/Student project: Deep Learning for Part-based Instance Segmentation of Orchard Point Clouds

Student project: Deep Learning for Part-based Instance Segmentation of Orchard Point Clouds

Research & development - Wageningen | Just now

Student project: Deep Learning for Part-based Instance Segmentation of Orchard Point Clouds

The project focuses on using 3D point cloud data collected from orchard environments to estimate plant vigour and quantify structural components such as branches. By analyzing the spatial distribution and density of the point clouds, the system can assess tree health and growth patterns. This approach enables more precise monitoring and management of orchard crops, supporting data-driven decisions in precision agriculture.

What you will do

Digital Orchard Program: 3D Point Cloud Analysis for Orchard Tree Structure and Vigour Estimation
In our Digital Orchard program we aims to develop a method for analyzing 3D point cloud data from orchards to estimate plant vigour and count structural elements such as branches. The existing data can be used along with the possibility to run new measurement campaign to collect new data and follow fruit tree development in the orchard overt time. The goal is to support precision agriculture by enabling automated, data-driven assessment of tree health and structure.

Main tasks:

  • Literature Review: Study existing methods for point cloud processing, plant vigour estimation, and branch detection in orchard environments.
  • Data Collection and Preprocessing: Acquire or use existing 3D point cloud datasets and prepare them for analysis (e.g., filtering, segmentation).
  • Algorithm Development: Design and implement algorithms to estimate vigour and detect/count plant parts from point clouds.
  • Evaluation and Validation: Test the developed methods against ground truth data and evaluate their accuracy and reliability.
  • Project Planning and Reporting: Create a timeline with milestones and deliverables, and document progress through reports and presentations.

What we do for you

  • We have a challenging problem where you have a lot of freedom to come up with solutions.
  • We have a diverse team of experts both from the biological and the technical sides to supervise and support you.
  • You will join the Data Science team of OnePlanet, which employs state of the art knowledge on machine learning for precision agriculture and the frameworks necessary to perform these big data tasks at huge scale.
  • You will be able to exchange views and knowledge with the OnePlanet and Imec community of experts and scientists, widening your professional network.
  • We can help you to improve your coding skills up to industry standards.
  • You have access to our cloud solutions to solve this problem allowing you to process large amount of data within reasonable time.

Who you are

  • Familiarity with LiDAR scanning & point clouds.
  •  Knowledge of Python.
  • Knowledge of Machine Learning.
  • Knowledge of OpenCV, Open3D is a plus
  • Experience with PyTorch or TensorFlow is a plus.
  • Knowledge of Git.
  • Basic understanding of Agile-Scrum.
  • You are passionate about bringing positive impact to environmental and societal challenges.

Interested

Does this position sound like an interesting next step in your career at imec? Don’t hesitate to submit your application by clicking on ‘APPLY NOW’.
Should you have more questions about the job, you can contact jobs@imec.nl.

Who we are
Accepteer analytics-cookies om deze content te kunnen bekijken.
imec's cleanroom
Accepteer analytics-cookies om deze content te kunnen bekijken.

Verzend deze job naar jouw e-mailadres