Multi-tier method using infrared photography and GPR to detect and locate water leaks

This paper presents newly developed method for detecting and locating leaks in water distribution networks utilizing two detection techniques; ground penetrating radar (GPR) and infrared photography (IR). The experimental work and field investigation were carried out over 2 years in three locations in City of Doha, Qatar to capture 115 IR image frames and 23 GPR image frames. Firstly, GPR technology is utilized to accurately define location of buried pipes. After locating these pipes, IR images are collected for simulated and actual leaks. The developed algorithm segments each image into leakage and non-leakage areas and the centroid of each leakage is calculated using Green's theorem. Subsequently, GPR images are introduced as a second layer and overlaid with IR images to compare pipes location with leak location. The method was successfully applied to detect simulated and actual leaks in summer and winter seasons with small margin of error (2.9–5.6%) in estimating leakage areas. When examining the investigated four operating conditions, it was found that the developed method can predict leaks in a more reliable way if the camera height is 2 m and the speed is 1.65 m/s in both simulated and actual leaks. The newly developed method is robust and can aid operators and city engineers in detecting and locating water leaks with high accuracy.     

Generative adversarial network for road damage detection

Machine learning can produce promising results when sufficient training data are available; however, infrastructure inspections typically do not provide sufficient training data for road damage. Given the differences in the environment, the type of road damage and the degree of its progress can vary from structure to structure. The use of generative models, such as a generative adversarial network (GAN) or a variational autoencoder, makes it possible to generate a pseudoimage that cannot be distinguished from a real one. Combining a progressive growing GAN along with Poisson blending artificially generates road damage images that can be used as new training data to improve the accuracy of road damage detection. The addition of a synthesized road damage image to the training data improves the F‐measure by 5% and 2% when the number of original images is small and relatively large, respectively. All of the results and the new Road Damage Dataset 2019 are publicly available ( https://github.com/sekilab/RoadDamageDetector ).     

Perturbation mapping of water leak in buried water pipes via laboratory validation experiments with high-frequency ground penetrating radar (GPR)

This paper studies the perturbation patterns of GPR images as a tool for water leakage detection in buried water pipes with laboratory experiments. Different perturbations patterns on GPR signals due to a water leak of metallic and PVC pipes buried in a sand box, were mapped and studied with controlled water injection and leak volume, as well as a fixed leak position in the pipes. These perturbation patterns of signal strength include the tale-tell signs of a central leak point and propagation of the radial wetting front vortex centered around the leak point at different injection times. These patterns, compared to the no-leak dry condition, were interpreted with the conventional principles of dielectric contrast and reflection coefficients, and the associated reflection and absorption mechanisms. It is believed that this set of data will serve as an image matching fingerprint to identify and map water leaks in the field.     

基于O-YOLOv3 的无人机森林火灾识别研究

为解决传统森林火灾检测误报率高、响应速度慢等问题,提出了以无人机作为探测平台,地面站作为火灾识别系统,实现森林火灾的自动探测、识别和定位。开发了六旋翼无人机平台,通过所搭载的红外摄像机和机载计算机获取森林火灾现场图像并实时传回地面。利用地面站对所接收到的火灾图像进行处理,实现对森林火场的在线监测。在森林火灾识别算法方面,提出了O_YOLOv3 算法,采用Darknet 框架进行网络训练,使用K_means 方法自动生成锚点,有效提高火灾识别精度与响应速度。将O_YOLOv3 算法与其他几种算法进行对比实验验证本文算法的有效性。实验结果表明：O_YOLOv3 火灾识别算法能够快速、精准识别森林火灾;所研制的基于O_YOLOv3 的无人机森林火灾探测系统能够用于实际森林火灾探测。     

Research on probing and predicting the diameter of an underground pipeline by GPR during an operation period

It is very important that the existing networks of underground pipelines be clearly surveyed when the underground space of an old urban area is rebuilt and expanded. The GPR method is always used to locate the embedded pipes; however, it is hard to determine their diameters, especially, when the underground pipe is full of a lossy medium (i.e., water, oil, or gas) during the operation period. First, this paper proposes a new method for probing and predicting the diameter of underground pipelines filled with lossy media based on GPR using the shape of a certain circle determined by the coordinates of three points on this circle. The operational procedure of this method is listed in detail. Secondly, this method is used to detect the diameters of underground pipelines in a model experiment and the project for the detection of a sewage pipe network in Yi’xing chemical industrial park. The measurement value is approximately consistent with the real value. Lastly, some factors influencing the accuracy of this method were comprehensively analysed by applying the finite difference time domain method (FDTD). These factors are the buried depth of the pipe, the detecting frequency of the GPR, the material of the pipe and the spacing of the measured points. The results showed that the proposed method has sufficient applicability and accuracy for practical engineering. These works demonstrate that the proposed method achieves good result.     

