GOReloc: Graph-based Object-Level Relocalization for Visual SLAM

TL;DR

GOReloc introduces a graph-based object-level relocalization method for visual SLAM that improves pose estimation accuracy by robustly associating objects with semantic uncertainties, enhancing relocalization success rates.

Contribution

It presents a novel graph-based approach using semantic descriptors and RANSAC refinement for object-level relocalization in visual SLAM systems.

Findings

Achieves more accurate data association.

Significantly increases relocalization success rates.

Demonstrates robustness across various datasets.

Abstract

This article introduces a novel method for object-level relocalization of robotic systems. It determines the pose of a camera sensor by robustly associating the object detections in the current frame with 3D objects in a lightweight object-level map. Object graphs, considering semantic uncertainties, are constructed for both the incoming camera frame and the pre-built map. Objects are represented as graph nodes, and each node employs unique semantic descriptors based on our devised graph kernels. We extract a subgraph from the target map graph by identifying potential object associations for each object detection, then refine these associations and pose estimations using a RANSAC-inspired strategy. Experiments on various datasets demonstrate that our method achieves more accurate data association and significantly increases relocalization success rates compared to baseline methods. The implementation of our method is released at \url{https://github.com/yutongwangBIT/GOReloc}.