No abstract

Sewers must be regularly inspected to prioritise effective maintenance, which can be an expensive and time-consuming process. This paper presents a methodology to automatically identify the type of a detected fault using raw closed circuit television (CCTV) footage. The procedure calculates the GIST descriptor of a video frame containing a fault before applying a collection of random forest classifiers to identify the fault's type. Order oblivious filtering is used to further improve the methodology's performance on continuous footage. The technology, including various classifier architectures, has been validated and demonstrated on CCTV footage collected by Wessex Water. The methodology achieved a peak accuracy of 73% when applied to well-represented fault types, showing promise for future application in the water industry.

No abstract

This work presents a methodology for automatic detection of structural faults in sewers from CCTV footage, which has been improved by combining the outputs of different machine learning techniques. The predictions of support vector machine and random forest classifiers are combined using three distinct techniques: 'both', 'most likely' and 'stacking'. Each technique is tested on CCTV data taken from real surveys covering a range of pipes at locations in the south-west of the UK. The best tested technique, stacking, offers a 5% increase in accuracy for minimal impact in efficiency, proving useful for future development and implementation of the fault detection methodology.

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.