by Kristiina KergeChoose a language:
4. June 2019, 20:22
Let`s Do It Foundation makes AI to map waste
Let’s Do It Foundation and SIFR in partnership with Microsoft, have developed an AI algorithm for detecting trash in geolocated images and videos.
I am charmed by ambitious plans and eager to seek solutions for complex challenges. That is why I joined Let’s Do It Foundation in 2010 to help to share awareness about environmental problems and connect technology with people. Last Friday on 31 May at the AI for Good Summit https://aiforgood.itu.int/ I had an opportunity to present new AI solution to detect waste from images and videos.
We, Let’s Do It Foundation and SIFR in partnership with Microsoft, have developed an AI algorithm for detecting trash in geolocated images and videos.
Not everything that LOOKS like trash IS trash.
Trash is a word people use of an object that lacks purpose, and the purpose of an object is often not obvious in the images we use for teaching an algorithm to spot trash.
We started with a sample of images, trained the model, and analysed the results. Based on the results, we determined what images we had to add to the next iteration of training.
Detailed overview how we did it is here http://ai.letsdoitworld.org/
The code is in GitHub https://github.com/letsdoitworld/wcd-ai Take a look and give us a Star!
The team behind the new solution is data driven, passionate and dedicated:
Last year Let’s Do It Foundation World Cleanup Day camping and Mapping campaigns brought to cleanups 18M people and they collected 80K tonnes of garbage in one day. What we achieved: prioritized the topic, proved that people care.
Currently Let’s Do It Foundation main activity is capacity building to move from cleanups to circular economy and zero waste solutions embracing the power of technology. Our aim is to end mismanaged waste by bringing attention to the resources that are being wasted and polluting our communities. Mismanaged waste is waste that falls out of the reuse/compost/recycling schemes and ends up burned, buried or dumped in the nature.
Making the mismanaged waste challenge clear and understandable, collecting, analysing and visualising data relates to 9 SDGs
Feel free to contact us with your questions and proposals: