Author: tzenchun

Last report!

After testing our replacement camera last week, we now need to test our new camera. This past week hasn’t seen much work on my end, as I’ve been swamped with other coursework, but as our system is effectively complete, it was not a big deal.

On top of new camera work, there’s also final deliverable work to be done such as the poster and demo preparation. We’ll need to collect a good representative video to showcase our device working.

Progress is on track.

Final week is coming up, more of the same of putting the finishing touches on our system. On my end this means in person testing of the camera. To this end, I’ve created python scripts for on boot recording and image capture. The major threat to the overall success is the replacement camera not arriving. It should have arrived last week, yet is still not here. Contingencies include using our MVP camera with no IR capability, or using the arducam.

Tomorrow will be going into the real world and getting our tests done, along with presentation work. Progress is on track, aside from the camera there are no concerns.

What I’ve needed to learn for this capstone project was the art of device selection and a shift in mentality to start working and ask questions later. By recognizing that the only way to solidify the knowledge from reading articles on the internet was to simply start working on something, things become so much clearer.

Post Carnival and demo day we are in the final stretch. There are no major threats to the overall success of the project anymore, as we have our MVP and are currently only iterating and testing full capabilities at this point. Feedback from said demo day was encouraging, as it was all positives and suggestions on how to proceed for the final showcase.

This week I focused on the final steps in making our system into a true dashcam, meaning the adapters and code for video capture. I also drafted a testing plan which includes taking our system into a vehicle and capturing footage for showcase. Next would be actually getting that footage, which will be next week when the newly ordered parts get picked up. Upon getting that footage and images at the design document specified distances, I would then run our model on it and measure/validate performance.

Progress is on track, and once again there are no concerns.

With the demo being Monday, we have all systems working right now besides the camera, which is alarming to say the least. The camera that we originally intended to use, the camera module 3 was being programmed and almost done, with pictures being taken and everything. Our backup camera is working though, but the problem with that is that it is a much more advanced camera, needing lots of configuration.

So right now we are working on our third alternative, a usb webcam that is acting as a substitute, which should need much less configuring than the arducam first backup. While hairy, we are on track to have a successful demo.

Ideally I would have been finishing the integration of UI, raspberry pi, and physical components, but I’ve been stuck on getting the main camera program working. The issue is that the camera appears to be plugged in, but is not detected by the computer. This is strange as before it was working just fine and we were able to take pictures with it.

Aside from the camera, much of the work this week was the ethics assignments, as it was a really unexpected time sink. Currently I need to solve the camera connection issue as soon as possible, and get back to work on other parts of the project where I’m needed like the UI.

Progress is currently behind schedule because of the camera hiccups and the ethics work, but with a bit of extra elbow grease next week we should be back on track. (Hopefully.)

This week was dedicated to coding all the systems together. I worked on adapting the OCR models to functions that can be called in a main routine on the raspberry pi. The supabase is created and linked to the pi as well, and work has begun on the front end implementation.

In addition to adapting the OCR models, I also began work coding the camera to take images in our program. This was done through using the picamera2 libraries. An unforeseen obstacle is the sheer depth of configuration that one can do on the settings of the camera. I sill need to work through what are the optimal settings for us, and if there should be some form of dynamic camera configurations for different conditions.

The next steps would be to determine what is the best way to host the UI frontend and begin significant work on that portion. Next week will be working on the UI and testing our current code on the pi and camera. Progress is on schedule, no concerns on my end.

This week I configured the raspberry pi. This included installing a new headless OS for improved performance, and configuring the IPv4 address to allow for remote ssh. This allows us to set the raspberry pi up on CMU wifi and let us ssh into it to program it from wherever we are. The github repo is now also installed on it and progressing towards basic integration.

I didn’t get to creating a table and linking supabase to a user interface yet, but I have been looking into setting it up on a github domain. Now instead of zero cameras we have two cameras, and one cable to test the feedback from the other similar group that we may not have the requisite resolution.

Another significant part of the work this past week was the design report. I handled the Introduction and Project management sections, along with the Testing and Verification sections. While the design report seemed simple on its surface, actually putting every idea down in writing had a very clarifying effect on the overall direction of the project.

Progress is on schedule and now that all major components are here progress will go even smoother.

This week had a spanner thrown into the plans. On top of a very important presentation for EPP that took more time out of my week than usual, the design presentation unveiled new considerations that need to be looked into.

The work that went into the design presentation helped the team straighten out the exact direction we want to head in, and the post-presentation feedback from professor Brumley was also extremely helpful. To incorporate that feedback into something tangible, I’ve been tinkering with Supabase and lovable.ai. Another group brought up that there may be an issue in our selected camera, and I’ve been doing some research into camera resolution, field of view, and how that relates to clarity at a distance.

What’s worrying is I haven’t received an email about our camera being delivered (suitable or not), and although the raspberry pi repository hasn’t been fully fleshed out yet I have a more complete picture of what needs to be done. Next week I should be more free to steam ahead and catch back up.