Personal Accomplishments
This week I’ve been working on integrating the backend code, the frontend code, and the hardware components to prepare for the interim demo. Our voice-operated system is now capable of detecting presence of customers, responding to their speech, and place orders. However, there are still a few minor bugs that pop up occasionally due to unhandled edge cases. For example, there is a particular thread that occasionally crash unexpectedly, whereas this issue does not occur on a Mac. We plan to address these issues next week. Overall, we’re in good shape for the demo. In additional to the integration, I’ve been doing some research on utilizing three extra PIR sensors (right now we are using just one) or a combo of a webcam and OpenCV to provide a more detailed understanding of the presence of a customer. I’ve narrowed down to an algorithm called Multiple Sensor Fusion, the process of combining sensor data or data derived from disparate sources such that the resulting information has less uncertainty than would be possible when these sources were used individually. While OpenCV is a viable option, I’m leaning towards a more “hardware” approach, which is using sensors, as this is an ECE project.
On schedule
Yes, my progress is on schedule.
Next week
I’ll be collaborating with Nina to make sure that our code is compatible with the Raspberry Pi. Additionally, I’ll be working on developing code to implement Multiple Sensor Fusion and see if it works better.