《测绘通报》
CSCD
北大核心
2019年第11期103-108,共6页
Bulletin of Surveying and Mapping
基金
国家自然科学基金(41571367)
