Offline Auto Labeling: BAAS

TL;DR

BAAS is a comprehensive framework for radar-based object tracking and label annotation in autonomous driving, combining Bayesian methods for accurate trajectories and shape estimation, with evaluation and continuous improvement capabilities.

Contribution

The paper presents BAAS, a novel EOT and fusion-based framework that enhances radar detection annotation accuracy and performance evaluation in complex urban environments.

Findings

Effective in urban real-world scenarios

Accurate shape and trajectory estimation

Supports continuous improvement with manual labels

Abstract

This paper introduces BAAS, a new Extended Object Tracking (EOT) and fusion-based label annotation framework for radar detections in autonomous driving. Our framework utilizes Bayesian-based tracking, smoothing and eventually fusion methods to provide veritable and precise object trajectories along with shape estimation to provide annotation labels on the detection level under various supervision levels. Simultaneously, the framework provides evaluation of tracking performance and label annotation. If manually labeled data is available, each processing module can be analyzed independently or combined with other modules to enable closed-loop continuous improvements. The framework performance is evaluated in a challenging urban real-world scenario in terms of tracking performance and the label annotation errors. We demonstrate the functionality of the proposed approach for varying dynamic objects and class types