Jenny Han, Bradley Zhou, Jade Wang. Carnegie Mellon ECE Capstone, Spring 2021
This week we worked on the distance module and tried to ensure the accuracy of our own device. We tried to use double integration to calculate the displacement. However, using double integration caused a lot of error which made it challenging to use the pen …
This week I worked on the calibration module and tried to get a reasonable accuracy with it. However, my team ran into the issue that double integration over acceleration caused issues in the calibration because the integration emphasized the inaccuracy. To deal with this, we …
This week I worked on the hand gesture model and the pen.
For the hand gestures, I marked the dataset and cleaned it:
After that, I trained and tested the model. Here are the results:
For the pen, I helped wire the accelerometer and Bluetooth components. I got the accelerometer reading data points and the Bluetooth component sending over the information to a Windows computer. I helped debug the software and hardware elements.
I think we are on track to completing the projector. This week I will focus on getting the pen to send click data as well as work on the projector element.
This week I worked on the design report and helped write the software implementation, introduction, software testing plan, schedule, and task breakdown sections. I also helped to revise and edit our report. In terms of the project, I worked on the gesture recognizer. I got …
This week, we finalized the Design Presentation Slides/speaker notes. We met a few times to discuss the feedback we got regarding our presentation regarding content. This week, we will focus on fleshing out timing measures of the Python code and more specific definitions of inputs/outputs of …
This week my team and I met to discuss in detail the specs of our implementation of Magic Mice. Specifically, I helped design how the software would be laid out and how individual components would communicate with each other. I did this by doing more research into how to train a neural network to detect gestures with OpenCV in python.
Also, I met with my team to discuss how to partition the Design Report. Here, I will be detailing the software design requirements, implementation, and testing. Finally, I helped Jade refine her oral presentation as well as create the design presentation slides and speaker notes for metrics, requirements, scheduling.
This week, I plan on finalizing all the functions we need on the software side as well as the input outputs for all the functions. With this, I can start to write code and training our model.
This week we worked on finalizing the design review presentation. We met 4 times this week to talk about the system design and making sure everyone had the same vision for the project. We finalized how each part was going to communicate with each other, …
This week I finalized the Design Presentation. For this, I helped create a visual block diagram for our solution approach hardware and software versions. I also created the presentation visuals and speaker notes for the application area, project management, and metric validation slides. I tried …
Overall, we are on track. The biggest risk for our project at the moment is if we mess up some part of our hardware and need to reorder different parts and try again. We decided to mitigate this by buying a couple of parts as they are cheap. Also, we wanted to make sure we always had backup hardware in case something happened to our final. This way, we could always roll back to the most recent version. By the end of next week, we will have ordered our parts and started to put together the hardware.
No major system changes have been made. In a team vote, we decided to move away from OpenPose and use OpenCV instead due to higher accuracy and a lighter-weight system.
This week, we worked on figuring out our system design and what parts to buy.
For our system design, we finalized how things were going to communicate with each other, how the user would interact with the system, and what software we would be using.
For buying parts, we looked into different functionality we needed and did research on how other people implemented similar ideas, how different parts were compatible with each other, and the cost o the parts. We found links to the items we wanted to buy and compiled them together, ensuring that we had everything to fulfill our requirements.
This week I did research on the different technologies we should use to implement our project. Specifically, I looked into parts for the Arduino including the Bluetooth module, accelerometer, and projector. I also looked into how these parts would fit together and if there was …