Automating Parking Studies Using LIDAR Sensors: Proof of Concept

This research investigates the possibility of using a sensor mounted on a vehicle to collect parking utilization data in parallel parking areas along arterial streets. There are many promising sensor technologies; Laser Detection and Ranging (LIDAR) is used in this pilot study. In this prototype system, the LIDAR scans 180 degrees in a vertical plane, orthogonal to the vehicle's direction of travel. In each scan the LIDAR sensor returns the distance to the nearest target at each angle. This paper discusses how these returns are then processed to estimate the location of the curb and the presence of objects in the road (i.e., on the near side of the curb). Occlusion reasoning and location reasoning are then applied to determine which of the objects are vehicles, which of those vehicles are parked, and where. The occupancy of the parking area, vehicle size, and vehicle-to-vehicle spacing are then measured. This automated vehicle presence detection promises to greatly reduce the labor of parking surveys, provide measures that were formerly cost prohibitive, and potentially do so in real time. The host vehicle could be a transit bus or another municipal vehicle performing ordinary duties, further reducing the data collection costs. The method was applied to an area with unmarked, on-street parking near the Ohio State University campus in Columbus, Ohio. Vehicle counts from five trips were compared against concurrent ground truth from video with favorable results. Results are then presented for 33 measurement trips made over four years.


  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; References; Tables;
  • Pagination: 18p
  • Monograph Title: TRB 91st Annual Meeting Compendium of Papers DVD

Subject/Index Terms

Filing Info

  • Accession Number: 01366410
  • Record Type: Publication
  • Report/Paper Numbers: 12-2886
  • Files: TRIS, TRB
  • Created Date: Mar 29 2012 7:14AM