End-to-End Deep Learning Models for Gap Identification in Maize Fields

We propose an approach to jointly count plants and detect gaps in maize fields using end-to-end deep-learning models. Unlike previous efforts that focused solely on plant detection, our methodology also integrates the task of gap identification, offering a holistic view of the state of the agricultu...

Full description

Saved in:
Bibliographic Details
Main Authors: Waqar, Rana, Grbovic, Zeljana, Khan, Maryam, Pajevic, Nina, Stefanovic, Dimitrije, Filipovic, Vladan, Panic, Marko, Djuric, Nemanja
Format: Conference Proceeding
Language:English
Subjects:
Conferences
Deep learning
end-to-end
gap identification
Industries
maize
multispectral
multitask
Plants (biology)
Precision agriculture
Prevention and mitigation
Soft sensors
UAV
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose an approach to jointly count plants and detect gaps in maize fields using end-to-end deep-learning models. Unlike previous efforts that focused solely on plant detection, our methodology also integrates the task of gap identification, offering a holistic view of the state of the agricultural field. Moreover, we consider different data sources in our experiments and explore the benefits of using multispectral over RGB images, which are commonly used in the industry. The findings suggest that multi-task learning on multispectral images significantly outperforms other model configurations, demonstrating the potential of the proposed approach for precision agriculture.
ISSN:2160-7516
DOI:10.1109/CVPRW63382.2024.00549