U.S. Department of Transportation
Federal Highway Administration
1200 New Jersey Avenue, SE
Washington, DC 20590
Federal Highway Administration Research and Technology
Exploratory Advanced Research Program
Highway transportation researchers are collecting and analyzing an increasing amount of video data. Reasons include recent technological breakthroughs that provide new and enhanced visual and other sensors for conducting research in multiple areas such as system planning, operations, safety, and infrastructure condition assessment.
The Strategic Highway Research Program (SHRP) 2 safety area includes elements of the above types of data in the naturalistic driving study (NDS). The amount of data can be orders of magnitude larger than what the highway researcher has worked with previously with research results expected to exceed one petabyte. FHWA’s EAR Program working with the Office of Safety R&D is sponsoring five research projects that will explore breakthroughs in machine learning to automate extraction of safety data from NDS such as SHRP2 project. The NDS involved collection of data on the daily travels of 3,150 volunteer drivers, whose vehicles were heavily instrumented for the study. Those drivers traveled 49.5 million miles during the study period, resulting in over 1.2 million hours of video and vehicle data. See http://www.trb.org/StrategicHighwayResearchProgram2SHRP2/Public/Pages/Safety_153.aspx, for more information on the SHRP2 safety area.
FHWA is also working with experts at Oak Ridge National Laboratory to test the research results and develop methods and test data sets for future researchers to use in comparing and validating the performance of automated data extraction algorithms.
While the research community is fortunate to be able to collect more and better data, the amount of data has the potential to overwhelm the capacity to assess the data using current methods. Current methods include a mix of automated and manual, frame-by-frame coding that is not able to manage massive data stream and provides results that are not consistent or error free enough. Large data sets in their present form are too time-consuming and expensive to analyze using traditional data extraction methods, yet they are important for providing understanding of the context around rare events such as crashes. Automating data extraction from video files is expected to dramatically reduce the costs of using these data, making them accessible to the widest possible pool of researchers.
ITS America conducted a technology scan for the USDOT Intelligent Transportation Systems (ITS) Joint Program Office. The scan report, "Connected Vehicles: Trends in Computer Vision," are located at http://www.itsa.org/knowledgecenter/technologyscan. As the technology moves from stand alone to integrated systems and from systems that provide driver or operator warnings to direct control of vehicle and infrastructure systems (i.e. steering, acceleration, braking, taffic signals) there is a critical need for compatible systems architecture and common conditions against which multiple manufacturers can test their equipment and software.