Michael Nielsen talks about his work in computer vision for field use in agriculture and recycling. Host Per Sjöborg, Robots in Depth #48 supported by https://carbon.ai & http://www.aptomica.com.
Michael started out in computer vision in the agriculture space doing machine vision and 3D reconstruction of plants. He then moved to the Danish Technological Institute when they expanded their work on machine vision for field use in agriculture.
Michael worked with a fusion of sensors like stereo vision, thermography, radar, lidar and high frame rate cameras, merging multiple images for high dynamic range. All this to be able to navigate the tricky situation in a farm field where you need to navigate close to or even in what is grown. Multi-baseline cameras were also used to provide range detection over a wide range of distances.
We also learn about how he expanded his work into sorting recycling, a very challenging problem. Here the sensor fusion gives him RGB as well as depth and temperature. Adding a powerful studio flash to the setup allowed him to heat the material being sorted, making it possible to determine the material, depending on how it absorbs the heat from the flash. Michael is also working on adding cameras capable of seeing above the human range of vision to make it easy to specify which materials to pick. We also hear about the problems faced when using time of flight and sheet of light cameras. He then shares some good results using stereo vision, especially combined with blue light random dot projectors.
This episode was recorded at the Danish Technological Institute in Odense 2016.
Please support the show on Patreon https://www.patreon.com/RobotsinDepth
You can find the show blog here http://www.robotsindepth.com
Robots in Depth on Twitter https://www.twitter.com/Robotsindepth
The host Per Sjöborg on http://www.flexibilityenvelope.com
Leave a Reply