Using AI to Keep City Clean Makes Amsterdam 2021 GO SMART Award Winner

Article By : GO SMART

Amsterdam is one of the recipients of the 2021 GO SMART Award for its smart city solution that detects street garbage with AI.

Amsterdam is one of the recipients of the 2021 GO SMART Award for its smart city solution that detects street garbage with AI.

The AI application automatically maps objects and identifies garbage on the street. Once garbage is detected, the information will be shared with the Amsterdam garbage management services for them to pick it up, helping the municipality keep the streets of Amsterdam even cleaner than before.

Keeping the streets clean in a dynamic urban environment is one of the major challenges on the streets of Amsterdam. Maarten Sukel, AI Lead of Amsterdam City, and the City of Amsterdam AI team developed a system that can recognize rubbish bags and other undesirable objects lying around in the street. Based on machine learning, the system can spot the objects in real time.

The Urban Object Detection Kit allows streets and other aspects of the public environment to be scanned with machine-learning technology at low cost and maximum efficiency. This could be a solution to a number of “blind spots” in the current methods used by the City of Amsterdam.

Cheap and Generic Solution

The new system, which is currently being tested by the City of Amsterdam, offers a cheap and generic solution that can easily be used in other cities as well. It uses smartphones linked to vehicles with an application that generates pictures. These are sent on to the server for object recognition. The Council uses the real-time object recognition system YOLO (You Only Look Once), which can process images very fast. Then they look if the results agree with reports from the neighborhood itself.

This system solves a big problem. Amsterdam has as many as 15,000 underground containers. “You can’t continuously drive past to see if there’s something lying next to them. For some things, like bulk waste, you need a special vehicle. By doing it properly from the outset, we not only keep the city clean but we also reduce the mileage,” said Sukel.

Privacy, however, is an important point. “We drive around with cameras and every citizen of Amsterdam should be able to move through the city without being followed. We only save images if they’re necessary for further research. Faces and distinguishing marks are removed,” Sukel explained.

System is Widely Deployable

The system can be applied beyond the recognition and removal of waste. It can also be used to recognize dangerous situations such as a knocked-down bollard or a crooked paving stone. The system is also very suitable for further research. This was an important requirement for the project.

“We want to focus on useful applications for urban areas, and we certainly wanted to incorporate that into this study. We initially chose the waste disposal problem as our focus because from a technical perspective this could be attained fastest,” Sukel said. In order to learn, AI requires huge amounts of data and there were many images of rubbish containers and waste available. More information about the project can be found in this paper.

To carry out the research, Sukel worked together with many people. ABS supervisors Marcel Worring and Stevan Rudinac played an important role and, at the City of Amsterdam, Sukel and his team collaborated with various domain experts. The project has brought together a lot of expertise, from the development of an application that is user-friendly to the backend of the system, and the people who collect waste and clear graffiti for the City of Amsterdam.

AI Team Develops New Applications for Amsterdam

The City of Amsterdam sees a bright future in the deployment of machine learning. Its AI team works on responsible AI for a more fair, just, and sustainable city. The team works with, among others, Civic AI Lab, a vehicle for the AI knowledge of civic AI, the University of Amsterdam, and other universities.

Images captured of the city contain valuable information about the city. Sukel’s team is working on a number of applications. “We created a privacy filter for panoramic images of the city so they can be shared openly, and thus allow for a lot of interesting research in using computer vision in urban areas. I hope it will inspire others to make privacy-friendly AI solutions for more fair and sustainable cities. We will keep using AI for a positive impact on the livability of cities,” Sukel said.

Subscribe to Newsletter

Leave a comment