A Vancouver computer vision company that specializes in hyperspectral imaging has landed a provincial grant to use its technology for better, faster more accurate plastics recycling.
Metaspectral has been awarded $419,000 under the CleanBC Plastics Action Fund to use its technology to sort plastics more accurately and quickly.
Hyperspectral imaging goes far beyond the visible light spectrum to analyze non-visible signatures along the full electromagnetic spectrum. Using hyperspectral imaging and deep learning, Metaspectral's technology can be used to identify chemical signatures that can help distinguish different types of plastics.
The financing from CleanBC will help Metaspectral fine tune its technology to differentiate between the type of plastic used in milk containers from that used in containers for detergents and automotive oil.
“It has historically been impossible for humans or traditional cameras to differentiate between plastics at this level, meaning that to date, various types of plastics have been recycled in bulk together,” said Metaspectral co-founder and CEO Francis Doumet. “When post-consumer recycled plastic cannot have its purity guaranteed, its quality and market value decrease significantly.”
“Our technology uses deep learning to analyze hyperspectral imagery from specialized cameras placed over a conveyor belt carrying recyclables,” said Migel Tissera, CTO and co-founder of Metaspectral. “The images captured contain information from across the electromagnetic spectrum, making it possible for our algorithms to identify materials immediately and sort them accordingly.”
