Journal of Infrastructure Systems

As a part of the digital highway data vehicle (DHDV), the automated survey system developed at the University of Arkansas is the implementation of a real-time system for pavement surface cracking survey. The researchers faced tremendous tasks in optimizing imaging algorithms to speed up the processing at the same time without sacrificing accuracy in identifying and classifying cracks. This paper introduces the automated real-time system and summarizes the experiences in developing parallel algorithms in imaging processing used in the real-time system. The hardware system for processing images is based on the ubiquitous multiple Central Processing Unit (CPU) $\times 86$ platform that has the capability of two levels of parallel processing at multiple CPU level and within each CPU level. The former is commonly called Symmetrical Processing (SMP) and the latter is called Single Instruction Multiple Data (SIMD). The paper also presents results of a network level survey with the DHDV and the distress analyzer on a network of about $161\mathrm{km}$ $\left(100\mathrm{mil}\right)$ of pavements. In addition, a manual survey was conducted on the same network of pavements. World Bank’s universal cracking indicator (CI) is used in this study. Because the distress analyzer is fully automated and results of the analysis are provided in synch with image collection, the potential cost savings when compared with manual survey methods and other semiautomated survey technologies are tremendous.

Many researchers have reported on the poor status of sewer pipes in Canadian cities, revealing the presence of a number of defects that impact their performance. Inadequate inspection is considered one of the main causes behind the declining condition of this class of pipes. This could be attributed to the high cost of inspection and inadequate funds allocated to this purpose. The labor-intensive current inspection practice gives rise to such high costs. This paper presents an automated system “AUTO-DETECT” that detects and classifies defects in sewer pipes automatically. The paper expands on earlier developments made by the writers, provides an overview of the overall configuration of the system, and focuses primarily on automated detection and classification of infiltration in sewer pipes. Infiltration is considered to be a serious and common defect that contributes to an undesirable extra flow of about 40% in this class of pipes. The system utilizes pattern recognition, image analysis techniques, and artificial intelligence to perform its task. A case example is presented to demonstrate the use and capabilities of the developed system.

Recent research has revealed that the nondestructive evaluation technique used most often to assess the physical condition of a bridge is visual inspection. During a routine visual inspection, observations and/or measurements are made and then recorded by means of field sketches, written descriptions, and site photographs. This information is ultimately entered into a bridge management system where it is maintained and used to make decisions regarding future maintenance, rehabilitation, or replacement of the bridge. Recognizing the importance of such documentation, this paper reports on the use of QuickTime Virtual Reality (QTVR) for recording and managing information normally collected during a routine inspection. With this technology, bridge inspection projects can be documented in an interactive, virtual reality format and supplement customary inspection reports. The specific details related to QTVR development (including field procedures and multimedia techniques) as applied to various bridge inspection projects are discussed in this paper. The study concludes with a discussion of the potential impact of the QTVR technology in bridge inspection.

Monitoring data are collected to measure the condition, environment, usage, and performance of civil infrastructure. High quality monitoring data are necessary for decision-support systems, design analysis, and research. However, little work has been done in the area of generic, automated data quality assessment and cleansing procedures. We have developed an automated, two-level data quality assessment procedure to address this deficiency. In the first level of our procedure, several different data quality assessment methods are used in a voting scheme to identify concentrations of anomalies in aggregate data. In the second level, differences between anomalies and normal data at the individual data level are identified; combined with domain knowledge, these differences can be used to identify different types of errors, such as missing data and calibration errors. In our case studies, we have been able to effectively cleanse the data using the results from our data quality assessment procedure. We have also developed a test bench to explore the sensitivity of the data quality assessment algorithms used in our approach. The test bench introduces a known error into a clean, artificial data set and then evaluates how well each assessment method identifies the error. The test bench results show that our approach is able to effectively identify anomalies, even those with small magnitudes of error.

Inspection activities such as bridge inspection generally rely on using paper-based forms for documenting the inspection results. However, recent advances in computer technology, where the hardware is getting smaller in size yet more powerful, allow computer systems to be used in the field to help inspectors collect inspection information. To provide useful and practical computing support for inspectors in performing inspection activities in the field, a computer system for supporting these inspectors has to be designed and customized to recognize the specific inspection tasks being performed and the physical and knowledge-based contexts of the inspection. Unfortunately, the development of field inspection support systems is both difficult and time consuming, since this process suffers from a lack of generality. Effort is currently wasted when implementing different applications for supporting different field workers that still share some common aspects. This paper first discusses the use of eXtensible Markup Language (XML) to model inspection information useful in the development of inspection support systems and then discusses how the model can be used by the Java Inspection Framework (JIF) to automatically create an inspection application. XML in concert with JIF reduces the effort required to create an inspection application because the application can be developed without requiring the application developer to create a single line of Java code.