Surface Modelling of Plants from Stereo Images

Plants are characterised by a range of complex and variable attributes, and measuring these attributes accurately and reliably is a major challenge for the industry. In this paper, we investigate creating a surface model of plant from images taken by a stereo pair of cameras. The proposed modelling architecture comprises a fast stereo algorithm to estimate depths in the scene and a model of the scene based on visual appearance and 3D geometry measurements. Our stereo algorithm employs a coarse-fine strategy for disparity estimation. We develop a weighting method and use Kalman filter to refine estimations across scales. A self-organising map is applied to reconstruct a surface from these sample points created by the stereo algorithm. We compare and evaluate our stereo results against other popular stereo algorithms, and also demonstrate that the proposed surface model can be used to extract useful plant features that can be of importance in plant management and assessing quality for marketing.

[1]  J. P. Lewis,et al.  Fast Template Matching , 2009 .

[2]  Shabtai Bittman,et al.  Automated monitoring of greenhouse crops , 2001 .

[3]  C. D. Kuglin,et al.  The phase correlation image alignment method , 1975 .

[4]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

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

[6]  Carlo Tomasi,et al.  A Pixel Dissimilarity Measure That Is Insensitive to Image Sampling , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Carlo Tomasi,et al.  Depth Discontinuities by Pixel-to-Pixel Stereo , 1999, International Journal of Computer Vision.

[8]  Jorma Laaksonen,et al.  SOM_PAK: The Self-Organizing Map Program Package , 1996 .

[9]  Nanning Zheng,et al.  Stereo Matching Using Belief Propagation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[11]  Vladimir Kolmogorov,et al.  Computing visual correspondence with occlusions using graph cuts , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[12]  J. L. Roux.  An Introduction to the Kalman Filter , 2003 .

[13]  Edward H. Adelson,et al.  PYRAMID METHODS IN IMAGE PROCESSING. , 1984 .

[14]  David Vernon,et al.  Machine vision - automated visual inspection and robot vision , 1991 .