Development, Education, and Implementation of A Low-Cost Audio Sensor-based Autonomous Surveillance System for Smart and Connected Transportation Infrastructure Construction and Maintenance

Each DOT has to govern and oversee an enormous number of transportation construction and maintenance projects. However, since a transportation construction project entails several miles of a job site including numerous work tasks and equipment operations, it has been increasingly challenging for each DOT to consistently monitor progress of all projects in each State as well as efficiently evaluate work performance. In this demanding situation, DOT practitioners and project managers have long recognized the importance of automated monitoring and surveillance of transportation construction and maintenance processes that helps consistently track work progress and take immediate remedial action. As one promising supplement for site monitoring and human inspection, this project proposes a new approach for low-cost audio sensor-based autonomous site and safety surveillance of transportation construction and maintenance, which allows for faster, more convenient, and more accurate work zone monitoring. The proposed innovation using the sound-based site and safety monitoring framework possesses several competitive advantages over traditional site management and existing vision-based work monitoring methods, which not only sounds can be easily recognized and instantly analyzed by diverse sound sensors. In addition, this sound-based monitoring approach supports an unlimited range of monitoring angles and illumination levels with lightweight data processing and comparatively quick analytics. To achieve these goals, this study will involve the following steps. First, this system will entail a schedule-based sound recognition approach using dynamic sound data training. By using project schedule including daily work activities, this system dynamically restricts the types of sound training data, significantly enhancing sound classification accuracy. Second, this system will involve a low-cost wearable audio-sensor for automated work zone monitoring and real-time activity log generation. The light-weight sound data can be readily captured, analyzed, shared, and visualized for real-time site monitoring and activity log generation that have not been achieved by the current methods because of limited human resource for in-person site monitoring and heavy-weight video data processing. This new intelligent site and safety surveillance system is expected to support real-time monitoring of construction progress, evaluation of task performance, and rapid identification of safety issues in transportation construction and maintenance projects.

Language

  • English

Project

  • Status: Active
  • Funding: $75000
  • Contract Numbers:

    19PPLSU12

  • Sponsor Organizations:

    Office of the Assistant Secretary for Research and Technology

    University Transportation Centers Program
    Department of Transportation
    Washington, DC  United States  20590
  • Managing Organizations:

    Transportation Consortium of South-Central States

    Louisiana State University
    Baton Rouge, LA  United States  70803
  • Project Managers:

    Melson, Christopher

  • Performing Organizations:

    Louisiana State University and A&M College

    202 Himes Hall
    Baton Rouge, LA  United States  70803
  • Principal Investigators:

    Lee, Yong-Cheol

    Choi, Jin-Woo

  • Start Date: 20190815
  • Expected Completion Date: 20210215
  • Actual Completion Date: 0
  • USDOT Program: University Transportation Centers Program

Subject/Index Terms

Filing Info

  • Accession Number: 01713228
  • Record Type: Research project
  • Source Agency: Transportation Consortium of South-Central States
  • Contract Numbers: 19PPLSU12
  • Files: UTC, RiP
  • Created Date: Aug 5 2019 3:45PM