Visual SLAMMOT Considering Multiple Motion Models

TL;DR

This paper introduces a visual SLAMMOT system that integrates multiple motion models to improve simultaneous localization, mapping, and multi-object tracking in dynamic environments, addressing limitations of previous static or simplified models.

Contribution

It extends the IMM-SLAMMOT framework from LiDAR to visual sensors, demonstrating the feasibility and benefits of multiple motion models in visual SLAMMOT for autonomous driving.

Findings

Enhanced accuracy in dynamic object tracking.

Successful implementation of multiple motion models in visual SLAMMOT.

Improved robustness in complex outdoor scenarios.

Abstract

Simultaneous Localization and Mapping (SLAM) and Multi-Object Tracking (MOT) are pivotal tasks in the realm of autonomous driving, attracting considerable research attention. While SLAM endeavors to generate real-time maps and determine the vehicle's pose in unfamiliar settings, MOT focuses on the real-time identification and tracking of multiple dynamic objects. Despite their importance, the prevalent approach treats SLAM and MOT as independent modules within an autonomous vehicle system, leading to inherent limitations. Classical SLAM methodologies often rely on a static environment assumption, suitable for indoor rather than dynamic outdoor scenarios. Conversely, conventional MOT techniques typically rely on the vehicle's known state, constraining the accuracy of object state estimations based on this prior. To address these challenges, previous efforts introduced the unified SLAMMOT paradigm, yet primarily focused on simplistic motion patterns. In our team's previous work IMM-SLAMMOT\cite{IMM-SLAMMOT}, we present a novel methodology incorporating consideration of multiple motion models into SLAMMOT i.e. tightly coupled SLAM and MOT, demonstrating its efficacy in LiDAR-based systems. This paper studies feasibility and advantages of instantiating this methodology as visual SLAMMOT, bridging the gap between LiDAR and vision-based sensing mechanisms. Specifically, we propose a solution of visual SLAMMOT considering multiple motion models and validate the inherent advantages of IMM-SLAMMOT in the visual domain.