Concrete bridge surface damage detection using a single‐stage detector

Early and timely detection of surface damages is important for maintaining the functionality, reliability, and safety of concrete bridges. Recent advancement in convolution neural network has enabled the development of deep learning‐based visual inspection techniques for detecting multiple structural damages. However, most deep learning‐based techniques are built on two‐stage, proposal‐driven detectors using less complex image data, which could be restricted for practical applications and possible integration within intelligent autonomous inspection systems. In this study, a faster, simpler single‐stage detector is proposed based on a real‐time object detection technique, You Only Look Once (YOLOv3), for detecting multiple concrete bridge damages. A field inspection images dataset labeled with four types of concrete damages (crack, pop‐out, spalling, and exposed rebar) is used for training and testing of YOLOv3. To enhance the detection accuracy, the original YOLOv3 is further improved by introducing a novel transfer learning method with fully pretrained weights from a geometrically similar dataset. Batch renormalization and focal loss are also incorporated to increase the accuracy. Testing results show that the improved YOLOv3 has a detection accuracy of up to 80% and 47% at the Intersection‐over‐Union (IoU) metrics of 0.5 and 0.75, respectively. It outperforms the original YOLOv3 and the two‐stage detector Faster Region‐based Convolutional Neural Network (Faster R‐CNN) with ResNet‐101, especially for the IoU metric of 0.75.     

Automated detection of cracks in buried concrete pipe images

The detection of cracks in concrete infrastructure is a problem of great interest. In particular, the detection of cracks in buried pipes is a crucial step in assessing the degree of pipe deterioration for municipal and utility operators. The key challenge is that whereas joints and laterals have a predictable appearance, the randomness and irregularity of cracks make them difficult to model. Our previous work has led to a segmented pipe image (with holes, joints, and laterals eliminated) obtained by a morphological approach. This paper presents the development of a statistical filter for the detection of cracks in the pipes. We propose a two-step approach. The first step is local and is used to extract crack features from the buried pipe images; we present two such detectors as well as a method for fusing them. The second step is global and defines the cracks among the segment candidates by processes of cleaning and linking. The influences of the parameters on crack detection are studied and results are presented for various pipe images.     

Mapping the Underworld – State-of-the-art review

A major UK initiative, entitled Mapping the Underworld (MTU), is seeking to address the serious social, environmental and economic consequences arising from an inability to locate accurately and completely the buried utility service infrastructure without resorting to excavations. One of the four MTU projects aims to develop and prove the efficacy of a multi-sensor device for accurate remote buried utility service detection, location and, where possible, utility identification. This paper aims to introduce the MTU programme followed by a state-of-the-art review of the three essential technologies that are to be combined in the device – ground penetrating radar (GPR), low-frequency quasi-static electromagnetic fields and acoustics – and a summary of the influence of different soil types and states on the transmission of the various signals, and therefore how the techniques might be optimised from a knowledge of the ground instead of using very broad simplifying assumptions. The latest developments in impulse GPR, frequency modulated continuous waveform (FMCW) GPR and stepped frequency continuous waveform (SFCW) GPR are described and previous attempts to combine GPR with other sensing technologies are introduced. The work on quasi-static fields explores the ‘fields-of-opportunity’ related to the 50 Hz currents flowing in existing underground power circuits and the electric field variations when low-frequency current in actively induced into the ground. Acoustic techniques have been primarily used for leak detection and the review focuses on the potential for their application to buried utility service location. The paper concludes with a discussion of the facilities required, and currently available, for comprehensive assessment and independent verification of the performance of both existing devices/technologies and of the multi-sensor device under development.     

Automatic Road Defect Detection by Textural Pattern Recognition Based on AdaBoost

Abstract: The state of roads is continuously degrading due to meteorological conditions, ground movements, and traffic, leading to the formation of defects, such as grabbing, holes, and cracks. In this article, a method to automatically distinguish images of road surfaces with defects from road surfaces without defects is presented. This method, based on supervised learning, is generic and may be applied to all type of defects present in those images. They typically present strong textural information with patterns that show fluctuations at small scales and some uniformity at larger scales. The textural information is described by applying a large set of linear and nonlinear filters. To select the most pertinent ones for the current application, a supervised learning based on AdaBoost is performed. The whole process is tested both on a textural recognition task based on the VisTex image database and on road images collected by a dedicated road imaging system. A comparison with a recent cracks detection algorithm from Oliveira and Correia demonstrates the proposed method's efficiency.     

