eval-vislam

Toolkit for VSLAM and VISLAM evaluation.

For more information, please refer to our project website.

License

This project is released under the Apache 2.0 license.

Prerequisites

• Eigen3
• yaml-cpp

Toolkit Usage

Accuracy (APE, RPE, ARE, RRE, Completeness)

Usage:
  ./accuracy <groundtruth> <input> <fix scale>

Arguments:
  <groundtruth>   Path to sequence folder, e.g. ~/VISLAM-Dataset/A0.
  <input>         SLAM camera trajectory file in TUM format(timestamp[s] px py pz qx qy qz qw).
  <fix scale>     Set to 1 for VISLAM, set to 0 for VSLAM.

Initialization Scale Error and Time

Usage:
  ./initialization <groundtruth> <input> <has inertial>

Arguments:
  <groundtruth>   Path to sequence folder, e.g. ~/VISLAM-Dataset/A0.
  <input>         SLAM camera trajectory file in TUM format(timestamp[s] px py pz qx qy qz qw).
  <has inertial>  Set to 1 for VISLAM, set to 0 for VSLAM.

Robustness

Usage:
  ./robustness <groundtruth> <input> <fix scale>

Arguments:
  <groundtruth>   Path to sequence folder, e.g. ~/VISLAM-Dataset/A0.
  <input>         SLAM camera trajectory file in TUM format(timestamp[s] px py pz qx qy qz qw).
  <fix scale>     Set to 1 for VISLAM, set to 0 for VSLAM.

Relocalization Time

Usage:
  relocalization <groundtruth> <input> <has inertial>

Arguments:
  <groundtruth>   Path to sequence folder, e.g. ~/VISLAM-Dataset/A0.
  <input>         SLAM camera trajectory file in TUM format(timestamp[s] px py pz qx qy qz qw).
  <has inertial>  Set to 1 for VISLAM, set to 0 for VSLAM.

Citation

If you are using our codebase or dataset for research, please cite the following publication:

@article{
  title={Survey and Evaluation of Monocular Visual-Inertial SLAM Algorithms for Augmented Reality},
  author={Jinyu Li, Bangbang Yang, Danpeng Chen, Nan Wang, Guofeng Zhang*, Hujun Bao*},
  journal={Journal of Virtual Reality & Intelligent Hardware},
  year={2019},
  url = {http://www.vr-ih.com/vrih/html/EN/10.3724/SP.J.2096-5796.2018.0011/article.html},
  doi = {10.3724/SP.J.2096-5796.2018.0011}
}