Diagnosis of sewer pipe defects on image recognition of multi-features and support vector machine in a southern Chinese city

2019, Volume 13, Issue 2

Abstract

Keywords

Related Research

Frontiers of Environmental Science & Engineering >> 2019, Volume 13, Issue 2 doi: 10.1007/s11783-019-1102-y

Diagnosis of sewer pipe defects on image recognition of multi-features and support vector machine in a southern Chinese city

¹. State Key Joint Laboratory of Environment Simulation and Pollution Control, School of Environment, Tsinghua University, Beijing 100084, China
². Thunip Corp., Ltd., 27F/Section C, S&T Building, Tsinghua S&T Park, Beijing 100084, China
³. China Water Environment Group. 10F, Campbell Building, 89th Jinbao Street, Beijing 101101, China

Available online: 2019-01-25

HTML0 PDF 14 Collect 0

Next Previous

Abstract

An image-recognition-based diagnosis system of pipe defect types was established.

1043 practical pipe images were gathered by CCTV robot in a southern Chinese city.

The overall accuracy of the system is 84% and the highest accuracy is 99.3%.

The accuracy shows positive correlation to the number of training samples.

Keywords

Sewer pipe defects ; Defect diagnosing ; Image recognition ; Multi-features extraction ; Support vector machine

Related Research