Visual Inspection of Storm-Water Pipe Systems using Deep Convolutional Neural Networks Ruwan Tennakoon, Reza Hoseinnezhad, Huu Tran and Alireza Bab-Hadiashar School of Engineering, RMIT University, Melbourne, Australia Keywords: Storm-Water Pipe Inspection, Automated Infrastructure Inspection, Deep Convolutional Neural Networks. Abstract: Condition monitoring of storm-water pipe systems are carried-out regularly using semi-automated proces- sors. Semi-automated inspection is time consuming, expensive and produces varying and relatively unreliable results due to operators fatigue and novicity. This paper propose an innovative method to automate the storm- water pipe inspection and condition assessment process which employs a computer vision algorithm based on deep-neural network architecture to classify the defect types automatically. With the proposed method, the operator only needs to guide the robot through each pipe and no longer needs to be an expert. The results obtained on a CCTV video dataset of storm-water pipes shows that the deep neural network architectures trained with data augmentation and transfer learning is capable of achieving high accuracies in identifying the defect types. 1 INTRODUCTION Condition monitoring of storm-water pipe systems are often carried-out to provide an understanding of the current status of the storm-water system, which enables the prediction of future deterioration of the pipes and facilitate investment planning. These infor- mation can also be used in allocating maintenance and repair resources efficiently. An on-site inspection with closed-circuit televi- sion (CCTV) is currently the most common and com- mercially available method for condition assessment of storm-water pipes. The typical inspection process can be described as follows. A certified technician guides a CCTV camera mounted on a robot that tra- vels inside a pipe segment. The technician must vi- sually detect the defects in the pipe segment by ob- serving the video feed. Once a defect is detected the technician manually rotates and zoom the camera to gain a better understanding of the defect and adds the information relating to that defect (i.e. defect type, defect parameters) to the video together with additi- onal information such as pipe diameter, location, in- spection date. The recorded video is then used for further analysis including discrete condition rating, deterioration modelling and planning (Tran et al., 2010). The above described CCTV inspection is conside- red semi-automated and is time consuming, expensive and produces varying and relatively unreliable results in some cases due to operators fatigue and novicity. In addition, training a professional technician to be able to classify all the defect types, estimate defect para- meters and conduct inspection is costly. Due to the above limitations of the manual inspection process, only around ten percent of the storm-water pipe sy- stem in Melbourne, Australia can be inspected given limited budget. Increasing the portion of the inspected pipes would increase the reliability of the network as well as improve the resource allocation and planning processes. In this paper, we propose an innovative method to automate the defect detection and condition asses- sment within the pipe inspection process. With the proposed method, the operator only needs to guide the robot through each pipe and no longer needs to be an expert in piping. A computer vision algorithm ba- sed on deep-neural network architecture is designed to classify the defect types automatically. The block- diagram of the overall process is shown in Figure 1. In the proposed system, the technician still needs to drive the robot through the pipe and record a clear video of all the internal conditions of the pipe. The video is then fed to the model and the model will go through the video frame by frame to detects the un- derlying defects in each frame. After successfully de- tecting a defect, the system extracts those frames with defects and classify the defect type and extract de- Tennakoon, R., Hoseinnezhad, R., Tran, H. and Bab-Hadiashar, A. Visual Inspection of Storm-Water Pipe Systems using Deep Convolutional Neural Networks. DOI: 10.5220/0006851001350140 In Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2018) - Volume 1, pages 135-140 ISBN: 978-989-758-321-6 Copyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved 135