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 Long-Term Bridge Performance (LTBP) Program is a 20-year research effort by the U.S. Federal Highway Administration (FHWA) to collect scientific performance field data from a representative sample of bridges nationwide that will help the bridge community better understands bridge deterioration and performance. The products from this program will be a collection of data-driven tools, including predictive and forecasting models, which will enhance the abilities of bridge owners to optimize their management of bridges. The paper describes a key product of the LTBP program, the Bridge Portal, which contains bridge performancerelated data mined from existing sources (National Bridge Inventory, State Highway Agency bridge element level data, national weather data, traffic data, weigh-in-motion data, bridge maintenance data, and other data sources), but it also serves as a central repository for all field data collected through the LTBP Program. Additionally, the Bridge Portal also functions as a research and decision-making tool by implementing bridge life-cycle and deterioration modeling using both mined data sources as well as LTBP-acquired field data to allow users to investigate bridge performance on many different levels.

/pdf/the-long-term-bridge-performance-ltbp-program-bridge-portal-5fprunevut.pdf

Hooman Parvardeh

Papers

The Long-Term Bridge Performance (LTBP) Program Bridge Portal

Comparative Study of Multiple NDT Technologies from the Surveys on a Reinforced Concrete Bridge Deck and Prefabricated Slab

Profiling structurally deficient bridges in the United States: Sampling bridge performance data for qualitative trends

A penalized-likelihood approach to characterizing bridge-related crashes in New Jersey