A*SLAM: A Dual Fisheye Stereo Edge SLAM

TL;DR

This paper introduces A*SLAM, a full-view fisheye stereo edge SLAM system that utilizes dual fisheye stereo cameras and edge features for robust, illumination-invariant localization and mapping.

Contribution

It presents a novel SLAM system combining dual fisheye stereo cameras with edge features, enabling full environmental coverage and improved robustness.

Findings

Full environmental view coverage with dual fisheye stereo cameras

Edge features provide illumination invariance for SLAM

Direct extraction of panorama depth images from fisheye pairs

Abstract

This paper proposes an A*SLAM system that features combining two sets of fisheye stereo cameras and taking the image edge as the SLAM features. The dual fisheye stereo camera sets cover the full environmental view of the SLAM system. From each fisheye stereo image pair, a panorama depth image can be directly extracted for initializing the SLAM feature. The edge feature is an illumination invariant feature. The paper presents a method of the edge-based simultaneous localization and mapping process using both the normal and inverted images interchangeably.