This week was the final push for integration. I met up almost daily with Heather and Anna to make sure that everything was connected properly. I also had to program a lot more solutions since we also changed how the motors would be moving. The motors still had a limited range but in order to still center a face in those cases I manually cropped the frame as much as possible to then add a black border to create an…
This week I spent time to better enhance the video feed that was being passed to the computer. It was easier than expected since we only needed to change how our windows were instantiated. After doing so I then began the code to better detect a speaker when there are multiple faces. The algorithm is still quite naive but in order to increase correctness I went about to consider the following things. The first was to account for issues caused…
This week we had started off preparing for the first demo. Since we got chosen for a later date we met again to discuss if we would continue working on the project for the first demo. We spent time preparing through a practice demo amongst ourselves and had all the parts ready to demo for Vyas and Cindy. Given the new arrangements with the video passthrough, I realized that we can now fully utilize the two cameras set up. Since…
So this week I was able to make some more progress with Heather in terms of getting a video feed through to a computer. We were able to send a receive video through gstreamer from the nano to the computer and see some of the frames. The big issue that still remains here is that the streaming of the bits may not be fast enough but we might be able to make use of a better streaming protocol using ethernet…
Earlier this week I was able to restructure the code that we previously used for testing and merged it into the new framework. It still needs a little more robust testing and the new servo motor control still needs to be added back in since right now the motors that do work are just the stepper motors. I also finally defined the final messages that will be sent to motors and that are expected by each of the programs. If…
Early in the week we spent finalizing the last portions of the design report. We all spent time proofreading the document and writing the last couple of paragraphs. After that I focused primarily on the integration between different components of the project. With the first demo coming so soon we felt that cutting out some of the software features and implementing them later was a better approach so we decided to start with integration The first thing I did this…
This week the team’s overall deliverable of the design review report led to me spending a lot of time on that rather than additional development on the software code base. We spent the beginning of the week wrapping up the presentation slides on Sunday which ate a chunk of my time. In the middle of the week I spent time looking into the additional libraries we could use for the concurrency and came to the conclusion that using the base…
This week I was able to have the set up for OpenCV up and running on the Jetson TX2. After doing research and looking into haar cascade models that are available to the public, we were able to get it working for facial recognition. I think that this is most likely the option to go with but more testing needs to be done on how well it can detect a face. I’ve also optimized the program to be less laggy…
This week I began by continuing research into openCV while I awaited confirmation for the Jetson Nano working from Heather. I began the code development on my personal machine and had success in setting up and running some code for face detection. On Wednesday I was able to actually borrow a Jetson TX2 from the capstone resources but ran into peripheral issues and had to wait for new peripherals to use for it. I again ran into some complications with…