Tracking from Patterns: Learning Corresponding Patterns in Point Clouds for 3D Object Tracking

Abstract

A robust 3D object tracker which continuously tracks surrounding objects and estimates their trajectories is key for self-driving vehicles. Most existing tracking methods employ a tracking-by-detection strategy, which usually requires complex pair-wise similarity computation and neglects the nature of continuous object motion. In this paper, we propose to directly learn 3D object correspondences from temporal point cloud data and infer the motion information from correspondence patterns. We modify the standard 3D object detector to process two lidar frames at the same time and predict bounding box pairs for the association and motion estimation tasks. We also equip our pipeline with a simple yet effective velocity smoothing module to estimate consistent object motion. Benifiting from the learned correspondences and motion refinement, our method exceeds the existing 3D tracking methods on both the KITTI and larger scale Nuscenes dataset.

arXiv comment4 pages, ECCV2020 Workshop on Perception for Autonomous Driving(PAD2020)

References in corpus (7)

• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• End-to-end Learning of Multi-sensor 3D Tracking by Detection
• Center-based 3D Object Detection and Tracking
• Joint Monocular 3D Vehicle Detection and Tracking
• Probabilistic 3D Multi-Object Tracking for Autonomous Driving
• GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning
• Frame-wise Motion and Appearance for Real-time Multiple Object Tracking