I. Introduction
Efficient and reliable 3-D multiple extended object tracking (MEOT) has played a pivotal role in various applications, such as autonomous driving, robotic navigation, and traffic monitoring [1], [2], [3]. Unlike traditional point-based tracking methods that treat objects as single points, 3-D MEOT utilizes modern high-resolution sensors to track objects with substantial spatial extents, allowing for a more comprehensive understanding of an object’s extent (e.g., shape and size) and kinematic state (e.g., position and velocity) [4].