This thesis deals with the problem of three dimensional scene reconstruction from multiple camera images. This is a well established problem in computer vision and has been significantly researched. In recent years some excellent results have been achieved, however existing algorithms often fall short of many biological systems in terms of robustness and generality. The aim of this research was to develop improved algorithms for reconstructing 3D scenes, with a focus on accurate system modelling and correctly dealing with occlusions. With scene reconstruction the objective is to infer scene parameters describing the 3D structure of the scene from the data given by camera images. This is an illposed inverse problem, where an exact solution cannot be guaranteed. The use of a statistical approach to deal with the scene reconstruction problem is introduced and the differences between maximum a priori (MAP) and minimum mean square estimate (MMSE) considered. It is discussed how traditional stereo matching can be performed using a volumetric scene model. An improved model describing the relationship between the camera data and a discrete model of the scene is presented. This highlights some of the common causes of modelling errors, enabling them to be dealt with objectively. The problems posed by occlusions are considered. Using a greedy algorithm the scene is progressively reconstructed to account for visibility interactions between regions and the idea of a complete scene estimate is established. Some simple and improved techniques for reliably assigning opaque voxels are developed, making use of prior information. Problems with variations in the imaging convolution kernel between images motivate the development of a pixel dissimilarity measure. Belief propagation is then applied to better utilise prior information and obtain an improved global optimum. A new volumetric factor graph model is presented which represents the joint probability distribution of the scene and imaging system. By utilising the structure of the local compatibility functions, an efficient procedure for updating the messages is detailed. To help convergence, a novel approach of accentuating beliefs is shown. Results demonstrate the validity of this approach, however the reconstruction error is similar or slightly higher than from the Greedy algorithm. To simplify the volumetric model, a new approach to belief propagation is demonstrated by applying it to a dynamic model. This approach is developed as an alternative to the full volumetric model because it is less memory and computationally intensive. Using a factor graph, a volumetric known visibility model is presented which ensures the scene is complete with respect to all the camera images. Dynamic updating is also applied to a simpler single depth-map model. Results show this approach is unsuitable for the volumetric known visibility model, however, improved results are obtained with the simple depth-map model.
| Identifer | oai:union.ndltd.org:canterbury.ac.nz/oai:ir.canterbury.ac.nz:10092/1227 |
| Date | January 2007 |
| Creators | Forne, Christopher Jes |
| Publisher | University of Canterbury. Electrical and Computer Engineering |
| Source Sets | University of Canterbury |
| Language | English |
| Detected Language | English |
| Type | Electronic thesis or dissertation, Text |
| Rights | Copyright Christopher Jes Forne, http://library.canterbury.ac.nz/thesis/etheses_copyright.shtml |
| Relation | NZCU |
Page generated in 0.0021 seconds