The week of 12/4 I prepped the final presentation as well as the finishing touches on the system in general for the techspark expo next week. I worked with Alan on the cursor smoothness metrics and we talked about changing the system at a working level by changing which gestures correspond to what. Mainly, we changed click and drag to be a fist, and single click to be an ok sign. This coming week, we’re going to work on planning out the final report and video as well as the techspark demo. I also spent a good amount of time refactoring the code by placing it in classes to make it much neater, since we originally had all the gesture recognition and flow chart logic in the main function of the demo file, so I put that all in a separate class and just called the class functions in the main. I added comments on all the major functions as well, so if we want to reuse this code and work on it in the future, it will be easy to modify. Most of the brunt work for the project is done, and all that’s left is getting our metrics set for the final report including the user testing and questions that we will include in our final report. Overall, I am on track with my work, and we are set to be good for the presentation portions next week.
Brian’s Status Report for 12/4
For the final two weeks of the semester I scheduled most of my time for refining the feel of using our product as well as preparing for our final presentation and public demo.
For the refining portion, I added a minor smoothing to the movement of the mouse by averaging the location of the 6 landmarks surrounding the palm of the user’s hand.
Following that, the location of the hand is averaged across 3 frames of calculation to act as a low pass filter on the noise generated by our CV system.
Further, in order to circumvent an issue with the product where it could not differentiate between a click and a click and hold, I segmented each action into its own gesture. Click and drag/holding is now the closing of the hand into a fist, while a simple click is touching your index finger to your thumb, like an ASL number 9.
Finally, in preparing for our final demo and presentation I spent a few hours running experiments involving different model architectures and data augmentation to provide reasonable insight into tradeoffs and design decision outcomes.
Alan’s Status Report for 12/4
This week and last week, I started doing system and component testing of our project and worked on and presented the Final Presentation for our group. For our metrics, I ran a bunch of trails of our clicking detection and jitter distance tests to contribute results to our group average. I also helped in contributing code to increase smoothness of mouse movement (by averaging positional inputs) and increase practical detection of gestures (by adjusting the number of detections needed to execute a mouse function). The coming week, I will continue to gather metrics for the other mouse functions and work on the final deliverables. I will continue adjusting numbers in our code to get us the best measurements possible so that we can surpass our requirements. I will also get new users such as my roommates to participate in user testing. I am on schedule and should be good to meet the final deadlines and contribute towards giving a successful final demo.
Team Status Report for 12/4
This week and last week, the team started doing testing, verification, and metric collection alongside consistent integration and improvement of our system. All of the risks and challenges throughout the semester have been handled and at this point we are just working on refining our product to function as well as possible for the final demo. We are mostly doing testing and making small system changes and adjustments to meet/surpass our requirements. The schedule and design for our project is still the same, and we will be focusing on finishing the final deliverables in the coming week.