A Novel Multiple Camera RGB-D Calibration Approach Using Simulated Annealing

Journal article


Taghipour-Gorjikolaie, M., Volino, M., Rusbridge, C. and Wells, K. (2024). A Novel Multiple Camera RGB-D Calibration Approach Using Simulated Annealing. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3424412
AuthorsTaghipour-Gorjikolaie, M., Volino, M., Rusbridge, C. and Wells, K.
Abstract

The development of a cost-effective surface scanning system tailored for live animal image capture can play an important role in biomedical research. The primary aim was to introduce a low-cost system, achieving a surface reconstruction error of less than 2mm, and enabling rapid acquisition speeds of approximately 1 second for a complete 360-degree surface capture. Leveraging a five RGB-D camera configuration, our approach offers a simple, low-cost alternative to conventional lab-based 3D scanning setups. Key to our methodology is a novel calibration strategy aimed at refining intrinsic and extrinsic camera parameters simultaneously for improved accuracy. We introduce a novel 3D calibration object, extending existing techniques employing ArUco markers, and implement a depth correction matrix to enhance depth accuracy. By utilizing Simulated Annealing optimization alongside our custom calibration object, we achieve superior results compared to conventional optimization techniques. Our obtained results show that the proposed depth correction method can reduce the reprojection error from 3.12 to 2.89 pixels. Furthermore, despite the simplicity of our reconstruction method, we observe around a 22% improvement in surface reconstruction compared to factory calibration parameters. Our findings underscore the practicality and efficacy of our proposed system, paving the way for enhanced 3D surface reconstruction for real-world surface capture.

KeywordsAzure Kinect, Depth correction, RGB-D calibration, sensors, surface reconstruction
Year2024
JournalIEEE Access
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISSN2169-3536
Digital Object Identifier (DOI)https://doi.org/10.1109/ACCESS.2024.3424412
Web address (URL)https://ieeexplore.ieee.org/document/10587236
Publication dates
Online08 Jan 2024
Publication process dates
Deposited10 Jul 2024
Permalink -

https://openresearch.lsbu.ac.uk/item/97q3z

  • 3
    total views
  • 0
    total downloads
  • 3
    views this month
  • 0
    downloads this month

Export as

Related outputs

Prediction of Nonsinusoidal AC Loss of Superconducting Tapes Using Artificial Intelligence-Based Models
Yazdani-Asrami, M., Taghipour-Gorjikolaie, M., Song, W., Zhang, M. and Yuan, W. (2020). Prediction of Nonsinusoidal AC Loss of Superconducting Tapes Using Artificial Intelligence-Based Models. IEEE Access. 8, pp. 207287 - 207297. https://doi.org/10.1109/access.2020.3037685
Deep Region of Interest and Feature Extraction Models for Palmprint Verification Using Convolutional Neural Networks Transfer Learning
Izadpanahkakhk, M., Razavi, S., Taghipour-Gorjikolaie, M., Zahiri, S. and Uncini, A. (2018). Deep Region of Interest and Feature Extraction Models for Palmprint Verification Using Convolutional Neural Networks Transfer Learning. Applied Sciences. https://doi.org/10.3390/app8071210