Inspiration
Approximately 9,500 deaths in older Americans are associated with falls each year. Falls are the leading cause of death from injury among people 65 and older. With a more effective monitoring system, we could minimize the damage falling could cause for the elder portion of the population.
What it does
The program employs deep learning model and could detect "falls". The program also detects the number of people present in the video. The program supports both real-time live camera detection and video detection.
How we built it
I used python and various libraries such as openCV, numpy, etc.
Challenges we ran into
The challenge I had was that the model could not effectively distinguish "sit" and "fall", but later was resolved when I obtained a larger data set. Additionally, working solo was a bit challenging as I had to figure out everything by myself, but I am glad it worked out.
Accomplishments that we're proud of
I am proud that I eventually managed to make the program work.
What we learned
I've learnt many things, one of which being coding effectively with time limit. I had to design the structure of my code previous to everything to make sure that I don't make any mistakes in the end, which would be extremely time consuming to debug.
What's next for Falling detection for the elders
This is merely a demo, I am trying to make a more legit version of it and possibly push it to the public.
Log in or sign up for Devpost to join the conversation.