Francis Doumet would like to think he has his eye on helping the environment.
The fight against “climate change is obviously very, very dear to our hearts,” said the CEO of MLVX Technologies Inc. (Metaspectral), whose Vancouver company specializes in computer vision software that helps computers see and perceive the world as humans do.
Data interpreted by Metaspectral’s software is so precise that a major plastics recycler is working with the B.C. company to help with visually identifying the different types of plastics coming into their plants based on the materials they’re made from.
“We can increase the sorting capability, and therefore increase the quality of the recycled material and increase the impact of the circular economy,” Doumet said.
Metaspectral is now taking its vision for effecting environmental change off this world with a little help from the Canadian Space Agency (CSA).
The company revealed Tuesday the CSA is providing it with $150,000 in funding for an initiative aimed at measuring carbon dioxide (CO2) levels on planet Earth by examining hyperspectral images and data captured by orbiting satellites.
While many computer vision applications rely on conventional pictures to identify images of dogs or trees, Metaspectral taps high-end, hyperspectral sensors to collect mountains of data that its software can then analyze pixel by pixel in real time.
“Conventional computer vision … basically [sees] what humans can see. But there’s a lot that goes beyond the human eye that conventional cameras cannot capture. And that's where our technology ventures into,” Doumet said, adding that those high-end sensors collect 300 frequencies of light compared with the three frequencies of light captured by typical cameras.
“That allows us to find defects, characteristics, and identify materials that conventional cameras, and therefore conventional computer vision, simply cannot find.”
The data collected for the space-bound venture comes from across the electromagnetic spectrum to allow Metaspectral’s software to identify and measure CO2. This means measuring how different frequencies of light invisible to the human eye reflect back to the sensor and then comparing it to previous measurements.
The company said that it’s able to accurately measure this within a three per cent margin of error.
“One of the key problems today with the whole carbon credit system is that farmers in general just have a have a hard time kind of defining exactly what their impact is,” Doumet said.
“And so if we were able to take out the guessing game, at least when it comes to accurately measuring the carbon sequestration potential of … a farmer's field, then that empowers them to kind of plug into the carbon credit system more efficiently.”
Another B.C.-based firm is trying to address the same problem, albeit in a much different manner.
No market for purchasing carbon credits based on carbon sequestration in the soil currently exists in Canada. In the U.S., the market leans heavily on best estimates based on initiatives deployed by farmers, such as the growth of cover crops or soil-tilling practices.
Last year Vancouver-based Terramera Inc. landed $7.9 million in funding from Sustainable Development Technology Canada (SDTC) to pursue technology that can better quantify carbon within farm soil without the reliance on expensive labour and lab work currently needed.
“The key thing that we've always been looking at is how do we start incenting that behavior,” Terramera CEO Karn Manhas told BIV in May 2021.
“We've developed a scalable, accurate, low-cost remote sensing technology where we actually have sensors and data pulled out of the field.”
Meanwhile, Doumet said Metaspectral’s technology also has direct agricultural applications, such as visually identifying plants that are sick vs. plants that are healthy.
“And there are also obvious applications in defense. For example, [detecting] a camouflage vehicle sitting under a canopy of trees,” he said.
Doumet said customers come from wide spectrum of industries but they all have one thing in common.
“They are typically customers that have already experimented with computer vision,” he said.
“Our customers don't necessarily come in asking for these hyperspectral sensors that we're talking about. They basically come in with a computer vision problem and we provide a different approach to solving their problems.”
