According to the 2013 ASCE report card America's infrastructure scores only a D+. There are more than four million miles of roads (grade D) in the U.S. requiring a broad range of maintenance activities. The nation faces a monumental problem of infrastructure management in the scheduling and implementation of maintenance and repair operations, and in the prioritization of expenditures within budgetary constraints. The efficient and effective performance of these operations however is crucial to ensuring roadway safety, preventing catastrophic failures, and promoting economic growth. There is a critical need for technology that can cost-effectively monitor the condition of a network-wide road system and provide accurate, up-to-date information for maintenance activity prioritization.The Versatile Onboard Traffic Embedded Roaming Sensors (VOTERS) project provides a framework and the sensing capability to complement periodical localized inspections to continuous network-wide health monitoring. Research focused on the development of a cost-effective, lightweight package of multi-modal sensor systems compatible with this framework. An innovative software infrastructure is created that collects, processes, and evaluates these large time-lapse multi-modal data streams. A GIS-based control center manages multiple inspection vehicles and the data for further analysis, visualization, and decision making. VOTERS' technology can monitor road conditions at both the surface and sub-surface levels while the vehicle is navigating through daily traffic going about its normal business, thereby allowing for network-wide frequent assessment of roadways. This deterioration process monitoring at unprecedented time and spatial scales provides unique experimental data that can be used to improve life-cycle cost analysis models.
Understanding the future transportation infrastructure performance demands a smart Cyber-Physical Systems (CPS) approach integrating heterogeneous sensors, versatile computing systems, and mobile agents. However, due to sensor versatility and computing intricacy, designing such systems faces challenges of immense complexity in mobile sensor fusion, big data handling, system scalability, and integration. This paper introduces SIROM 3 , a Scalable Intelligent ROaming Multi-Modal Multi-Sensor framework, for next generation transportation infrastructure performance inspection. SIROM 3 offers a scalable and expandable framework through orthogonally abstracting software / hardware structures in a layered Run-Time Environment (RTE), which facilities sensor fusion, distributed computing, communication and mobile services. A Heterogeneous Stream File-system Overlay (HSFO) and a flexible plugin system (PLEX) are embedded in SIROM 3 to simplify big data storage, processing, and correlation. To evaluate the scalability of SIROM 3 , we implemented a mobile sensing system of 30 heterogeneous sensors and 5 computing platforms coordinated by 1 data center. SIROM 3 's expandability is highlighted by adding an advanced radar platform which required less than 50 lines of C++ code for integration. Over 20 terabytes of data covering 300 miles have been collected, aggregated, and fused using SIROM 3 for comprehending the pavement dynamics of the entire city of Brockton, MA. SIROM 3 offers a unified solution and ideal research platform for rapid, intelligent and comprehensive evaluation of tomorrow's transportation infrastructure performance using heterogeneous systems.Current roadway pavement monitoring methodologies often face challenges such as intrusive data gathering (e.g. stopping traffic), manual efforts and subsequently infrequent data collection and limited coverage [33]. Hence, non-intrusive, automated, fast, and adaptive solutions for data collection and infrastructure assessment are necessary. Heterogeneous sensor systems such as Multi-Modal Multi-Sensor (MMMS) systems are promising aiming for adaptability, automated operations, power and fuel efficiency, and ubiquitous assessment capability in multiple data domains [9], [12]. Integrating MMMS systems onto a mobile platform creates a Roaming Multi-Modal MultiSensor (RMMMS) system to collect multi-modal data under roaming conditions. However, RMMMS systems are challenging to develop and operate due to the heterogeneity in sensors, data types and synchronization principles, as well as the sheer number of sensors. Typically sensor systems are designed tailor-made to a specific application, which impedes the overall scalability. Meanwhile, system complexity increases exponentially with computational diversities, network-wide collaboration and data correlation. In addition, data-intensive sensors produce a large volume of streaming data in real-time raising the importance to effectively store, access, and process big data. Additionally, deploying multiple RMMMS to increase geogr...
Around 3,000,000 million vehicle miles are annually traveled utilizing the US transportation systems alone. In addition to the road traffic safety, maintaining the road infrastructure in a sound condition promotes a more productive and competitive economy. Due to the significant amounts of financial and human resources required to detect surface cracks by visual inspection, detection of these surface defects are often delayed resulting in deferred maintenance operations. This paper introduces an automatic system for acquisition, detection, classification, and evaluation of pavement surface cracks by unsupervised analysis of images collected from a camera mounted on the rear of a moving vehicle. A Hessian-based multi-scale filter has been utilized to detect ridges in these images at various scales. Post-processing on the extracted features has been implemented to produce statistics of length, width, and area covered by cracks, which are crucial for roadway agencies to assess pavement quality. This process has been realized on three sets of roads with different pavement conditions in the city of Brockton, MA. A ground truth dataset labeled manually is made available to evaluate this algorithm and results rendered more than 90% segmentation accuracy demonstrating the feasibility of employing this approach at a larger scale.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.