The last week or so has been spent trying to get over a problem with the training code however the inital problems has been fixed, Simular problem have arose later on in the training.
This week we had a meeting to discuss the inner workings of the classification part of the algorithm, specifically how the part based HOG detector worked. Which gave myself a better understanding of how the system actually works.
The current plan is to continue attempting to get the training working and then look in to how to used our data with the detector. This will involved some annotating of data and adjustments of the code.