Rick van de Zedde is a senior scientist/ business developer Phenomics and Automation at the Wageningen Plant Science Group. He has worked at WUR since 2004. His background is in Artificial Intelligence with a focus on imaging and robotics. In 2002, he graduated with a MSc in Artificial Intelligence from the University of Groningen.
Since 2006 he has been a coordinator of www.AgroFoodRobotics.nl, a joint initiative of several research institutes within Wageningen UR. He is also one of the initiators of the Phenomics initiative within WUR - www.phenomics.nl - in which 15 WUR research groups work closely together on plant phenotyping projects. In 2012 he was directly involved in launching the EU-project PicknPack - www.picknpack.eu, in which advanced robotic food packaging lines will be developed and demonstrated to the food industry.
He also takes an active role in research. In 2011, he was head of the MARVIN-project in which he and his team developed a tomato seedling inspection approach based on 3D reconstruction. In the current EU project EPPN, he is the leader of the “Novel Instrumentation for Plant Phenotyping” work package.
In the EU-COST action FA1306, http://costfa1306.eu/ “The quest for tolerant varieties - Phenotyping at plant and cellular level”, he is WG3 leader taking care of the integration of phenotyping at plant and cell level and translation into good practices for applied end use.
EPPN, PicknPack and other on-going projects explore the potential of fast 3D shape analysis agrifood products and vision-guided robotics, areas in which WUR has recently made significant breakthroughs.
Research Areas: Phenomics
Validation of plant part measurements using a 3D reconstruction method suitable for high-throughput seedling phenotyping.
publication date: Dec 1, 2015
Springer - Machine Vision and Applications
In plant phenotyping, there is a demand for high-throughput, non-destructive systems that can accurately analyse various plant traits by measuring features such as plant volume, leaf area, and stem length. Existing vision-based systems either focus on speed using 2D imaging, which is consequently inaccurate, or on accuracy using time-consuming 3D methods. In this paper, we present a computer-vision system for seedling phenotyping that combines best of both approaches by utilizing a fast three-dimensional (3D) reconstruction method. We developed image processing methods for the identification and segmentation of plant organs (stem and leaf) from the 3D plant model. Various measurements of plant features such as plant volume, leaf area, and stem length are estimated based on these plant segments. We evaluate the accuracy of our system by comparing the measurements of our methods with ground truth measurements obtained destructively by hand. The results indicate that the proposed system is very promising.
Art house - volunteer - bar, projection, organiser movie festivals.