Automated detection of sewer pipe defects in closed-circuit television images using deep learning techniques

Sanitary sewer systems are designed to collect and transport sanitary wastewater and stormwater. Pipe inspection is important in identifying both the type and location of pipe defects to maintain the normal sewer operations. Closed-circuit television (CCTV) has been commonly utilized for sewer pipe inspection. Currently, interpretation of the CCTV images is mostly conducted manually to identify the defect type and location, which is time-consuming, labor-intensive and inaccurate. Conventional computer vision techniques are explored for automated interpretation of CCTV images, but such process requires large amount of image pre-processing and the design of complex feature extractor for certain cases. In this study, an automated approach is developed for detecting sewer pipe defects based on a deep learning technique namely faster region-based convolutional neural network (faster R-CNN). The detection model is trained using 3000 images collected from CCTV inspection videos of sewer pipes. After training, the model is evaluated in terms of detection accuracy and computation cost using mean average precision (mAP), missing rate, detection speed and training time. The proposed approach is demonstrated to be applicable for detecting sewer pipe defects accurately with high accuracy and fast speed. In addition, a new model is constructed and several hyper-parameters are adjusted to study the influential factors of the proposed approach. The experiment results demonstrate that dataset size, initialization network type and training mode, and network hyper-parameters have influence on model performance. Specifically, the increase of dataset size and convolutional layers can improve the model accuracy. The adjustment of hyper-parameters such as filter dimensions or stride values contributes to higher detection accuracy, achieving an mAP of 83%. The study lays the foundation for applying deep learning techniques in sewer pipe defect detection as well as addressing similar issues for construction and facility management.     

Segmentation of Pipe Images for Crack Detection in Buried Sewers

Abstract:   Assessing the condition of underground pipelines such as water lines, sewer pipes, and telecommunication conduits in an automated and reliable manner is vital to the safety and maintenance of buried public infrastructure. To fully automate condition assessment, it is necessary to develop robust data analysis and interpretation systems for defects in buried pipes. This article presents the development of an automated data analysis system for detecting defects in sanitary sewer pipelines. We propose a three-step method to identify and extract cracks from contrast enhanced pipe images. This method is based on mathematical morphology and curvature evaluation that detects crack-like patterns in a noisy pipe camera scanned image. As cracks are the most common defects in pipes and are indicative of the residual structural strength of the pipe, they are the focus of this study. This article discusses its implementation on 225 pipe images taken from different cities in North America and shows that the system performs very well under a variety of pipe conditions.     

Automated annotation for visual recognition of construction resources using synthetic images

The recognition of construction equipment is always necessary and important to monitor the progress and the safety of a construction project. Recently, the potentials of computer vision (CV) techniques have been investigated to facilitate the current equipment recognition method. However, the process of manually collecting and annotating a large image dataset of different equipment is one of the most time-consuming tasks that may delay the application of the CV techniques for construction equipment recognition. Moreover, collecting effective negative samples brings more difficulties for training the object detectors. This research aims to introduce an automated method for creating and annotating synthetic images of construction equipment while significantly reducing the required time. The synthetic images of the equipment are created from the three-dimensional (3D) models of construction machines combined with various background images taken from construction sites. The location of the equipment in the images is known since that equipment is the only object over the single-color background. This location can be extracted by applying segmentation techniques and then used for the annotation purpose. Furthermore, an automated negative image sampler is introduced in this paper to automatically generate many negative samples with different sizes out of one general image of a construction site in a way that the samples do not include the target object. The test results show that the proposed method is able to reduce the required time for annotating the images in comparison with traditional annotation methods while improving the detection accuracy.     

探地雷达在路面厚度无损检测中的应用

探讨了探地雷达在道路无损检测中应用的基本原理和雷达波传播速度的计算方法,分析了道路结构层及电磁波的反射特性,以及探地雷达对路面结构层厚度检测的过程,说明应用探地雷达检测路面厚度是切实可行的。     

探地雷达在福州某路面塌陷勘察中的应用

探地雷达因其快捷、经济的特点,在现今城市道路勘察中得到了广泛的应用。结合对福州某路面塌陷的勘察实例,介绍了探地雷达剖面法的工作方式及其原理,在该工程得到的雷达剖面上认清了路面下方的管线和地层的分布情况,从而对塌陷区域周边是否还会继续塌陷进行了评价。     

路用探地雷达的工程应用

路面结构层厚度检测是道路质量控制的重要工作,采用具有快速、无损、可连续测试的探地雷达技术对其进行检测,更能为竣工验收提供科学依据。文中介绍了探地雷达技术在公路路面工程厚度检测中的实际应用,说明探地雷达检测公路路面厚度在实际应用中是切实可行的,在公路工程质量检测中具有独特的优势,为公路路面厚度检测增添了一种新的技术方法。     

