Scene reconstruction using a pan-tilt-zoom camera with a moving spherical mirror

3D scene reconstruction from 2D images can serve as a foundation for solving a number of robotics and computer vision problems such as robot navigation and 3D object recognition in which covering a large field of view could be critical. As conventional cameras have limited fields of view, we propose an approach to reconstruct large 3D scene models using a combination of a pan-tilt-zoom (PTZ) camera and a moving spherical mirror. The proposed system provides uncertainty estimates of the scene model. The uncertainty of moving spherical mirror detection and localization is represented using samples. Two images are used to computed a location measurement of a 3D point in the scene in which the combinations of the sample sets of the two mirror locations are exploited and location measurements of 3D points are represented using Gaussian distributions. Localization of 3D points in the scene is done using a Kalman filter. The experimental results demonstrate the feasibility of the proposed system.

[1]  Hungwen Li,et al.  Fast Hough transform: A hierarchical approach , 1986, Comput. Vis. Graph. Image Process..

[2]  Kuang-Yow Lian,et al.  Synchronization of coupled dynamic systems using fuzzy design approach , 2009, 2009 ICCAS-SICE.

[3]  Douglas Lanman,et al.  Spherical Catadioptric Arrays: Construction, Multi-View Geometry, and Calibration , 2006, Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06).

[4]  Peter I. Corke,et al.  Scale invariant feature matching with wide angle images , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Jean-Yves Bouguet,et al.  Camera calibration toolbox for matlab , 2001 .

[6]  Nicolás Guil Mata,et al.  Lower order circle and ellipse Hough transform , 1997, Pattern Recognit..

[7]  Philippe Bekaert,et al.  Screen-Camera Calibration using a Spherical Mirror , 2007, Fourth Canadian Conference on Computer and Robot Vision (CRV '07).

[8]  Kanbara Masayuki,et al.  3D Scene Reconstruction from Reflection Images in a Spherical Mirror , 2006 .

[9]  Shree K. Nayar,et al.  A Theory of Single-Viewpoint Catadioptric Image Formation , 1999, International Journal of Computer Vision.

[10]  Ming-Li Chiang,et al.  Adaptive control of a class of unknown switched linear systems with dwell time , 2009, 2009 ICCAS-SICE.

[11]  Matthijs C. Dorst Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[12]  K. Sphereo : Determining Depth using Two Specular Spheres and a Single Camera , 1988 .