Tracks

AI / ML & AR / VR

Inspiration

While talking about computer's camera it's necessary that it can recognize humans specifically so that while adding effects it doesn't become weird While we talk about creating any app or website like Snapchat or something related it's necessary to that the device is able to recognize human Even when we want to help Computers & Robots recognize Humans it's necessary that it doesn't recognize any human like animal such as chimpanzees, etc. or even some time others And there are many problemS like that in **AR & VR fields **so I have used here Mediapipe for solving it

  • So what is Media Pipe
    • Mediapipe is an open-source framework to “build word-class machine learning solutions” by Google — currently in the alpha stage. It has been open-sourced for a year now but has likely been under development for far longer. A key “selling” point (it’s free) of Mediapipe is that the code is written in c++, but it can easily be deployed to any platform, from web assembly to Android to MacOS. When it first released, Mediapipe had only a few demos, but now their GitHub page boasts almost a dozen different demos from persistent object tracking, AR hair coloring, to pose tracking that may leave OpenPose in the dust.

What it does

It can recognize any human who is infront of the cam and it will create a holistic frame over that human in screen which can help computers and machines to recognize humans

How I built it

  • HTML:- It was used to create for the front end part
  • CSS:- It was used to give some styling to the website
  • JavaScript:- It was used for the backend and realtime animation on the website and even it was used for connecting MediaPipe
  • MediaPipe:- It was used to creating a frame when a human is recognised on the cam
  • Artificial Intelligence / Machine Learning:- It was used for recognizing any human by providing it some datasets

Challenges we ran into

I was sufferring from an issue on recognizing any human who is available in the cam but I after that I used some MediaPipe datasets as well to recognize a human

Accomplishments that we're proud of

All the features majorly Human Recognition worked properly

What we learned

I learnt to integrate AI & DataSets in Javascript

What's next for Holistic Media Pipe

As soon as I work more on it I will soon add some more feature such as changing to different frames and so on..

Built With

Share this project:

Updates