ITS Support for Pedestrians and Bicyclists Count: Developing a Statewide Multimodal Count Program

It is critical to understand the travel behavior of pedestrians and cyclists on Louisiana’s roadways. Not only do pedestrian and cyclist counts assist in research for safety, but these statistics are also essential for planners and policymakers when evaluating the usage of roadways and dictating infrastructure spending. Better understanding of overall statewide and location-specific transportation trends ultimately affects long-term planning and investment. Counting of pedestrians and cyclists using video surveillance and image processing technology has promised to be effective and feasible. While the research on newer technologies is not as robust as that of traditional ones, there is enough evidence to justify and guide the use of automated video count technology. This study concentrates on a specific algorithm, which would aid in automatic counting. This goal is achieved by following a part-based method, which utilizes the Histogram of Oriented Gradient (HOG) technique as well as a latent support vector machine (SVM). This technique was the preferred algorithm for automation due to its high-speed processing capability and its open source availability. The accuracy of the HOG algorithm in this study is validated using manual counts of pedestrians and cyclists from the collected video data. It is anticipated that the results will assist LTRC-16-4SA in evaluating available count technology options and in identifying preferred alternatives suitable for statewide deployment. The tested algorithm led to accuracy rates between 29-91% for pedestrians and 0-60% for cyclists. Despite the poor results obtained, the algorithm’s efficacy was thoroughly evaluated and documented. Some of the specific challenges faced in this study involved maintaining accurate viewpoint angles as well as conducting object detection in high-density environments and complicated scenes like intersections. New automated video counting systems have sought to improve algorithms in these problematic areas. Future work involves effectively handling these challenges and reevaluating the algorithm while considering others currently being used today.

  • Record URL:
  • Corporate Authors:

    Louisiana Transportation Research Center

    Louisiana State University, 4101 Gourrier Avenue
    Baton Rouge, LA  United States  70808

    Louisiana Department of Transportation and Development

    1201 Capitol Access Road, P.O. Box 94245
    Baton Rouge, LA  United States  70804-9245

    Federal Highway Administration

    1200 New Jersey Avenue, SE
    Washington, DC  United States  20590
  • Authors:
    • Codjoe, Julius
    • Holamoge, Yoshita
    • Tian, Rui
    • Ash, C
    • Saunders, William
  • Publication Date: 2019-7

Language

  • English

Media Info

  • Media Type: Digital/other
  • Edition: Final Report
  • Features: Appendices; Figures; Photos; References; Tables;
  • Pagination: 101p

Subject/Index Terms

Filing Info

  • Accession Number: 01716644
  • Record Type: Publication
  • Report/Paper Numbers: FHWA/LA.017/598, LTRC Project Number: 17-2SA, State Project Number: DOTLT1000162
  • Files: TRIS, ATRI, USDOT, STATEDOT
  • Created Date: Sep 4 2019 3:46PM