Contour Errors: An Ego-Centric Metric for Reliable 3D Multi-Object Tracking

TL;DR

This paper introduces Contour Errors, a novel ego-centric metric for more reliable 3D multi-object tracking, significantly improving match accuracy over traditional 2D metrics in complex scenes, especially in autonomous vehicle contexts.

Contribution

The paper proposes Contour Errors, a new 3D object matching metric that enhances tracking reliability by focusing on ego-centric bounding box comparisons, outperforming existing metrics.

Findings

Contour Errors outperform IoU and CPD in 3D tracking accuracy.

Significant reduction in functional failures (80% at close range, 60% at far range).

Improved reliability in complex 3D scenes for autonomous vehicle perception.

Abstract

Finding reliable matches is essential in multi-object tracking to ensure the accuracy and reliability of perception systems in safety-critical applications such as autonomous vehicles. Effective matching mitigates perception errors, enhancing object identification and tracking for improved performance and safety. However, traditional metrics such as Intersection over Union (IoU) and Center Point Distances (CPDs), which are effective in 2D image planes, often fail to find critical matches in complex 3D scenes. To address this limitation, we introduce Contour Errors (CEs), an ego or object-centric metric for identifying matches of interest in tracking scenarios from a functional perspective. By comparing bounding boxes in the ego vehicle's frame, contour errors provide a more functionally relevant assessment of object matches. Extensive experiments on the nuScenes dataset demonstrate that contour errors improve the reliability of matches over the state-of-the-art 2D IoU and CPD metrics in tracking-by-detection methods. In 3D car tracking, our results show that Contour Errors reduce functional failures (FPs/FNs) by 80% at close ranges and 60% at far ranges compared to IoU in the evaluation stage.