Automatic Generation of Feature Inventory from 3D Point Cloud

Supervisor: Dr Yonghuai Liu (yyl@aber.ac.uk)

3D point clouds can be captured using various devices such as laser range finders and stereo vision systems [4]. However, it is challenging to understand what these point clouds represent. This project intends to understand and create a semantic representation of these data [1, 2 ]. To this end, various techniques [3] will be developed to segment and cluster the points according to various structural consistency: geometry, function, structure, etc. To facilitate the data understanding, the prior knowledge about the object category and structure may be formalized[1].

References

[1] F. Boudon, C. Pradal, T. Cokelaer, P. Prusinkiewicz and C. Godin. L-Py: an L-system simulation framework for modeling plant architecture development based on a dynamic language. Front. Plant Sci., 30 May 2012
[2] Marin Talbot Brewer, Lixin Lang, Kikuo Fujimura, Nancy Dujmovic, Simon Gray and Esther van der Knaap. Development of a Controlled Vocabulary and Software Application to Analyze Fruit Shape Variation in Tomato and Other Plant Species. Plant Physiology May 2006 vol. 141 no. 1 15-25
[3] C. Moenning, N. Dodgson. A new point cloud simplification algorithm. Proc. IASTED Int. Conf. Visualization, Imaging, and Image Processing, 2003.
[4] http://www.riegl.com/uploads/tx_pxpriegldownloads/DataSheet_VZ-6000_19-11-2012_PRELIMINARY.pdf