Robust Laser Cross Detection
Type of the data | Software | |
Type of the data | Image | |
Total size of the dataset | 16386809 | |
Author | Kluwe, Moritz Niklas | |
Author | Hardege, Robert | |
Upload date | 2024-12-12T16:37:42Z | |
Publication date | 2024-12-12T16:37:42Z | |
Publication date | 2024-12-12 | |
Abstract of the dataset | The source code repository contains the complete Python implementation of the laser cross detection algorithm, including example datasets. The repository includes synthetic image generation tools, evaluation scripts, and reference implementations of RANSAC and Probabilistic-Hough-Transform methods for comparison. Example datasets feature both synthetic and real-world calibration images, with documentation detailing their usage. All code is thoroughly commented and includes usage examples. The implementation requires common Python libraries (numpy, scipy, lmfit) and provides a straightforward API for integration into existing calibration workflows. | |
Public reference to this page | https://opara.zih.tu-dresden.de/handle/123456789/1157 | |
Public reference to this page | https://doi.org/10.25532/OPARA-697 | |
Publisher | Technische Universität Bergakademie Freiberg | |
Licence | MIT | en |
URI of the licence text | https://opensource.org/license/MIT | |
Specification of the discipline(s) | 4::44::409::409-05 | |
Specification of the discipline(s) | 4::42::404::404-03 | |
Title of the dataset | Robust Laser Cross Detection | |
Project abstract | Recent advances in volumetric camera calibration techniques have established non-invasive methods for multi-camera setups. Laser-beam methods, particularly those introduced by Hardege et al. (2022, 2023) and enhanced by Gunady et al. 2024, show significant promise. A critical component of these calibration procedures is the precisely detection of laser beam intersections in 2D images. Current methodologies, including Hough-Line-Transformation, Template Matching, RANSAC, and 2D Gaussian beam fitting, exhibit limitations in both stability and accuracy, especially when encountering reflections, refractions, and other image artifacts. This paper introduces a deterministic approach for identifying straight light beams and accurately determining their intersections in grayscale 2D images. The proposed method exploits the Gaussian intensity distribution of laser beams and eliminates the need for binarization or probabilistic sampling. Extensive evaluation using both synthetic and real-world images demonstrates superior accuracy and robustness compared to existing methods, particularly for intersection angles above 20◦ and in the presence of significant noise. | |
Project title | Robust laser cross detection for non-invasive volumetric camera calibration |
Collections
