For me, this week was mainly focused on fleshing out the computer vision component of our project. Originally, we had planned to utilize an existing model and made modifications to that model as well as integrating it into our system. However, after further discussion and research, we decided we would learn more by creating our own model. This would allow us to showcase our prowess, while also achieving viable results. Here is a bulleted list of the tasks completed:
- Conducted research on existing computer vision models
- Noted the methods varying projects attempted and what level of success was achieved with each
- Chose to utilize a convolutional neural network within Pytorch
- This will allow us to run our model using CUDA software on the Jetson so that processing is in real-time
- Created the final design presentation
- Conducted research on existing facial recognition models to understand the limits of our project in terms of latency and accuracy
- Set an accuracy goal of 70-75%
- Lead discussion with my teammates regarding my choices for the model allowing for feedback
- Updated my part of the schedule to reflect the start of my work on our computer vision component
- Attended 2 team meetings to work together with teammates
- Found 2 existing datasets that we might use for our machine-learning model
I’d say that we are on schedule.
Goals for next week:
- Submit orders for our hardware components to ensure they come on time
- Get more feedback from our peers during the design presentation and make reasonable changes if any problems are noticed