During this week, my main focus was on setting up the verification vision systems for our live testing setup. I setup our newly ordered Raspberry on the CMU network, configuring it to automatically connect to the network on startup, and verifying that I could communicate with it through my laptop. After this configuring our verification system, we were able to record from multiple cameras at once. For now, our system is recording both the main detection camera feed with an additional verification feed for later analysis, as our current hardware can not reliably process more that one camera feed live.
My portion of the project remains on schedule. My upcoming objective is to further smoothen the recordings of our camera system on the CMU internet. While there are no bandwidth issues with sending our relatively small video frames over the CMU network, there continues to be spikes in our camera latency during our testing this week, most likely due to network instability on the CMU Wifi. It was discovered this week that these latency spikes are also causing the video recordings to skip around when video frames fail to be delivered. A goal for next week is to implement a synchronization system for our recordings, so that we can recover from these latency spikes while post processing our recordings.