Evaluation of an Uncertainty-Aware Late Fusion Algorithm for Multi-Source Bird's Eye View Detections Under Controlled Noise

TL;DR

This paper presents a systematic evaluation framework for multi-source fusion in autonomous perception, introducing UniKF, a Kalman filter-based late fusion method that effectively manages noise and synchronization issues, significantly improving detection accuracy.

Contribution

The work introduces a novel evaluation framework with controlled noise injection and proposes UniKF, a Kalman filter-based late fusion algorithm for BEV detections, enhancing robustness and accuracy.

Findings

UniKF reduces position and orientation errors by up to 3x.

UniKF halves dimension estimation errors.

Fusion precision and recall remain above 99.5%.

Abstract

Reliable multi-source fusion is crucial for robust perception in autonomous systems. However, evaluating fusion performance independently of detection errors remains challenging. This work introduces a systematic evaluation framework that injects controlled noise into ground-truth bounding boxes to isolate the fusion process. We then propose Unified Kalman Fusion (UniKF), a late-fusion algorithm based on Kalman filtering to merge Bird's Eye View (BEV) detections while handling synchronization issues. Experiments show that UniKF outperforms baseline methods across various noise levels, achieving up to 3x lower object's positioning and orientation errors and 2x lower dimension estimation errors, while maintaining nearperfect precision and recall between 99.5% and 100%.