This week we tried to get all of our stuff running together integrated on the pi. The first issue that occurred is when running my cv stuff on the pi, we realized that it was very slow (despite being very fast on my computer), as it took 17 seconds on the pi and only 1 second on my laptop. So I re-wrote all of the cv stuff to be the exact same algorithm I had but very efficient (I had implemented a lot of it with the ability to debug in mind rather than sheer speed), and I was able to get it down to less than a second for all of the image processing. The next issue that occurred was that we realized that the way we were taking the picture on the raspberry pi took about 5.7 seconds to take the picture, and we can’t have that, so I found a new way of taking pictures that takes less than a second. The picture size, etc. was very different with the new method, so I’ve had to change up a lot of the parameters I was using for object recognition to work with the new pictures. After we got all of that working, we were able to successfully integrate my and Will’s parts, and begin the process of testing and tweaking our algorithms so they actually work well. Next we tried to integrate Alli’s part with our’s (which should have been seamless), but we are currently trying to fix a very weird bug with that. Tomorrow we would like to ideally fix the bug we are having, as well as try a bunch of tests to get preliminary results for our slides, as well as make our slides. After that it’s mostly just testing and tweaking everything to get it all working as best as we can before the demo. We have the end to end time of our system down to about 2 seconds, which is much faster than we thought, and everything seems to be looking pretty good, so it’s really just trying to get everything to finish line.