This week was a big week for us in terms of getting off the ground with our Nano development. We got our camera working with the Nano and now have our backend up and running on the board and are able to interface with the camera. While there are still some hurdles to clear on this front this is a massive improvement over where we were a week ago as now we essentially have a working video camera system, with many of the capabilities we were planning to implement now implemented.
We also have the CNC for the camera case made and sent off to TechSpark, so hopefully next week sometime we are able to pick up the finished product and see if it’ll work and if we should iterate on it again. We designed the case with the battery in mind but also left a small hole in the back so its possible to plug it in if the battery doesn’t properly fit.
Our CNN is still getting worked on, but is getting closer than it was before. The current iteration of weights now don’t negatively effect the image and more or less have minimum impact, which we think, while not ideal and obviously not achieving our goal of spatially invariant blur deblurring, is a step in the right direction and should hopefully allow us to implement the CNN with the rest of the system such that even if it doesn’t have much of an impact as planned it’ll give us the complete system that we’d proposed and worked towards.
0 Comments