Multi-view Sensor Fusion by Integrating Model-based Estimation and Graph Learning for Collaborative Object Localization

TL;DR

This paper presents a novel spatiotemporal graph filter that combines model-based estimation and graph learning to enhance multi-view sensor fusion for collaborative object localization, improving accuracy under uncertainty.

Contribution

It introduces a new graph-based approach that models complex object relationships and fuses multi-view data in a Bayesian framework for better localization.

Findings

Outperforms previous techniques in collaborative localization tasks.

Achieves state-of-the-art performance in connected autonomous driving.

Effectively models complex object relationships and uncertainty.

Abstract

Collaborative object localization aims to collaboratively estimate locations of objects observed from multiple views or perspectives, which is a critical ability for multi-agent systems such as connected vehicles. To enable collaborative localization, several model-based state estimation and learning-based localization methods have been developed. Given their encouraging performance, model-based state estimation often lacks the ability to model the complex relationships among multiple objects, while learning-based methods are typically not able to fuse the observations from an arbitrary number of views and cannot well model uncertainty. In this paper, we introduce a novel spatiotemporal graph filter approach that integrates graph learning and model-based estimation to perform multi-view sensor fusion for collaborative object localization. Our approach models complex object relationships using a new spatiotemporal graph representation and fuses multi-view observations in a Bayesian fashion to improve location estimation under uncertainty. We evaluate our approach in the applications of connected autonomous driving and multiple pedestrian localization. Experimental results show that our approach outperforms previous techniques and achieves the state-of-the-art performance on collaboration localization.