- Accomplished this week: This week I first worked on the UI with Adriana then focused on tweaking the calibration and classification code for our device. For the UI, we first did some research into integrating UI such as tkinter with our OpenCV code but we realized this may be difficult. So we decided to make buttons by creating a box and when a click occurs in the box an action should occur. We then designed our very simple UI flow. I also spent some time working on a friendly logo for our device. This was what we designed. Our flow starts at the top left box with our CarMa Logo then goes on to the Calibration step below. Then tells the user it is ready to begin.
Once we designed this. We simply coded up the connection between pages and connected the UI to our current calibration and main process code. We needed to work on connecting the calibration because this step required the real time video whereas for the main process we are not planning on showing the user any video. We only sound the alert if required. After we completed the UI, I started working on tweaks for the calibration and classification code for the board. When we ran our code some small things were off such as the drawn red ellipse the user is attempting to align their face with. For this I adjusted the red ellipse dimensions but also made it easier for us later on to simply change the x, y, w, h constants with out go through the code and understand values. Once I completed this, I started working on adjusting our classification to fit the board. I also started working on the final presentation Power Point slides. - Progress: I am currently ahead of our must recent schedule. We planned to have the UI completed this week. We completed this early and started working on auxiliary items.
- Next week I hope to complete the final presentation and potentially work on the thresholding. I am wondering if this is the reason the classification of the eye direction is not great. We also need to complete a final demo video.
Carnegie Mellon ECE Capstone, Spring 2021: Adriana Martinez, Jananni Rathnagiri, Evann Wu