Large Scale Indoor Camera Positioning Using Fiducial Markers
This project introduces a novel approach that employs fiducial markers to estimate first the pair-wise relationship between nearby cameras and then performs a full optimization incorporating real-world information.
Abstract
Estimating the pose of a large set of fixed indoor cameras is a requirement for certain applications in augmented reality, autonomous navigation, video surveillance, and logistics. However, accurately mapping the position of these cameras remains an unresolved problem. While providing partial solutions, existing alternatives are limited by their dependence on distinct environmental features, the requirement for large overlapping camera views and specific conditions. This work introduces a novel approach that employs fiducial markers to estimate first the pair-wise relationship between nearby cameras and then performs a full optimization incorporating real-world information to refine results further. We validate our approach using novel artificial and real datasets with varying levels of complexity. Our experiments demonstrate superior performance over existing state-of-the-art techniques and increased effectiveness in real-world applications. Accompanying this paper, we provide the research community with access to our code, tutorials, and an application framework to support the deployment of our methodology.
Tutorials
We have prepared some initial tutorials in order to take a first contact with the tool!
Introduction to Indoor Camera Positioning
Overview of the Indoor Camera Positioning application
Download
To support the research community and encourage further exploration, we have made our code, tutorials, and applications readily accessible. Researchers and developers can now build and calibrate their custom fiducial objects using the comprehensive resources available at the following links:
- Download the code from SourceForge . Developed using CPP
, OpenCV 
,CMake 
and QT Creator 
. We include a user-friendly GUI Interface. - Access the dataset generated for the source paper at SourceForge . It includes both the Real and Artifitial datasets, as well as, the sources needed for the generation of the Artifitial datasets in Blender
.
Citing
If you use this library in your research, you must cite:
- García-Ruiz, P.; Romero-Ramrize, F.J.; Muñoz-Salinas, R.; Marín-Jiménez, M.J.; Medina-Carnicer, R. Large Scale Indoor Camera Positioning Using Fiducial Markers. Sensors 2024, 24, 4303. https://doi.org/10.3390/s24134303.
- Garrido-Jurado, S.; Munoz-Salinas, R.; Madrid-Cuevas, F.J.; Marin-Jimenez, M.J. Automatic generation and detection of highly reliable fiducial markers under occlusion. Pattern Recognition 2014, 47, 2280–2292.
- Muñoz-Salinas, R.; Marín-Jimenez, M.J.; Yeguas-Bolivar, E.; Medina-Carnicer, R. Mapping and localization from planar markers. Pattern Recognition 2018, 73, 158–171.
Paper
The article where this method was developed can be read here.
License
This software is licensed under MIT license.
Contact
If you have any further question, please contact pgruiz@uco.es.
Please support my career through my Github and YouTube profiles 
.
Related Projects
Marker Mapper and Aruco.