Significant Risks
- Motion tracking is functional but needs smoothing. Sometimes there is a jittering effect when holding the glove still.
- We solved the previous risk of IR LEDs needing a certain orientation to be detected by reducing the resistance of the resistor, and now they are bright from all angles.
- From the very beginning of the project we decided to focus mostly on the glove, and the AR aspect was intentionally left as a ‘nice to have’. We are able to plug a webcam into the laptop and show the game with a background of the player’s living room for example, but it is not very intuitive. It would be better if the game was being displayed on true AR goggles, but this was not in our original scope so it is unlikely that we will attempt to add that.
Changes Made
- We actually changed back to infrared LED tracking with a Gaussian blur to differentiate it from other bright objects in the room. Currently motion tracking works very well in low-light rooms.
- We are back to our original plan of the game running on the laptop. The player simply then plugs in the Raspberry Pi system over USB and the data is transmit via a serial connection, as outlined in our original design.
Schedule
We are back on schedule. Our MVP is nearing completion for the demo this week. For the remainder of the semester we will be using the pre-planned slack time to further improve our system. This includes work on the tracking algorithms to work better in rooms with other light sources, improvements to the game interface itself, as well as integrating IMU data into our motion tracking to develop a predictive algorithm.