Gr-IoU: Ground-Intersection over Union for Robust Multi-Object Tracking with 3D Geometric Constraints

TL;DR

This paper introduces Gr-IoU, a novel 3D geometric-based metric for improving data association in multi-object tracking by transforming bounding boxes to the ground plane, leading to better tracking accuracy especially in crowded scenes.

Contribution

We propose Gr-IoU, a ground-plane based IoU metric that enhances multi-object tracking by incorporating 3D scene geometry, reducing ID switches and improving accuracy.

Findings

Outperforms conventional methods on MOT17 and MOT20 datasets.

Reduces ID switches in crowded and occluded scenes.

Improves data association accuracy without appearance features.

Abstract

We propose a Ground IoU (Gr-IoU) to address the data association problem in multi-object tracking. When tracking objects detected by a camera, it often occurs that the same object is assigned different IDs in consecutive frames, especially when objects are close to each other or overlapping. To address this issue, we introduce Gr-IoU, which takes into account the 3D structure of the scene. Gr-IoU transforms traditional bounding boxes from the image space to the ground plane using the vanishing point geometry. The IoU calculated with these transformed bounding boxes is more sensitive to the front-to-back relationships of objects, thereby improving data association accuracy and reducing ID switches. We evaluated our Gr-IoU method on the MOT17 and MOT20 datasets, which contain diverse tracking scenarios including crowded scenes and sequences with frequent occlusions. Experimental results demonstrated that Gr-IoU outperforms conventional real-time methods without appearance features.