Refine
Year of publication
- 2005 (1)
Document Type
- Doctoral Thesis (1)
Language
- English (1)
Has Fulltext
- yes (1)
Is part of the Bibliography
- no (1)
Institute
- Physik (1)
In this thesis, we opened the door towards a novel estimation theory for homogeneous vectors and have taken several steps into this new and uncharted territory. Present state of the art for homogeneous estimation problems treats such vectors p 2 Pn as unit vectors embedded in Rn+1 and approximates the unit hypersphere by a tangent plane (which is a n-dimensional real space, thus having the same number of degrees of freedom as Pn). This approach allows to use known and established methods from real space (e.g. the variational approach which leads to the FNS algorithm), but it only works well for small errors and has several drawbacks: • The unit sphere is a two-sheeted covering space of the projective space. Embedding approaches cannot model this fact and therefore can cause a degradation of estimation quality. • Linearization breaks down if distributions are not highly concentrated (e.g. if data configurations approach degenerate situations). • While estimation in tangential planes is possible with little error, the characterization of uncertainties with covariance matrices is much more problematic. Covariance matrices are not suited for modelling axial uncertainties if distributions are not concentrated. Therefore, we linked approaches from directional statistics and estimation theory together. (Homogeneous) TLS estimation could be identified as central model for homogeneous estimation and links to axial statistics were established. In the first chapters, a unified estimation theory for the point data and axial data was developed. In contrast to present approaches, we identified axial data as a specific data model (and not just as directional data with symmetric probability density function); this led to the development of novel terms like axial mean vectors, axial variances and axial expectation values. Like a tunnel which is constructed from both ends simultaneously, we also drilled from the parameter estimation side towards directional/axial statistics in the second part. The presentation of parameter estimation given in this thesis deviates strongly from all known textbooks by presenting homogeneous estimation problems as a distinguished class of problems which calls for different estimation tools. Using the results from the first part, the TLS solution can be interpreted as the weighted anti-mean vector of an axial sample. This link allows to use our results from axial statistics; for instance, the certainty of the anti-mode (i.e. of the TLS solution!) can be described with a weighted Bingham distribution (see (3.91)). While present approaches are only interested in the eigenvector of the some matrix, we can now exploit the whole mean scatter matrix to describe TLS solution and its certainty. Algorithms like FNS, HEIV or renormalization were presented in a common context and linked to each other. One central result is that all iterative homogeneous estimation algorithms essentially minimize a series of evolving Rayleigh coefficients which corresponds to a series of (converging?) cost functions. Statistical optimization is only possible if we clearly identify every step as what it exactly is. For instance, the vague statement “solving Xp ... 0” means nothing but setting ˆp := arg minp pTXp pT p . We identified the most complex scenario for which closed form optimal solutions are possible (in terms of axial statistics: the type-I matrix weighted model). The IETLS approach which is developed in this thesis then solves general type-II matrix weighted problems with an iterative solution of a series of type-I matrix weighted problems. This approach also allows to built converging schemes including robust and/or constrained estimation – in contrast to other approaches which can have severe convergence problems even without such extensions if error levels are not low. Chapter 6 then is another big step forward. We presented the theoretical background of homogeneous estimation by introducing novel concepts like singular vector unbiasedness of random matrices and solved the problem of optimal estimation for correlated data. For instance, these results could be used for better estimation of local image orientation / optical flow (see section 7.2). At the end of this thesis, simulations and experiments for a few computer vision applications were presented; besides orientation estimation, especially the results for robust and constrained estimation for fundamental matrices is impressive. The novel algorithms are applicable for a lot of other applications not presented here, for instance camera calibration, factorization algorithm formulti-view structure from motion, or conic fitting. The fact that this work paved the way for a lot of further research is certainly a good sign.