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

TL;DR

This paper introduces a novel 3D object tracking approach that learns correspondences directly from point cloud data, improving tracking accuracy by focusing on motion patterns rather than pairwise similarity, and demonstrates superior performance on KITTI and Nuscenes datasets.

Contribution

The paper proposes a new method that learns 3D object correspondences directly from point clouds and infers motion patterns, bypassing complex similarity computations of previous methods.

Findings

Outperforms existing 3D tracking methods on KITTI dataset

Achieves better accuracy on Nuscenes dataset

Effective velocity smoothing improves motion consistency

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.