The problem Pose-Bot solves

Pose-Bot

Inspiration ⚡

In these difficult times, where everyone is forced to work remotely and with the mode of schools and colleges going digital, students are
spending time on the screen than ever before, it not only affects student but also employees who have to sit for hours in front of the screen. Prolonged exposure to computer screen and sitting in a bad posture can cause severe health problems like postural dysfunction and affect one's eyes. Therefore, we present to you Pose-Bot.

What it does 🤖

We created this application to help users maintain a good posture and save from early signs of postural imbalance and protect your vision, this application uses a
image classifier from teachable machines, which is a Google API to detect user's posture and notifies the user to correct their posture or move away
from the screen when they may not notice it. It notifies the user when he/she is sitting in a bad position or is too close to the screen.

We first trained the model on the Google API to detect good posture/bad posture and if the user is too close to the screen. Then integrated the model to our application.
We created a notification service so that the user can use any other site and simultaneously get notified if their posture is bad. We have also included EchoAR models to educate the children about the harms of sitting in a bad position and importance of healthy eyes 👀.

Challenges we ran into

• Creating a model with good acccuracy in a general setting.
• Reverse engineering the Teachable Machine's Web Plugin snippet to aggregate data and then display notification at certain time interval.
• Integrating the model into our website.
• Embedding EchoAR models to educate the children about the harms to sitting in a bad position and importance of healthy eyes.
• Deploying the application.