How a Little AI Helped Me Keep the World a Bit Safer —

Author(s): Prachi Tewari

Originally published on Towards AI.

This member-only story is on us. Upgrade to access all of Medium.

Imagine this: you’re scrolling through your phone with your morning coffee, and a headline grabs your attention — “AI Detects Knives in Real Time.” Pretty cool, right? That’s what I set out to build. My project uses AI to spot knives in surveillance footage, aiming to boost public safety in a simple but impactful way — nothing complicated, just effective.

Why Focus on Knives?Knives are useful tools, but in the wrong context, they can be dangerous. My project’s goal was to use AI to automatically detect knives in surveillance footage, which could help security systems become more proactive. The idea was to give security personnel an extra set of “eyes,” allowing them to spot threats quickly and act before it’s too late.

The Challenge — Getting the Right DatasetOne of the biggest challenges I faced was finding the right dataset. You’d think that a large dataset for knife detection would be easy to find, but I needed something without annotations, and that was much harder to come by. Annotating thousands of images manually is a massive task, so I decided to put together my own dataset of around 16,000 images —… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI