LiDAR Vehicle Point Cloud Reconstruction Framework for Axle-Based Classification

As light detection and ranging (LiDAR) technology rapidly advances, it is becoming increasingly viable as a solution to collect vehicle classification data. The main challenge of LiDAR compared with video in vehicle classification lies in its resolution, which limits the ability of LiDAR-based models to classify vehicles in detail from a single captured frame. This article proposes a novel framework for reconstructing the vehicle point clouds generated by a roadside LiDAR sensor, by considering ground plane constraints and developing a bootstrap aggregating deep neural network (bagging DNN) model to classify the reconstructed vehicle point clouds, according to the U.S. Federal Highway Administration (FHWA) axle-based vehicle classification scheme. First, a probabilistic-based registration algorithm is used to estimate the transformation matrix between consecutive frames of each vehicle point cloud. Then, a multiway registration is conducted to fine-tune the estimated transformation matrices to rebuild the 3-D model of each moving vehicle. Second, key features are extracted from the reconstructed vehicle models and fed into a bagging DNN model to provide classifications based on the FHWA scheme. The classification model with the reconstruction framework outperforms the latest developed LiDAR-based FHWA classification model in terms of both accuracy and robustness. The model has an 83% average correct classification rate (CCR) on the test set. Remarkably, the proposed model can accurately distinguish Class 5 and 8 trucks, which have overlapping axle configurations, with a 97% and a 90% CCR, respectively.