United States Department of Transportation
i
Innovative vehicle classification strategies : using LIDAR to do more for less.
-
2012-06-23
-
[PDF-2.70 MB]
Details:
-
Alternative Title:USDOT Region V Regional University Transportation Center Final Report
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Final report.
-
Corporate Publisher:
-
Abstract:This study examines LIDAR (light detection and ranging) based vehicle classification and classification
performance monitoring. First, we develop a portable LIDAR based vehicle classification system that can
be rapidly deployed, and then we use the LIDAR based system for automated validation of conventional
vehicle classification stations.
We develop the LIDAR based classification system with the sensors mounted in a side-fire configuration
next to the road. The first step is to distinguish between vehicle returns and non-vehicle returns. The
algorithm then clusters the vehicle returns into individual vehicles. The algorithm examines each vehicle
cluster to check if there is any evidence of partial occlusion from another vehicle. Several measurements
are taken from each non-occluded cluster to classify the vehicle into one of six classes: motorcycle,
passenger vehicle, passenger vehicle pulling a trailer, single-unit truck, single-unit truck pulling a trailer,
and multi-unit truck. The algorithm was evaluated at six different locations under various traffic
conditions. Compared to concurrent video ground truth data for over 27,000 vehicles on a per-vehicle
basis, 11% of the vehicles are suspected of being partially occluded. The algorithm correctly classified
over 99.5% of the remaining, non-occluded vehicles. This research also uncovered emerging challenges
that likely apply to most classification systems, e.g., differentiating commuter cars from motorcycles.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
