Probabilistic 3D Multi-Object Tracking for Autonomous Driving

Abstract

3D multi-object tracking is a key module in autonomous driving applications that provides a reliable dynamic representation of the world to the planning module. In this paper, we present our on-line tracking method, which made the first place in the NuScenes Tracking Challenge, held at the AI Driving Olympics Workshop at NeurIPS 2019. Our method estimates the object states by adopting a Kalman Filter. We initialize the state covariance as well as the process and observation noise covariance with statistics from the training set. We also use the stochastic information from the Kalman Filter in the data association step by measuring the Mahalanobis distance between the predicted object states and current object detections. Our experimental results on the NuScenes validation and test set show that our method outperforms the AB3DMOT baseline method by a large margin in the Average Multi-Object Tracking Accuracy (AMOTA) metric.

References in corpus (2)

• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Argoverse: 3D Tracking and Forecasting with Rich Maps

Cited by in corpus (10)

• DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition
• An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds
• FlowMOT: 3D Multi-Object Tracking by Scene Flow Association
• 1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking
• PnPNet: End-to-End Perception and Prediction with Tracking in the Loop
• Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds
• Uncertainty-aware Self-supervised 3D Data Association
• Multi-Object Tracking using Poisson Multi-Bernoulli Mixture Filtering for Autonomous Vehicles
• A two-stage data association approach for 3D Multi-object Tracking
• FLAVA: Find, Localize, Adjust and Verify to Annotate LiDAR-Based Point Clouds