DeepArUco++: Improved detection of square fiducial markers in challenging lighting conditions

Rafael Berral-Soler, Rafael Muñoz-Salinas, Rafael Medina-Carnicer, Manuel J. Marín-Jiménez

Abstract: Highlights•A fiducial marker detection system under difficult lighting, using neural networks.•A straightforward method to generate synthetic training data.•A new real-world dataset featuring ArUco markers under difficult lighting conditions.•A comparison against other state-of-the-art marker detection methods.

External IDs:doi:10.1016/j.imavis.2024.105313