This week, the team worked on putting all the components together. Kanon and Hiroko worked on the communications between the website and the hardware, and recorded the test results to verify metrics have been met. Sarah came over to the greenhouse and recalibrated the CV application parameters based on the different lighting and picture quality from placing the plants in the greenhouse.
Some risks that we encountered this week were making the soil moisture sensors waterproof. Hiroko was able to find some heat shrinks in the ECE department and use that for the soil moisture. Sarah currently has a large false positive and negative rate on the dark spotting disease detection, so she is going to cover the area surrounding the plant with white paper to get more accurate testing results.
There were slight software infrastructure changes made to the CV Application. Instead of finding a stem, Sarah decided to measure bending by measuring the angle between the Y-axis and the line between the flower to the plant center, since this was a much more efficient and accurate way to detect stem bending. She has changed that in her block diagram.
We are on task so far, and Sarah and Kanon’s collaboration to embed the live stream on the website is the only thing pushed to this upcoming week.
