Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter

TL;DR

This paper introduces a differentiable multi-sensor Kalman Filter for 3D multi-object cooperative tracking in autonomous driving, significantly improving accuracy while maintaining low communication costs.

Contribution

It proposes a novel learning-based method to estimate measurement uncertainty for each detection, enhancing Kalman Filter tracking in V2V cooperative perception.

Findings

Improves tracking accuracy by 17% over state-of-the-art.

Achieves low communication costs of 0.037x.

Demonstrates effectiveness on V2V4Real benchmark.

Abstract

Current state-of-the-art autonomous driving vehicles mainly rely on each individual sensor system to perform perception tasks. Such a framework's reliability could be limited by occlusion or sensor failure. To address this issue, more recent research proposes using vehicle-to-vehicle (V2V) communication to share perception information with others. However, most relevant works focus only on cooperative detection and leave cooperative tracking an underexplored research field. A few recent datasets, such as V2V4Real, provide 3D multi-object cooperative tracking benchmarks. However, their proposed methods mainly use cooperative detection results as input to a standard single-sensor Kalman Filter-based tracking algorithm. In their approach, the measurement uncertainty of different sensors from different connected autonomous vehicles (CAVs) may not be properly estimated to utilize the theoretical optimality property of Kalman Filter-based tracking algorithms. In this paper, we propose a novel 3D multi-object cooperative tracking algorithm for autonomous driving via a differentiable multi-sensor Kalman Filter. Our algorithm learns to estimate measurement uncertainty for each detection that can better utilize the theoretical property of Kalman Filter-based tracking methods. The experiment results show that our algorithm improves the tracking accuracy by 17% with only 0.037x communication costs compared with the state-of-the-art method in V2V4Real. Our code and videos are available at https://github.com/eddyhkchiu/DMSTrack/ and https://eddyhkchiu.github.io/dmstrack.github.io/ .