We have completed most of our project, so the most significant risk could be when we gather the metrics that we need for our final presentation. Some of the metrics such as system latency, accuracy, etc. may be rather difficult to collect and require a large amount of data to make an accurate metric assessment. In order to manage these risks, we have discussed exact plans about how we will be testing every single one of the metrics so we can properly assess how our system works. Vaheeshta has started writing a script for getting the metrics for eye classification from various datasets, so we will continue doing similar scripts for the other metrics to make it easier to test.
There were no major changes made to the existing design of the system. However, we have decided to completely forego doing head pose calibration during the calibration step, as we believe that just having a pre-trained data set will be faster and simpler. We have been having some issues with head pose calibration, so this should help the program run more smoothly. Vaheeshta has found some datasets for this which we will be finishing up this week.
We have gotten the audio prompts completely working and have added both the left and down direction to our head pose estimation. Thus, we are pretty much done with our project, and we just need to spend the next week fine tuning our hardware setup and getting prepared for the final presentation and gathering metrics by testing in the car.