Uncalibrated two-view metrology

A method of visual metrology from uncalibrated cameras is proposed in this paper, whereby a camera, which captures two images separated by a (near) pure translation, becomes a height measurement device. A novel projective construction allows accurate affine height measurements to be made relative to a reference plane, given that the reference plane planar homography between the two views can be accurately recovered. To this end a planar homography estimation method is presented, which is highly accurate and robust and based on a novel reciprocal-polar (RP) image rectification. The absolute height of any pixel or feature above the reference plane can be obtained from this affine height once the camera's distance to the reference plane, or the height of a second measurement in the image is specified. Results from our data show a mean absolute error of 6.9 mm and with two outliers removed this falls to 1.5 mm.

[1]  Edmond Boyer,et al.  Camera calibration and 3D reconstruction from single images using parallelepipeds , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[2]  Ian D. Reid,et al.  Single View Metrology , 2000, International Journal of Computer Vision.

[3]  Zhengyou Zhang,et al.  Determining the Epipolar Geometry and its Uncertainty: A Review , 1998, International Journal of Computer Vision.

[4]  Anders Heyden,et al.  An iterative factorization method for projective structure and motion from image sequences , 1999, Image Vis. Comput..

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

[6]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[7]  Ian D. Reid,et al.  Goal-directed Video Metrology , 1996, ECCV.

[8]  Bill Triggs,et al.  Factorization methods for projective structure and motion , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.