This week, we all worked on our individual design block diagrams for the design review presentation, looked into more risk factors, and began implementing our components. We also ordered all the materials we need and we have received most of them. We made a list of bills and materials and are working on the design documentation report as well.
Hiroko looked into the sensors she will be working with and ordered all the materials that she needed and picked up a few from Home Depot. Then, she made a visual design of how the greenhouse will look like and created the hardware block diagram which specified all the relays and feedback loops in the system. She also signed up for access to TechSpark in order to solder the sensors to the ESP32 , and hopes to receive some help from TAs to properly soldering the sensors. Kanon created the website login and registration as well as the main page where there is a toggle to change temperature, a switch for turning on/ off the light, a. soil moisture modifier, and a section for putting the live stream video later on. She also found Twilio, an API aids in notifications and alerts to users, which would help our project significantly. She updated her block diagram with the Twilio API included. Sarah researched the OpenCV modules more, and layed out the algorithms and components she would need to properly implement a CV application for plants. In specific, she figured out HSV Color detection and edge detection for images. She also received her materials and is setting up the hardware to do proper CV analysis.
Some risks we are looking into is receiving the wrong data from the database, and to mitigate this issue we are thinking about either regaining the data before outputting the value to the website or to notify the website if drastic changes take place. We are also hoping that the night vision in the IR-Cut cameras will work properly, but in the case that it does not we will need to reconfigure the LED lights to be on a certain brightness for night vision to work. After testing the OpenCV module, we found it very important that the subject we are analyzing contrasts with the background or the unnecessary components of an image, so we are looking into making a monochrome backdrop in the greenhouse that provides the best contrast. Any unexpected issues that we may come across with the hardware, we have decided that our system will be able to detect and notify the user about it.
We updated our schedule a bit to figure out when to start planting the pea shoots and which tests we will be conducting on which days. We’ve decided that we would plant the pea shoots a week before testing, as it takes around 7 days for pea shoots to sprout and grow. Below are also some images of visible progress.
Web site progress:
