A defect classification methodology for sewer image sets with convolutional neural networks (original) (raw)
Related papers
A deep learning-based framework for an automated defect detection system for sewer pipes
Automation in Construction, 2020
The municipal drainage system is a key component of every modern city's infrastructure. However, as the drainage system ages its pipes gradually deteriorate at rates that vary based on the conditions of utilisation (i.e., intrinsic conditions) and other extrinsic factors such as the presence of trees with deep roots or the traffic load above the sewer lines, which collectively can impact the structural integrity of the pipes. As a result, regular monitoring of the drainage system is extremely important since replacement is not only costly, but, more importantly, can disturb the daily routines of citizens. In this respect, closed-circuit television (CCTV) inspection has been widely accepted as an effective inspection technology for buried infrastructure. Since sewer pipes can run for thousands of kilometers underground, cities collect massive amounts of CCTV video footage, the assessment of which is time-consuming and may require a large team of trained technologists. A framework is proposed to realize the development of a real-time automated defect detection system that takes advantage of a deep-learning algorithm. The framework focuses on streamlining the information and data flow, proposing patterns of input and output data processing. With the development of deep learning techniques, a state-of-theart convolutional neural network (CNN) based object detector, namely YOLOv3 network, has been employed in this research. This algorithm is known to be very efficient in the field of object detection from the perspective of processing speed and accuracy. The model used in this research has been trained with a data set of 4056 samples that contains six types of defects (i.e., broken, hole, deposits, crack, fracture, and root) and one type of construction feature (tap). The performance of the model is validated with a mean average precision (mAP) of 85.37%. The proposed output of the system includes labeled CCTV videos, frames that contain defects, and associated defect information. The labeled video can serve as the benchmark for assessment technologists while the multiple output frames provide an overview of the condition of the sewer pipe.
A Neural Network-Based Application for Automated Defect Detection for Sewer Pipes
2019
Manual defect identification and classification for sewer pipes using footage from closedcircuit television (CCTV) monitoring is generally time-consuming and can have varying degrees of accuracy depending on the expertise of the technologist conducting the analysis. In order to address this issue, automation is proposed as an alternative to human visual inspection and consists of extracting still frames from collected videos, examining whether these frames include defects, and finally classifying these defects into different types (e.g., cracks or fractures). A classifier based on a new convolutional neural network, called You only look once (YOLO), is proposed in this paper which consists of four parts: (1) extracting the colour frames including defects from the video; (2) transferring information in the selected frames in order to highlight the part of the image containing the defect; (3) using the training images with the corresponding information as inputs to generate a classifi...
Obstruction Level Detection of Sewers Videos Using Convolutional Neural Networks
2021
Worldwide, sewer networks are designed to transport wastewater to a centralized treatment plant to be treated and returned to the environment. This is a critical process for preventing waterborne illnesses, providing safe drinking water and enhancing general sanitation in society. To keep a perfectly operational sewer network several inspections are manually performed by a Closed-Circuit Television system to report the obstruction level which may trigger a cleaning operative. In this work, we design a methodology to train a Convolutional Neural Network (CNN) for identifying the level of obstruction in pipes. We gathered a database of videos to generate useful frames to fed into the model. Our resulting classifier obtains deployment ready performances. To validate the consistency of the approach and its industrial applicability, we integrate the Layer-wise Relevance Propagation (LPR) algorithm, which endows a further understanding of the neural network behavior. The proposed system provides higher speed, accuracy, and consistency in the sewer process examination.
2003
Convolutional neural networks (CNNs) impose con- straints on the weights, and the connectivity of a stan- dard neural network, providing a framework well suited to the processing of spatially or temporally distributed data. Although CNNs have been applied to face and character recognition, they have still received relatively little atten- tion. The present paper applies the CNN architecture to an artificial test problem and to an application in robot vision. Autonomous sewer robots must navigate independently the sewer pipe system using information from sensors. One re- quired component is robust detection of pipe joints and in- lets using data from the omnidirectional sensor. A simple CNN is shown to robustly classify 32x32 pixel normalized video frame data on a limited validation set. The study in- dicates that machine learning methods for robot vision are feasible in terms of classification accuracy and online im- plementation.
Automated sewer inspection using image processing and a neural classifier
International Joint Conference on Neural Networks (IJCNN 02), 2002
The focus of the research presented here is on the automated assessment of sewer pipe conditions using a laserbased sensor. The proposed method involves image and data processing algorithms categorising signals acquired from the internal pipe surface. Fault identification is carried out using a neural network. Experimental results are presented.