Overcoming Domain Shift in Neural Networks for Accurate Plant Counting in Aerial Images

This paper presents a novel semi-supervised approach for accurate counting and localization of tropical plants in aerial images that can work in new visual domains in which the available data are not labeled. Our approach uses deep learning and domain adaptation, designed to handle domain shifts bet...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 15; no. 6; p. 1700
Main Authors Rodriguez-Vazquez, Javier, Fernandez-Cortizas, Miguel, Perez-Saura, David, Molina, Martin, Campoy, Pascual
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.03.2023
Subjects
aerial imagery
Annotations
Cameras
Counting
Crop diseases
Crops
Datasets
Deep learning
domain adaptation
Domains
Localization
Methods
Neural networks
plant detection
precision agriculture
Regression analysis
Remote sensing
Semantics
Tropical plants
Unmanned aerial vehicles
unsupervised learning
Online AccessGet full text

Cover

More Information
Summary:This paper presents a novel semi-supervised approach for accurate counting and localization of tropical plants in aerial images that can work in new visual domains in which the available data are not labeled. Our approach uses deep learning and domain adaptation, designed to handle domain shifts between the training and test data, which is a common challenge in this agricultural applications. This method uses a source dataset with annotated plants and a target dataset without annotations and adapts a model trained on the source dataset to the target dataset using unsupervised domain alignment and pseudolabeling. The experimental results show the effectiveness of this approach for plant counting in aerial images of pineapples under significative domain shift, achieving a reduction up to 97% in the counting error (1.42 in absolute count) when compared to the supervised baseline (48.6 in absolute count).
ISSN:2072-4292
2072-4292
DOI:10.3390/rs15061700