Water pipeline failure detection using distributed relative pressure and temperature measurements and anomaly detection algorithms

This paper presents the validation of a novel leak detection method for water distribution pipelines, although it could be applied to any buried pressurized fluid flow pipe. The detection method is based on a relative pressure sensor attached non-invasively to the outside of the pipe combined with temperature difference measurements between the pipe wall and the soil. Moreover, this paper proposes an anomaly detection algorithm, originally developed for monitoring website traffic data, which differentiates a ‘leak’ event from ‘normal’ pressure change events. It is compared to two more commonly used methods based on a fixed threshold and a moving average. The validation of the new system in a field trial over a 6-month period showed that all the known leaks were identified with 98.45% accuracy, with the anomaly detection algorithm performing best, making this system a real contender for leak detection in pipes.     

Measurement radius of reinforcing steel bar in concrete using digital image GPR

Ground penetrating radar (GPR) is currently one of the most efficient sensors used for the detection of dielectric cylindrical objects buried under concrete. Physical and theoretical modeling and experimental results of buried reinforcing steel bar (rebar) are given and studied using measurements of radargram data. This allows for reinforcing steel of radii (1.6 cm, 1 cm) to be detected and estimated from the radargrams. A physical model is presented for the electromagnetic signature of a buried reinforcing steel bar, which takes into account the radius of the rebar. This is achieved by subjecting GPR radargrams to a series of digital image processing stages, followed by different power reflectivity within the energy zone during the motion of the GPR antenna along the reinforced concrete surface. Power reflectivity for vertically oriented migration traces was generated. The distance between variant power reflectivity and the long dimension radius of an energy footprint can be considered when calculating the radius of reinforcing steel bar. The results indicate that, this model is capable of estimating the reinforcing steel bar radius to within 7%.     

混凝土构件深浅埋钢筋模拟检测试验与偏移分析

应用地质雷达进行混凝土构件缺陷检测时,浅埋钢筋会对层下钢筋及目标物的探测造成干扰,对其原因进行分析并采取有效的手段去除干扰具有重要意义。通过理论计算设计了检测试验方案,在沙槽中埋设不同埋深钢筋模拟混凝土中钢筋的检测,运用多种偏移手段对检测信号进行处理。结果表明:浅层钢筋对深层钢筋检测的干扰,与地质雷达探测区域覆盖的浅层钢筋的长度有关;相较于绕射叠加偏移、Kirchoff偏移、F-K域偏移等方法,Tau-p域偏移能够更好地对钢筋检测信号进行偏移处理,钢筋的位置被更为准确地识别,偏移后的地质雷达三维图像变得平坦、干净。结合工程实例,对地质雷达数据进行了偏移分析,取得了良好的效果。     

Numerical modeling and experimental evaluation of a time domain UWB technique for soil void detection

A growing percentage of waste and storm water conveyance systems are approaching or exceeded their design life, suffering from accelerated deterioration and subsequently increased rates of failure. Discontinuities in the pipe wall may lead to the formation of voids in the soil embedment surrounding it via the transportation of fine soil particles by infiltrating ground water. This paper describes a method that utilizes ultra wideband (UWB) time domain principles to detect the presence and location of soil voids in early stages of formation, thus preventing a catastrophic collapse of the pipe and/or a structure above it (e.g., road surface). A three dimensional numerical model simulating the propagation of UWB pulses within a buried pipeline was developed. The results from the numerical model were validated using experimental measurements performed utilizing a full scale test bed. It is shown that a UWB based sensory system is capable of detecting even minor voids around non-ferrous buried pipes.     

预应力管道灌浆密实度探地雷达模型试验及正演模拟

预应力桥梁管道的灌浆质量直接影响桥梁的使用年限,为了将探地雷达探测应用到预应力管道灌浆质量检测的实际工程中,首先制作含有不同工况的预应力管道物理模型,用探地雷达对模型进行探测。对所探测得到的数据进行处理分析,并分别对不同工况的预应力管道进行正演模拟分析。结果表明:探地雷达对塑料管道内部探测效果好于金属管道,但两者对电磁波的反射信号剖面图上均显示为弧形。二维雷达剖面图像能准确反映出管道的位置和塑料管道灌浆质量,三维图更加立体直观。将正演模拟结果和物理模型探地雷达探测结果进行对比分析,表明了模拟结果的正确性,充分验证了探地雷达对预应力管道灌浆质量探测的可行性,对桥梁的质量检测提供理论依据。