Object Detection
My initial approach to object detection was using TensorFlow to recognize objects, and while I was able to do this via tutorials online [ref: https://towardsdatascience.com/real-time-object-tracking-with-tensorflow-raspberry-pi-and-pan-tilt-hat-2aeaef47e134, this was a pretty good resource]. However, I quickly realized that TensorFlow's robustness and preloaded object detection algorithms are too complex for the purpose of my project. At this point I had one of two options 1) continue with TensorFlow and use a process called transfer learning (change up the top few layers of the CNN), or 2) proceed with a more computer vision-focused approach, and start by using OpenCV. I decided to do the latter for now because that is what I have more experience in, and I spent a great deal of time downloading the necessary software. I used a tutorial online to do edge detection for images, as this is the first step to the object detection that is necessary for the project [ref: https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_canny/py_canny.html]. I modified the parameters used in the Canny method to improve the edge detection precision.