Extrinsic Calibration of Multiple RGB-D Cameras From Line Observations

This letter presents a novel method to estimate the relative poses between RGB and depth cameras without the requirement of an overlapping field of view, thus providing flexibility to calibrate a variety of sensor configurations. This calibration problem is relevant to robotic applications that can benefit of using several cameras to increase the field of view. In our approach, we extract and match lines of the scene in the RGB and depth cameras, and impose geometric constraints to find the relative poses between the sensors. An analysis of the observability properties of the problem is presented. We have validated our method in both synthetic and real scenarios with different camera configurations, demonstrating that our approach achieves good accuracy and is very simple to apply, in contrast with previous methods based on trajectory matching using visual odometry or simultaneous localization and mapping.

[1]  Marc Pollefeys,et al.  CamOdoCal: Automatic intrinsic and extrinsic calibration of a rig with multiple generic cameras and odometry , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Yang Shang,et al.  A Flexible Online Camera Calibration Using Line Segments , 2016, J. Sensors.

[3]  Eduardo Fern,et al.  Extrinsic calibration of 2D laser rangefinders from perpendicular plane observations , 2015 .

[4]  Gim Hee Lee.  A Minimal Solution for Non-perspective Pose Estimation from Line Correspondences , 2016, ECCV.

[5]  Francisco Angel Moreno,et al.  An Instrumented Vehicle for Efficient and Accurate 3D Mapping of Roads , 2013, Comput. Aided Civ. Infrastructure Eng..

[6]  Hans-Joachim Wünsche,et al.  Odometry-based online extrinsic sensor calibration , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Bruno Vallet,et al.  Generation of an integrated 3D city model with visual landmarks for autonomous navigation in dense urban areas , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[8]  Patrick Rives,et al.  Dense accurate urban mapping from spherical RGB-D images , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[9]  A. Habib,et al.  Bundle Adjustment with Self–Calibration Using Straight Lines , 2002 .

[10]  José Luis Blanco Claraco,et al.  Simultaneous Localization and Mapping for Mobile Robots: Introduction and Methods , 2012 .

[11]  Josechu J. Guerrero,et al.  Peripheral Expansion of Depth Information via Layout Estimation with Fisheye Camera , 2016, ECCV.

[12]  Javier González,et al.  Extrinsic calibration of 2D laser rangefinders from perpendicular plane observations , 2015, Int. J. Robotics Res..

[13]  Javier González,et al.  Extrinsic calibration of a 2d laser-rangefinder and a camera based on scene corners , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Juho Kannala,et al.  Joint Depth and Color Camera Calibration with Distortion Correction , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Josechu J. Guerrero,et al.  Automatic Line Extraction in Uncalibrated Omnidirectional Cameras with Revolution Symmetry , 2015, International Journal of Computer Vision.

[16]  Derek Hoiem,et al.  Indoor Segmentation and Support Inference from RGBD Images , 2012, ECCV.

[17]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[18]  Jong-Eun Ha,et al.  Extrinsic calibration of a camera and laser range finder using a new calibration structure of a plane with a triangular hole , 2012 .

[19]  Javier González,et al.  Extrinsic calibration of a set of range cameras in 5 seconds without pattern , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Seth J. Teller,et al.  Extrinsic Calibration from Per-Sensor Egomotion , 2012, Robotics: Science and Systems.

[21]  Josechu J. Guerrero,et al.  A novel hybrid camera system with depth and fisheye cameras , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[22]  Pavel Zemcík,et al.  Absolute pose estimation from line correspondences using direct linear transformation , 2016, Comput. Vis. Image Underst..

[23]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Richard Szeliski,et al.  Creating full view panoramic image mosaics and environment maps , 1997, SIGGRAPH.

[25]  Richard Hartley.  Camera Calibration Using Line Correspondences , 2001 .