OpenGV 2.0: Motion prior-assisted calibration and SLAM with vehicle-mounted surround-view systems

2025-03-05

AI Summary

To address the practical challenges of low field-of-view overlap and frequent unidirectional camera configurations in automotive surround-view systems, this paper proposes a visual SLAM framework integrating Ackermann motion priors. Methodologically, it is the first to deeply embed the vehicle’s nonholonomic motion model into a three-stage optimization pipeline: online extrinsic calibration, robust frontend initialization, and continuous-time B-spline trajectory estimation. By jointly modeling motion constraints and two-view geometry, the approach resolves partial pose unobservability. Contributions include: (1) the first production-ready, city-scale surround-view SLAM system for mass-market passenger vehicles; (2) significantly improved extrinsic calibration accuracy and trajectory consistency; and (3) open-sourcing the framework as OpenGV 2.0. Extensive evaluation on large-scale public datasets validates its effectiveness.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The present paper proposes optimization-based solutions to visual SLAM with a vehicle-mounted surround-view camera system. Owing to their original use-case, such systems often only contain a single camera facing into either direction and very limited overlap between fields of view. Our novelty consist of three optimization modules targeting at practical online calibration of exterior orientations from simple two-view geometry, reliable front-end initialization of relative displacements, and accurate back-end optimization using a continuous-time trajectory model. The commonality between the proposed modules is given by the fact that all three of them exploit motion priors that are related to the inherent non-holonomic characteristics of passenger vehicle motion. In contrast to prior related art, the proposed modules furthermore excel in terms of bypassing partial unobservabilities in the transformation variables that commonly occur for Ackermann-motion. As a further contribution, the modules are built into a novel surround-view camera SLAM system that specifically targets deployment on Ackermann vehicles operating in urban environments. All modules are studied in the context of in-depth ablation studies, and the practical validity of the entire framework is supported by a successful application to challenging, large-scale publicly available online datasets. Note that upon acceptance, the entire framework is scheduled for open-source release as part of an extension of the OpenGV library.

Problem

• Optimizes visual SLAM for vehicle-mounted surround-view camera systems.
• Addresses limited overlap and single-camera constraints in vehicle systems.
• Exploits motion priors for calibration and optimization in urban environments.

Innovation

• Optimization-based visual SLAM for vehicle-mounted cameras
• Motion priors exploit non-holonomic vehicle characteristics
• Continuous-time trajectory model for accurate back-end optimization