Convolutional Unscented Kalman Filter for Multi-Object Tracking with Outliers

TL;DR

This paper introduces ConvUKF, a robust multi-object tracking algorithm that effectively handles outliers in autonomous driving scenarios, improving accuracy and stability over existing methods.

Contribution

The paper proposes a convolutional UKF variant that explicitly models outliers, maintaining real-time performance and providing bounded tracking error in complex traffic environments.

Findings

ConvUKF outperforms baseline algorithms on KITTI and nuScenes datasets.

ConvUKF maintains Gaussian conjugacy, enabling real-time processing.

The method demonstrates bounded error, ensuring robust stability in the presence of outliers.

Abstract

Multi-object tracking (MOT) is an essential technique for navigation in autonomous driving. In tracking-by-detection systems, biases, false positives, and misses, which are referred to as outliers, are inevitable due to complex traffic scenarios. Recent tracking methods are based on filtering algorithms that overlook these outliers, leading to reduced tracking accuracy or even loss of the objects trajectory. To handle this challenge, we adopt a probabilistic perspective, regarding the generation of outliers as misspecification between the actual distribution of measurement data and the nominal measurement model used for filtering. We further demonstrate that, by designing a convolutional operation, we can mitigate this misspecification. Incorporating this operation into the widely used unscented Kalman filter (UKF) in commonly adopted tracking algorithms, we derive a variant of the UKF that is robust to outliers, called the convolutional UKF (ConvUKF). We show that ConvUKF maintains the Gaussian conjugate property, thus allowing for real-time tracking. We also prove that ConvUKF has a bounded tracking error in the presence of outliers, which implies robust stability. The experimental results on the KITTI and nuScenes datasets show improved accuracy compared to representative baseline algorithms for MOT tasks.