Progress Report #2: (11/6)
Goals:
- Figure out how to communicate data between 2 Google AIY kits.
- Finalize infrared lights, sensors, lenses, and servo motors that would work best with our project.
- Test convolutional neural nets with tensor flow.
- Figure out a signal processing algorithm to achieve clear signal (long-term goal that necessitates a prototype).
Progress:
This week we wrote a Project Design Report outlining our needs, design, schedule, team overview, and a log of meetings with our adviser. This helps to detail our progress thus far and reaffirm our aims for the project. The design aspects are a good base for future goals in our project. A presentation of our specific project was done this week which yielded a good number of useful questions and design considerations moving forward.
A weekly group meeting time has been solidified to aid in consistent productivity. With our approach for the project well-defined, accomplishing our current goals should lead to a rough concept prototype. Teams within our group have been given separate tasks. Computer engineers are focusing on convolutional neural nets. Electrical engineers are focusing on hardware parts – motor, infrared lights, sensors. Biomedical engineers are looking at lenses and researching pulse
To be done:
Focus efforts into researching parts based on our needs, cost, availability, and functionality. Finalize a part list which focus on the infrared lights and the lens; a movable camera may take more thought to achieve. Then, meeting with our adviser to put in an order for parts is a priority.
Linking both Google AIY kits using online tutorials will be key. Data can be displayed on a monitor and that has been proven. However, getting data to output to another modivius chip in a format that can be read will be key. Another problem factor is the timing between data transfer. To have a camera move to follow a face, data must be processed quickly and without sufficient lag.