Time-series data extraction from aerial images
Supervisor TU Delft: Neil Budko
Site of the project:
VanBoven Drones B.V.
2521 AL Den Haag
start of the project: November 2019
Supervisor VanBoven Drones B.V.: Eric Verhoeff
In April 2020 the
has been given.
The Master project has been finished in July 2020
by the completion of the
and a final
has been given.
For working address etc. we refer to our
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.
Back to the
Master students page of Kees Vuik