Year: 2025
Type: dissertation
Abstract: Traditional weed management relies on herbicides, harming the environment and posing health risks. Remote sensing and deep learning enable site-specific weed management but face challenges like motion blur in drone images and high variability of weed species. This thesis addresses these issues by (a) proposing solutions for motion blur and (b) presenting a large-scale greenhouse weed dataset to advance precision agriculture.
Authors: Genze, Nikita, Grimm, Dominik, Technische Universität München
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: green
Funder: Technische Universität München
OpenAlex ID: W7045744864
