Uncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss

TL;DR

This paper introduces a novel approach to 3D object detection and tracking that incorporates uncertainty estimation using von-Mises and Gaussian NLL losses, enhancing robustness and tracking accuracy in autonomous systems.

Contribution

It proposes a new uncertainty regression method for 3D detection that improves tracking performance by integrating angular and positional uncertainties into existing frameworks.

Findings

Enhanced tracking accuracy with uncertainty modeling

Effective estimation of positional, dimensional, and angular uncertainties

Improved robustness in 3D object tracking systems

Abstract

Object detection and tracking is a key task in autonomy. Specifically, 3D object detection and tracking have been an emerging hot topic recently. Although various methods have been proposed for object detection, uncertainty in the 3D detection and tracking tasks has been less explored. Uncertainty helps us tackle the error in the perception system and improve robustness. In this paper, we propose a method for improving target tracking performance by adding uncertainty regression to the SECOND detector, which is one of the most representative algorithms of 3D object detection. Our method estimates positional and dimensional uncertainties with Gaussian Negative Log-Likelihood (NLL) Loss for estimation and introduces von-Mises NLL Loss for angular uncertainty estimation. We fed the uncertainty output into a classical object tracking framework and proved that our method increased the tracking performance compared against the vanilla tracker with constant covariance assumption.