Bayesian filter

In our work we are going to use a Bayesian filter to do the estimating of the position of the pictures that are being handed in. Given that the input data will include matches between points that will suggest very different possible points therefore filters that use a single modal function to represent their hypothesis are unsuitable for our purpose. Therefore we need to use Bayesian filters that can represent several hypothesis.

Platform implementation for hierarchical localization

I need a platform for performing my tests and then implementing the system. There are several requirements for this platform. It has to provide basic image manipulation capabilities, It should help with performing tests and in the end I should be able to use it for implementing the final solution.

So what I have started to build my work on top of openCV that provides great vision features. Currently it reads a map from a directory of images and extracts SIFT features from that map. I have used a code by Rob Hess for the SIFT extraction (The code is clean (bad naming though) but I think some rather unconventional methods were used :( ).

Furthermore I extract features from a given image and match them with the features from the map. These matches will be used to aid a particle filter component provide the location of a given image in relation to the map.