A*SLAM: A Dual Fisheye Stereo Edge SLAM
This is an incremental improvement for robotics and autonomous systems needing reliable SLAM in challenging lighting conditions.
The paper tackles the problem of robust visual SLAM in varying illumination by using dual fisheye stereo cameras and edge features, achieving full environmental coverage and illumination invariance.
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.