LSU_AIM2024

This zip file contains a subset of the image sequences and all YOLOv5 neural networks used in the "Solving Short-Term Relocalization Problems in Monocular Keyframe Visual SLAM Using Spatial and Semantic Data" paper. This paper was presented in 2024 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM) held in Boston, MA, USA.

The proposed framework, along with links to the preprint paper and presentation slides is made publicly available in this GitHub repository: https://github.com/RKinDLab/ros2_psd_pcb_reloc

UPDATE: 07/30/2024

After careful consideration, we have decided to remove the image sequences from the EuRoC MAV and TUM RGBD SLAM datasets to avoid future confusion with redistribution.  Only the image sequenecs from our in-house UGV dataset (LSU-iCORE-Mono) have been provided along with the neural network weights.

Please follow the updated instructions in the GitHub repo regarding how to setup sequences from EuRoC MAV and TUM RGBD SLAM (Robot SLAM category) datasets.