Low-cost LIDAR based Vehicle Pose Estimation and Tracking

TL;DR

This paper introduces a robust, real-time vehicle detection and tracking method using low-cost LIDAR data, employing T-Linkage RANSAC for segmentation and a multi-model approach for smooth trajectory estimation, outperforming previous methods.

Contribution

The paper presents a novel data-driven, model-based vehicle segmentation and tracking approach that eliminates the L-shape assumption and improves robustness against noise in low-cost LIDAR data.

Findings

Outperforms previous segmentation methods in accuracy.

Runs in real-time on low-cost LIDAR data.

Provides smooth vehicle trajectories with multi-model association.

Abstract

Detecting surrounding vehicles by low-cost LIDAR has been drawing enormous attention. In low-cost LIDAR, vehicles present a multi-layer L-Shape. Based on our previous optimization/criteria-based L-Shape fitting algorithm, we here propose a data-driven and model-based method for robust vehicle segmentation and tracking. The new method uses T-linkage RANSAC to take a limited amount of noisy data and performs a robust segmentation for a moving car against noise. Compared with our previous method, T-Linkage RANSAC is more tolerant of observation uncertainties, i.e., the number of sides of the target being observed, and gets rid of the L-Shape assumption. In addition, a vehicle tracking system with Multi-Model Association (MMA) is built upon the segmentation result, which provides smooth trajectories of tracked objects. A manually labeled dataset from low-cost multi-layer LIDARs for validation will also be released with the paper. Experiments on the dataset show that the new approach outperforms previous ones based on multiple criteria. The new algorithm can also run in real-time.