For my progress this week, it was threefold. The first aspect of this week involved trying to successfully boot up the Raspberry PI and SSH into it in a headless fashion since that is how it will be operating on the rover. However, I ran into some trouble earlier this week when I broke a microSD card while attempting the first boot, so progress on this front was delayed until the end of the week. Towards the end of the week, I successfully managed to SSH into the PI and register our devices MAC address to CMU-DEVICE.
The middle half of the week saw me spend pretty much all of Thursday doing the ethics assignment, and I found both readings extremely insightful.
The last part of my week involved installing dependencies and running the depthai software on the Raspberry Pi remotely through SSH. After doing research on the ColorCamera issue as stated in previous status reports, I might have found my issue, which is that when the device is connected to the Pi, and when it reconnects back to the host after performing inference, it is using a USB2 connection instead of a USB3 connection. One potential way to solve this is to reduce the data stream, but as of now I am unsure how to do this.
Currently, I am working on two different pipelines. MonoCamera -> Object Detection Pipeline and a depth pipeline that uses a colormap where I am trying to extract coordinate data and potentially link it with the Object Detection pipeline.
Currently, progress is behind because there are still issues with the camera being laggy on the Pi side as well as continued development that needs to be done with my two pipelines. With no exams this coming week, I hope to catch up to the project schedule by utilizing the week’s free time effectively.
In the next week, I hope to develop a pipeline that takes the closest depth value in an image as well as find a method to reduce data rate by potentially editing a bandwidth or FPS setting.