Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Autonomous concrete crack detection using deep fully convolutional neural network

Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring

A literature review of next-generation smart sensing technology in structural health monitoring

Detection of cracks on bridge decks is a vital task for maintaining the structural health and reliability of concrete bridges. Robotic imaging can be used to obtain bridge surface image sets for automated on-site analysis. We present a novel automated crack detection algorithm, the STRUM (spatially tuned robust multifeature) classifier, and demonstrate results on real bridge data using a state-of-the-art robotic bridge scanning system. By using machine learning classification, we eliminate the need for manually tuning threshold parameters. The algorithm uses robust curve fitting to spatially localize potential crack regions even in the presence of noise. Multiple visual features that are spatially tuned to these regions are computed. Feature computation includes examining the scale-space of the local feature in order to represent the information and the unknown salient scale of the crack. The classification results are obtained with real bridge data from hundreds of crack regions over two bridges. This comprehensive analysis shows a peak STRUM classifier performance of 95% compared with 69% accuracy from a more typical image-based approach. In order to create a composite global view of a large bridge span, an image sequence from the robot is aligned computationally to create a continuous mosaic. A crack density map for the bridge mosaic provides a computational description as well as a global view of the spatial patterns of bridge deck cracking. The bridges surveyed for data collection and testing include Long-Term Bridge Performance program's (LTBP) pilot project bridges at Haymarket, VA, USA, and Sacramento, CA, USA.

Automated Crack Detection on Concrete Bridges

The condition of bridges is critical for the safety of the traveling public. Bridges deteriorate with time as a result of material aging, excessive loading, environmental effects, and inadequate maintenance. The current practice of nondestructive evaluation (NDE) of bridge decks cannot meet the increasing demands for highly efficient, cost-effective, and safety-guaranteed inspection and evaluation. In this paper, a mechatronic systems design for an autonomous robotic system for highly efficient bridge deck inspection and evaluation is presented. An autonomous holonomic mobile robot is used as a platform to carry various NDE sensing systems for simultaneous and fast data collection. The robot's NDE sensor suite includes ground penetrating radar arrays, acoustic/seismic arrays, electrical resistivity sensors, and video cameras. Besides the NDE sensors, the robot is also equipped with various onboard navigation sensors such as global positioning system (GPS), inertial measurement units (IMU), laser scanner, etc. An integration scheme is presented to fuse the measurements from the GPS, the IMU and the wheel encoders for high-accuracy robot localization. The performance of the robotic NDE system development is demonstrated through extensive testing experiments and field deployments.

/pdf/mechatronic-systems-design-for-an-autonomous-robotic-system-2l2mbywkbt.pdf

Mechatronic Systems Design for an Autonomous Robotic System for High-Efficiency Bridge Deck Inspection and Evaluation

Bridges are one of the critical civil infrastructure for safety of traveling public. The conditions of bridges deteriorate with time as a result of material aging, excessive loading, and inadequate maintenance, etc. In this paper, the development of an autonomous robotic system is presented for highly-efficient bridge deck inspection and evaluation. An autonomous mobile robot is used as a platform to carry various non-destructive evaluation (NDE) sensing systems for simultaneous and fast data collection. Besides the NDE sensors, the robot is also equipped with various onboard navigation sensors. A sensing integration scheme is presented for high-accuracy robot localization and navigation. The effectiveness of the autonomous robotic NDE system is demonstrated through extensive experiments and field deployments.

Autonomous robotic system for high-efficiency non-destructive bridge deck inspection and evaluation

The primary objective of this research was to demonstrate the benefits of non-destructive testing (NDT) technologies for effectively detecting and characterizing deterioration in bridge decks. In particular, the objectives were to demonstrate the capabilities of ground-penetrating radar (GPR) and impact echo (IE), and to evaluate and describe the condition of nine bridge decks proposed by Iowa Department of Transportation (DOT). The first part of the report provides a detailed review of the most important deterioration processes in concrete decks, followed by a discussion of the five NDT technologies utilized in this project. In addition to GPR and IE methods, three other technologies were utilized, namely: half-cell (HC) potential, electrical resistivity (ER), and ultrasonic surface waves (USW) method. The review includes a description of the principles of operation, field implementation, data analysis, and interpretation; information regarding their advantages and limitations in bridge deck evaluations and condition monitoring are also implicitly provided.. The second part of the report provides descriptions and bridge deck evaluation results from the nine bridges. The results of the NDT surveys are described in terms of condition assessment maps and are compared with the observations obtained from the recovered cores or conducted bridge deck rehabilitation. Results from this study confirm that the used technologies can provide detailed and accurate information about a certain type of deterioration, electrochemical environment, or defect. However, they also show that a comprehensive condition assessment of bridge decks can be achieved only through a complementary use of multiple technologies at this stage,. Recommendations are provided for the optimum implementation of NDT technologies for the condition assessment and monitoring of bridge decks.

Comprehensive Bridge Deck Deterioration Mapping of Nine Bridges by Nondestructive Evaluation Technologies

The information presented in this report provides a detailed assessment of the condition of the Arlington Memorial Bridge (AMB) deck. The field-data collection was obtained by both the RABIT™ Bridge Inspection Tool and a number of semi-automated non-destructive evaluation (NDE) tools. The deployment of the semi-automated NDE tools was performed to inspect the AMB deck condition and also to validate data obtained by the RABIT™ Bridge Inspection Tool. Data mining and analysis were accomplished through enhanced data interpretation and visualization capabilities using advanced data integration, fusion, and 2D rendering. One of the major challenges that the research team had to overcome in assessing the condition of the AMB deck was the presence of an asphalt overlay on the entire bridge deck.

Hooman Parvardeh

Papers

Automated Crack Detection on Concrete Bridges

Mechatronic Systems Design for an Autonomous Robotic System for High-Efficiency Bridge Deck Inspection and Evaluation

Autonomous robotic system for high-efficiency non-destructive bridge deck inspection and evaluation

Comprehensive Bridge Deck Deterioration Mapping of Nine Bridges by Nondestructive Evaluation Technologies

Nondestructive evaluation inspection of the Arlington Memorial Bridge using a robotic assisted bridge inspection tool (RABIT)