NPEC Computer Vision & Robotics

Real client project for the Netherlands Plant Eco-phenotyping Centre (NPEC), delivered during Year 2 Block B at BUas. Team of 4 working directly with NPEC researchers on live phenotyping infrastructure.

Computer vision + robotics pipeline for the Netherlands Plant Eco-phenotyping Centre. Root segmentation (F1: 0.85), root system architecture extraction, and reinforcement learning agents controlling a liquid handling robot.

Key Highlights

01.Root segmentation model achieving F1 score of 0.85 on held-out phenotyping imagery.
02.Root system architecture (RSA) extraction pipeline computing topology and branching metrics.
03.Reinforcement learning agent trained to control a liquid handling robot with precision dispensing.
04.PID controller integration for fine-grained robotic motion between waypoints.
05.Deployed within an active research environment at the Netherlands Plant Eco-phenotyping Centre.