Truck Body-Type Classification using Single-Beam Lidar Sensors

Abstract

Understanding commodity flow through a region is key for estimating the demand for freight transportation facilities and services, forecasting energy consumption, analyzing safety risks, and addressing environmental concerns. Transportation planners and decision makers use commodity flow data to develop and implement long-term freight plans and manage infrastructure. State-of-the-practice commodity flow estimations based on regional socioeconomic data and periodic surveys have limited spatial and temporal coverage. Moreover, no existing methods tie vehicles to commodity movements at the link level. Although intrusive inductive loop detectors can identify the industry served (or commodity carried) by trucks based on the truck’s body type, intrusive sensor performance is limited by pavement quality. Unfortunately, poor pavement conditions are common in locations with high truck volumes. This paper investigates the use of a non-intrusive traffic sensor, Lidar, for high-resolution truck body-type classification. This paper develops a proof-of-concept Lidar sensor and a truck body-type classification model capable of classifying five-axle tractor-trailers into distinct body types: van and container, platform, low-profile trailer, tank, and hopper and end dump. These body-class groups link to commodity movements and provide insight into link-level commodity flows. Data for model development and validation were collected along a major interstate corridor and a low-speed local road. The classification model achieves an 81% true positive rate (TPR) with class-specific TPR as high as 94% and average volume accuracy of 87% for the primary test location. Overall, the proposed sensor represents an adequate proof of concept to evaluate the industry served by trucks on a network link.