Hacker News new | past | comments | ask | show | jobs | submit login

Any computer vision / machine learning experts want to weigh in on the difficulty involved in writing an algorithm to visually detect drowning?




You'll need loads of (labeled) training data. And I'm afraid there is no good way to create such a labeled dataset. Unless we'd put some people who can't swim in a pool.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: