Project Idea
For my final project, I was thinking of creating an interactive website where users can learn yoga themselves and have a greater appreciation for the practice of it. Essentially, users can choose from several images of yoga poses and try to imitate them. Based on how accurate their poses are, parts of their environment will change to match the pose name. If their pose is completely accurate, they themselves will become the animal/object the pose is named after.
For example, “downwards dog” is a famous yoga pose. If a users pose is 50% accurate, perhaps only the background image on the web screen will become a backyard, but at 100% accurate, the user will become a downwards facing dog.
Inspiration
I was inspired by both the names of certain yoga poses and by one of my favorite childhood Wii games, WarioWare Smooth Moves. I always found the names of certain yoga poses really interesting/amusing, such as “downwards dog”, “cat”, etc. and always wondered if these poses were actually similar to the animals/objects they were named after. As for the Wii game, there is a part in the game where players have to follow designated poses in order to earn a point. The game is typically fast paced but there are random “yoga” poses that are thrown in to give users a break. Here is a link to a game play to understand (skip to 3:30).
Developing the Project
Yoga comes from India, which is a country that heavily believes in Hinduism. After looking into Hinduism, it really values nature and respects it which is why I want to make users grow their appreciation and understanding of the poses. Because yoga is often very calm and spiritual, I want to try and keep the environment/user changes serene and very nature-like.
Technically speaking, I would like to follow the code that Professor Moon provided our class, which uses the KNN classification, mobileNet, and webcame iamges. This means that I’m going to need to gather a database of images of people’s poses for the yoga poses. Because my project would involve a lot of body movement, I realized it would be difficult for users to capture an image of themselves without breaking the pose. So, I will also try to incorporate voice recognition to trigger a image capture. Aside from the KNN classification, mobileNet, and voice recognition, I think the remainder of the project will just be very css heavy.