Week 5 Post 2

I got more clarification on my current status with the project today. It was very helpful to have a meeting with Mythra, the person with whom I worked on the project. He explained to me that even though he is leaving for three weeks to go to another country, he will still be available via Zoom. However, there is another thing that worries me about this situation, which is the almost 10-hour time difference between the countries. He assured me that the communication would still be on the same level, though, so I feel better. This means that I will continue working on the Arms project instead of switching to the other project that I was considering, which is quality assurance in ultrasound. That would have been very inconvenient to switch to a completely different project in the middle of my internship because, from what I know, they use other tools and concepts to work on the ultrasound images. I feel lucky for being in such a situation and still keeping the same project. Additionally, I progressed a lot on the project, and I got to the part where I did the actual coding, which made me happy because I was not writing the actual code until the fifth week of my internship. Now, since I am working with a convolutional neural network, I implemented an algorithm with the help of YOLO and openCV to process the videos of my hands moving in different directions. I found it super fun to be able to see the bounding box around my palm on the video with the confidence level that specifies whether it is a hand palm or not. The confidence level varies from 0 to 1. I wrote code for iterating through each frame of the video to recognize where the confidence level is above 0.65. If it is above this rate, then the video is good. However, most of my videos did not have that rate, so I had to redo them, which took me a long time. I feel exhausted today because of doing all the videos over again and checking their confidence level many times to be sure that they pass. The reason why I check the confidence level is because I want to extract the centroid with x and y values from that bounding box that YOLO creates around my palm. That centroid is helpful for me because I need to eliminate the unwanted background and only focus on my hand because that is what the robot is going to recognize to try to learn the gesture that I am showing in the video. Even though the first few weeks in the internship seemed a little boring due to the overwhelming amount of information and all the research papers that I needed to read, it now seems very exciting to be able to be practical and actually experiment with the algorithm, videos, and the 3D camera. I am delighted by the work that has already been done using YOLO and by the possibilities that are ahead. The more I work on the project, the more I realize that this is the future I want. I am more sure than ever now that I want to do a Master's degree after graduating from Berea College, and Purdue University seems to be a good fit. Perhaps, I will even do it in Robotics and get to the same lab I currently work in. I cannot wait to continue my exploration of AI and discover more amazing things that this field offers!