Work

Beikrauterkennung in landwirtschaftlichen Bildern mittels Deep Learning

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
Subfield: Plant Science
Open Access status: green
OpenAlex ID: W7045744864
Cites: 371
Cited by:
Related to: 9