Denoising algorithms can alleviate the trade-off between noise-level and acquisition time that still exists for certain image types. Nonlocal means, a recently proposed technique, outperforms other methods in removing noise while retaining image structure, albeit at prohibitive computational cost. Modifications have been proposed to reduce the cost, but the method is still too slow for practical filtering of 3D images. This paper proposes a hashed approach to explicitly represent two summed frequency (hash) functions of local descriptors (patches), utilizing all available image data. Unlike other approaches, the hash spaces are discretized on a regular grid, so primarily linear operations are used. The large memory requirements are overcome by recursing the hash spaces. Additional speed gains are obtained by using a marginal linear interpolation method. Careful choice of the patch features results in high computational efficiency, at similar accuracies. The proposed approach can filter a 3D image in less than a minute versus 15 minutes to 3 hours for existing nonlocal means methods.

Mutual Information (MI) is popular for registration via function optimisation. This work proposes an inverse compositional formulation of MI for Levenberg-Marquardt optimisation. This yields a constant Hessian, which may be pre-computed. Speed improvements of 15% were obtained, with convergence accuracies similar to those of the standard formulation.

Recently, the Nonparametric (NP) Windows has been proposed to estimate the statistics of real 1D and 2D signals. NP Windows is accurate, because it is equivalent to sampling images at a high (infinite) resolution for an assumed interpolation model. This paper extends the proposed approach to consider joint distributions of image-pairs. Second, Green's Theorem is used to simplify the previous NP Windows algorithm. Finally, a resolution-aware NP Windows algorithm is proposed to improve robustness to relative scaling between an image pair. Comparative testing of 2D image registration was performed using translation-only and affine transformations. Although more expensive than other methods, NP Windows frequently demonstrated superior performance for bias (distance between ground truth and global maximum) and frequency of convergence. Unlike other methods, the number of samples and the number of bins have little effect on NP Windows and the prior selection of a kernel is not required.

An approach for fast tracking of arbitrary image features with no prior model and no offline learning stage is presented. Fast tracking is achieved using banks of linear displacement predictors learnt online. A multi-modal appearance model is also learnt on-the-fly that facilitates the selection of subsets of predictors suitable for prediction in the next frame. The approach is demonstrated in real-time on a number of challenging video sequences and experimentally compared to other simultaneous modeling and tracking approaches with favourable results.

This paper presents an approach to object tracking which, given a single example of a target, learns a hierarchical constellation model of appearance and structure on the fly. The model becomes more robust over time as evidence of the variability of the object is acquired and added to the model. Tracking is performed in an optimised Lucas-Kanade type framework, using Mutual Information as a similarity metric. Several novelties are presented: an improved template update strategy using Bayes theorem, a multi-tier model topology, and a semi-automatic testing method. A critical comparison with other methods is made using exhaustive testing. In all 11 challenging test sequences were used with a mean length of 568 frames. 1

A novel method for the simultaneous modeling and tracking (SMAT) of a feature set during motion sequence is proposed. The method requires no prior information. Instead the a posteriori distribution of appearance and shape is built up incrementally using an exemplar based approach. The resulting model is less optimal than when a priori data is used, but can be built in real-time. Data in any form may be used, provided a distance measure and a means to classify outliers exists. Here, a two tier implementation of SMAT is used: at the feature level, mutual information is used to track image patches; and at the object level, a structure model is built from the feature positions. As experiments demonstrate, the tracker is robust and operates in real-time without requiring prelearned data.