The Overview
PolyPerception provides an AI-powered waste management platform to plastics and material recovery facilities, giving them visibility into their waste streams so they can operate more efficiently and responsibly. The team has partnered with Sama to help fuel this technology, to further their mission of empowering stakeholders across waste management—from recyclers to municipalities to legislators—to make more sustainable decisions about waste and its impact on the environment.
“There’s a possibility to make an impact on legislation and on the environment, but not without accurately labeled data.”
Parshva Mehta, COO at PolyPerception
The Challenge
In order to deliver actionable insights and quantitative data to their clients, PolyPerception set out to build a robust multi-object tracking model, but quickly found that the accurate labeling of data would play a key role:
Low light and fast-moving objects
Waste objects travel quickly on conveyor belts in facilities with less-than-ideal lighting conditions
Volume of waste
On average, 8 tonnes of waste passes through a waste sorting facility every hour
Diversity of required labels
Wide range of packaging types and materials, with regulations and trends constantly shifting
1M+
Millions of waste objects labeled
99%
Average Quality Score of 99%
MORE
Efficient operations and better commercial terms for facilities
The Solution
Sama worked with PolyPerception to deliver high-quality labeled data to power their technology:
- Accurately labeled millions of waste objects
- Delivered annotations with an average Quality Score of 99%
- Maintained open feedback loops to adapt to changing regulations and the nuances of waste objects from region to region
“The team quickly learned to distinguish between waste objects, which differ greatly from region to region. Communication channels remained open for feedback, with a continuous open discussion about how efforts were progressing.”
Rafael Hautekiet, CEO of PolyPerception
Conclusion
For PolyPerception, accurate data in waste management has cascading effects for society – a rising tide to lift all boats. With more reliable data:
- Recyclers can better understand the composition of their input waste streams, allowing them to reach higher recycling rates, and meet federal/state regulations while cutting costs.
- Municipalities and government agencies can confidently establish data-backed regulations that will have positive lasting impacts.
- Consumers can be better informed of how their actions have a direct and measurable impact on the world around us.
The economic, social, and environmental benefits of the above are too numerous to list, but they are at the core of PolyPerception’s long-term vision of empowering stakeholders across waste management to make more impactful decisions.
-
Continental Demetrio Aiello, Head of the Artificial Intelligence & Robotics Labs
-
Continental Demetrio Aiello, Head of the Artificial Intelligence & Robotics Labs
-
Getty Images Steve Heck, CTO
-
Indoor Robotics Naty Shemer, R&D Group Manager at Indoor Robotics
-
Microsoft Ankur Khator, Sr. Program Manager
-
PolyPerception Parshva Mehta, COO & Co-founder
-
Swift Medical Dhanesh Ramachandram, Senior ML Researcher