Three dimensional measurement using fisheye stereo vision

In this paper, we describe on a method for a three dimensional measurement of omni-directional space of camera view, using a fisheye stereo vision. In the method, the correction image is made from fisheye image. Three dimensional data of a moving object is calculated, using a parallax detected by template matching in the correction image. An ellipse as a geometrical model is calculated, using a plane coordinate on the object in real space. And a volume of the object is detected using the detected height and the ellipse. In the paper, composition of an experimental system and the measurement method are explained, and the experimental result is shown.

[1]  Clemens Rabe,et al.  6D Vision Goes Fisheye for Intersection Assistance , 2008, 2008 Canadian Conference on Computer and Robot Vision.

[2]  Atsushi Imiya,et al.  Panoramic image transform of omnidirectional images using discrete geometry techniques , 2004, Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004..

[3]  Gonzalo Pajares,et al.  A Featured-Based Strategy for Stereovision Matching in Sensors with Fish-Eye Lenses for Forest Environments , 2009, Sensors.

[4]  Atsushi Yamashita,et al.  Three-Dimensional Environment Model Construction from an Omnidirectional Image Sequence , 2009, J. Robotics Mechatronics.

[5]  Jake K. Aggarwal,et al.  Mobile robot navigation and scene modeling using stereo fish-eye lens system , 1997, Machine Vision and Applications.

[6]  J. Yamaguchi,et al.  Human tracking using fisheye images , 2007, SICE Annual Conference 2007.

[7]  Masato Inoue,et al.  Development of “All-Around View” System , 2003 .

[8]  Atsushi Yamashita,et al.  Construction of 3D Environment Model from an Omni-Directional Image Sequence , 2008 .

[9]  Andrew W. Fitzgibbon,et al.  Bundle Adjustment - A Modern Synthesis , 1999, Workshop on Vision Algorithms.

[10]  Yasushi Yagi,et al.  HyperOmni vision: Visual navigation with an omnidirectional image sensor , 1997 .

[11]  Kaj Madsen,et al.  Methods for Non-Linear Least Squares Problems , 1999 .

[12]  Gonzalo Pajares Martinsanz,et al.  Choquet Fuzzy Integral Applied to Stereovision Matching for Fish-Eye Lenses in Forest Analysis , 2009 .

[13]  Gaurav S. Sukhatme,et al.  Combined optic-flow and stereo-based navigation of urban canyons for a UAV , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  William Thompson,et al.  Three-dimensional measurement using a single image , 1996 .

[15]  Jake K. Aggarwal,et al.  Intrinsic parameter calibration procedure for a (high-distortion) fish-eye lens camera with distortion model and accuracy estimation , 1996, Pattern Recognit..

[16]  Jun'ichi Yamaguchi,et al.  A vehicle identification using fisheye camera , 2008 .