If there's one thing that doesn't seem to suffer from supply chain problems, it's garbage. It's everywhere, easy to locate and - you think - pick up. Sadly, most of us see litter as someone else's problem, but with something like This Machine Vision Litter MapperYou can at least be part of the solution.
for the civic-minded [Nathaniel Felleke]In his native San Diego, the litter problem was getting worse. He argued that a map of where garbage is located could help municipal employees with cleanup, so he thought of creating a system to find garbage automatically. Using Edge Impulse and a collection of roadside images taken from a variety of sources, they built a model for recognizing waste. To find trash, a webcam with a car window mount captures images while driving, and a Raspberry Pi 4 model runs and looks for trash. When litter is found on the side of the road, the Pi uses a BlueZ wireless notecard to send the garbage's GPS location to a cloud database via its cellular modem.
wandering the streets of san diego, [Nathaniel]The system maintains a database of garbage hotspots. From there, it's pretty easy to pull in the data and overlay it on Google Maps to figure out where to put the trash. The video below shows his system in action.
Yes, driving around a private vehicle specifically for litter detection is adding more waste to the mix, but you'd imagine putting something like this on municipal vehicles that are already driving around cities. Either way, we picked up some neat tips, especially those wireless IoT cards. We've seen them used beforeBut [Nathaniel]The project gives us a way forward on some of the ideas that we've been inspired by for a while.
0 Comments