Time-series data extraction from aerial images
Martijn Bos

Supervisor TU Delft: Neil Budko

Site of the project:
VanBoven Drones B.V.
Lulofsstraat 55
2521 AL Den Haag

start of the project: November 2019

Supervisor VanBoven Drones B.V.: Eric Verhoeff

In April 2020 the Interim Thesis has appeared and a presentation has been given.

The Master project has been finished in July 2020 by the completion of the Masters Thesis and a final presentation has been given.

For working address etc. we refer to our alumnipage.

Summary of the master project:
Aerial images of agricultural fields taken at different time instants (dates) contain valuable information about the development of plants. The present Msc project is aimed at extracting this information from a series of images acquired by a drone-mounted camera. The main focus will be on the so-called Very High Resolution (<1cm) drone imagery and agricultural applications, specifically potatoes in the early stages of their development. Sample images are provided and remain the property of the HZPC Holland BV.

The student will first study and provide a concise description of the mathematical and algorithmic aspects of the standard single-day image processing pipeline, including: feature detection, image matching, feature matching, structure from motion, depth maps, orthorectification, and meshing. Applicability and efficiency of different approaches and open-source software tools will be analyzed.

Further, the question of multiple-date image (point-cloud, surface model, etc) alignment will be investigated with the goal to detect and record temporal changes in plants.

Contact information: Kees Vuik

Back to the home page or the Master students page of Kees Vuik