Counting Empty Parking Spots at Truck Stops

Project summary:

For at least the past decade, truck driver fatigue has been thought to be a contributing factor in a number of heavy truck accidents. It is estimated that driver fatigue leads to about 40% of all truck accidents, and that 90% of drivers perceive a shortage of parking. Contrary to this only 53% of truck stops are occupied on any given night.

For better utilization of truck stops and to provide truck drivers with safe rest options, the researchers envision an automated truck stop management system that can compute occupancy rates at stops and notify drivers about the availability of parking spots using variable message displays located about 30 or 40 miles before the stop. The proposed system detects, classifies, and localizes vehicles on the truck stop's grounds by using a set of video cameras, from which video frames are analyzed in real-time. Since exact knowledge of which stops are occupied will be available, variable message displays at the site of the stop itself will be able to direct drivers to free spots.

A novel Computer Vision based framework and algorithm was developed to obtain a reliable state of individual parking spots. It was tested using an intuitive calibration system, with which a new parking area can be setup in a matter of minutes. Preliminary results from sample videos were very convincing, and practical challenges using the system outdoors were identified and overcome. Future steps to make the system deployable and trustworthy were also identified.