Chapter 3 – View Extraction

Views are the fundamental elements of view-based 3-D object analysis and view extraction comprises the first step of this methodology. A group of carefully obtained views can provide a good foundation for further V3DOR. As a result, effective view acquisition techniques are highly desired for 3-D applications. There are generally three types of view extraction methods: dense sampling viewpoints, predefined camera arrays, and generated views. In the methods of dense sampling viewpoints, multiple views are captured from the densely sampled directions. In the second type of methods, multiple views can be collected by 2-D projections taken from canonical or noncanonical view directions and each projection is described by a 2-D image. Setting the camera array with view directions is the primary task related to view extraction. For the third type of methods, the view is generated from the 3-D object, as opposed to the direct graph or depth images. In this chapter, we introduce these three types of view extraction methods and discuss them in detail.

[1]  Ryutarou Ohbuchi,et al.  Dense sampling and fast encoding for 3D model retrieval using bag-of-visual features , 2009, CIVR '09.

[2]  Yue Gao,et al.  View-based 3D model retrieval with probabilistic graph model , 2010, Neurocomputing.

[3]  Ming Ouhyoung,et al.  On Visual Similarity Based 3D Model Retrieval , 2003, Comput. Graph. Forum.

[4]  Ryutarou Ohbuchi,et al.  Scale-weighted dense bag of visual features for 3D model retrieval from a partial view 3D model , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[5]  Mohamed Daoudi,et al.  A Bayesian 3-D Search Engine Using Adaptive Views Clustering , 2007, IEEE Transactions on Multimedia.

[6]  Ryutarou Ohbuchi,et al.  Salient local visual features for shape-based 3D model retrieval , 2008, 2008 IEEE International Conference on Shape Modeling and Applications.

[7]  Ioannis Pratikakis,et al.  PANORAMA: A 3D Shape Descriptor Based on Panoramic Views for Unsupervised 3D Object Retrieval , 2010, International Journal of Computer Vision.

[8]  Chang-Hsing Lee,et al.  A new 3D model retrieval approach based on the elevation descriptor , 2007, Pattern Recognit..

[9]  Petros Daras,et al.  A 3D Shape Retrieval Framework Supporting Multimodal Queries , 2010, International Journal of Computer Vision.

[10]  Mohamed Daoudi,et al.  A Bayesian approach for 3D models retrieval based on characteristic views , 2004, ICPR 2004.

[11]  Mohamed Daoudi,et al.  A Bayesian framework for 3D models retrieval based on characteristic views , 2004, Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004..

[12]  Yue Gao,et al.  3D model comparison using spatial structure circular descriptor , 2010, Pattern Recognit..