A Flexible Technique for Accurate Omnidirectional Camera Calibration and Structure from Motion

By Davide Scaramuzza, Agostino Martinelli, Roland Yves Siegwart. International Conference on Virtual Storytelling, 2006

502 citations recorded by the source corpus.

In this paper, we present a flexible new technique for single viewpoint omnidirectional camera calibration. The proposed method only requires the camera to observe a planar pattern shown at a few different orientations. Either the camera or the planar pattern can be freely moved. No a priori knowledge of the motion is required, nor a specific model of the omnidirectional sensor. The only assumption is that the image projection function can be described by a Taylor series expansion whose coefficients are estimated by solving a two-step least-squares linear minimization problem. To test the proposed technique, we calibrated a panoramic camera having a field of view greater than 200 in the vertical direction, and we obtained very good results. To investigate the accuracy of the calibration, we also used the estimated omni-camera model in a structure from motion experiment. We obtained a 3D metric reconstruction of a scene from two highly distorted omnidirectional images by using image correspondences only. Compared with classical techniques, which rely on a specific parametric model of the omnidirectional camera, the proposed procedure is independent of the sensor, easy to use, and flexible.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/91563584d8bcfb5471876d9353b46a5ab5c2ff2f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Large-scale direct SLAM for omnidirectional cameras (2015, methodology): “Accurate results were obtained by moving all nonlinearities into a radially symmetric function, and identifying the first coefficients of its Taylor expansion [17].”
A Toolbox for Easily Calibrating Omnidirectional Cameras (2006, unknown): “A PARAMETRIC CAMERA MODEL For major clarity, we initially report the central camera model introduced in [20], then, we provide its new simplified version.”
Graph-Based Classification of Omnidirectional Images (2017, unknown): “The natural way to do it is to apply calibration techniques [5, 6, 7] to undistort images and then use standard computer vision algorithms.”
Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit (2020, methodology): “Then these images were undistorted using tools in [53] and we annotated the traffic lines in each image to obtain one million training samples.”
Visual-lidar odometry and mapping: low-drift, robust, and fast (2015, methodology): “We assume that the camera is modeled by a general central camera model [21].”
Vision-based state estimation for autonomous rotorcraft MAVs in complex environments (2013, methodology): “Both cameras in the system are modeled with a spherical camera model and calibrated using the Omnidirection Calibration Toolbox [15].”
Monocular Omnidirectional Visual Odometry for Outdoor Ground Vehicles (2008, methodology): “To calibrate our omnidirectional camera, we used the method proposed in [15].”
Spatial As Deep: Spatial CNN for Traffic Scene Understanding (2017, methodology): “These images were undis-torted using tools in (Scaramuzza, Martinelli, and Siegwart 2006) and have a resolution of 1640 × 590 .”
SVO: Semidirect Visual Odometry for Monocular and Multicamera Systems (2017, methodology): “V-A we have already introduced a body frame B, which is rigidly attached to the camera, it is now straightforward to generalize sparse image alignment to multiple cameras.”