This week was spent getting the project far enough for the demo. I wrote the section picking algorithm for runners and biker’s, by implementing a knn influenced machine learning algorithm for picking the section most similar to the runner training images, and picking the section most similar to the biker images (total euclidean distance of closest k points), and going with the closer of the two. I also spent a good bit of time getting my stuff set up on the pi for the demo. Adding in cars shouldn’t be too bad, the only difference is that the sections for cars are different than runners and bikers. I was only using 4 online images each of runners and bikers for the demo, but I would like to collect training data with our camera now that our wearable is mostly constructed. I also spent a good bit of time this week getting it all set up so we could download Alli’s iOS App onto our phones. Next week I would like to implement the car part of the algorithm, and start collecting training data with our wearable (but that isn’t very easy to do until the rest of the wearable is built). After I have that, all that is left is fine tuning the algorithm based on testing, and what I have so far is all very low power and very fast, so neither of those should be a problem.