Author(s): Joshua Myrans; Zoran Kapelan; Richard Everson

Linked Author(s):

Keywords: Utomatic; Fault Identification; Machine Learning; Random Forest; Sewers

Abstract: Water companies all over the world regularly perform inspections of their sewer networks. The data collected this way is then analysed by human technician which is time consuming and expensive. Previous work by the authors has developed methodology that can automatically detect faults in sewer pipes using standard CCTV footage. This paper presents a methodology to automatically identify types of detected faults aiming to further improve the efficiency and accuracy (i. e. consistency) of surveys. The methodology calculates a feature descriptor for individual frames of CCTV footage, before predicting the contents using a multi-class Random Forest classifier. Demonstrated on a comprehensive library of frames extracted from real-life CCTV footage of a UK water company, the methodology correctly identified the fault type in 71% of frames. Most common fault types were included in this experiment, covering a wide range of pipe sizes and materials, including vitrified clay, PVC and brick. Overall, this preliminary work shows promise for application in industry, proving an effective tool for analysing CCTV surveys.

DOI:

Year: 2018