Event cameras triggered a paradigm shift in the computer vision community delineated by their asynchronous nature, low latency, and high dynamic range. Calibration of event cameras is always essential to account for the sensor intrinsic parameters and for 3D perception. However, conventional image-based calibration techniques are not applicable due to the sparse, binary output of the sensor. The current standard for calibrating event cameras relies on either blinking patterns or event-based image reconstruction algorithms. These approaches are difficult to implement in the field and are affected by noise and artifacts degrading the calibration performance. To bridge these limitations, we present Event-Calibration (E-Calib), a novel, fast, and accurate calibration tool for event cameras utilizing the asymmetric circles grid. In our method, the sparse events are initially clustered using a resolution agnostic spatiotemporal density-based clustering (ST-DBSCAN) algorithm to match the events to their corresponding calibration targets. An efficient, novel weighted least squares method is proposed to extract the image points of the calibration targets from the clustered events with sub-pixel accuracy and robustness to noise. Finally, a modified hierarchical clustering algorithm is devised to detect the calibration grid apart from the background clutter. The work of this paper was tested in a variety of rigorous experiments for different event camera models, on circle grids with different geometric properties, and under challenging illumination conditions. The results show that our approach outperforms the state-of-the-art in detection success rate, reprojection error, and estimation accuracy of extrinsic parameters.

Reference:
M. Salah, A. Ayyad, M. Humais, D. Gehrig, A. Abusafieh, L. Seneviratne, D. Scaramuzza, and Y. Zweiri, "E-Calib: A Fast, Robust, and Accurate Calibration Toolbox for Event Cameras," in IEEE Transactions on Image Processing, vol. 33, pp. 3977-3990, 2024, doi: 10.1109/TIP.2024.3410673.
PDF: [ Ссылка ]
Project Page & Code: [ Ссылка ]

Affiliations:
M. Salah, A. Ayyad, and Y. Zweiri are with the Advanced Research & Innovation Center, Khalifa University, Abu Dhabi, UAE, [ Ссылка ]
M. Humais and L. Seneviratne are with Khalifa University Center of Autonomous Robotic Systems, Abu Dhabi, UAE, [ Ссылка ]
D. Gehrig and D. Scaramuzza are with the Robotics and Perception Group, University of Zurich, Switzerland, [ Ссылка ]
A. Abusafieh is with Research and Development, Strata Manufacturing PJSC (a Mubadala company), Al Ain, UAE, [ Ссылка ]

свернуть