Bridging technology and ecology: enhancing applicability of deep learning and UAV-based flower recognition

The decline of insect biomass, including pollinators, represents a significant ecological challenge, impacting both biodiversity and ecosystems. Effective monitoring of pollinator habitats, especially floral resources, is essential for addressing this issue. This study connects drone and deep learni...

Full description

Saved in:
Bibliographic Details
Main Authors: Marie Schnalke, Jonas Funk, Andreas Wagner
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1498913/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850038415021572096
author Marie Schnalke
Jonas Funk
Andreas Wagner
Andreas Wagner
author_facet Marie Schnalke
Jonas Funk
Andreas Wagner
Andreas Wagner
author_sort Marie Schnalke
collection DOAJ
description The decline of insect biomass, including pollinators, represents a significant ecological challenge, impacting both biodiversity and ecosystems. Effective monitoring of pollinator habitats, especially floral resources, is essential for addressing this issue. This study connects drone and deep learning technologies to their practical application in ecological research. It focuses on simplifying the application of these technologies. Updating an object detection toolbox to TensorFlow (TF) 2 enhanced performance and ensured compatibility with newer software packages, facilitating access to multiple object recognition models - Faster Region-based Convolutional Neural Network (Faster R-CNN), Single-Shot-Detector (SSD), and EfficientDet. The three object detection models were tested on two datasets of UAV images of flower-rich grasslands, to evaluate their application potential in practice. A practical guide for biologists to apply flower recognition to Unmanned Aerial Vehicle (UAV) imagery is also provided. The results showed that Faster RCNN had the best overall performance with a precision of 89.9% and a recall of 89%, followed by EfficientDet, which excelled in recall but at a lower precision. Notably, EfficientDet demonstrated the lowest model complexity, making it a suitable choice for applications requiring a balance between efficiency and detection performance. Challenges remain, such as detecting flowers in dense vegetation and accounting for environmental variability.
format Article
id doaj-art-c1241fa8062e4ec79cead31bf4ffc3d4
institution DOAJ
issn 1664-462X
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-c1241fa8062e4ec79cead31bf4ffc3d42025-08-20T02:56:36ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-03-011610.3389/fpls.2025.14989131498913Bridging technology and ecology: enhancing applicability of deep learning and UAV-based flower recognitionMarie Schnalke0Jonas Funk1Andreas Wagner2Andreas Wagner3Faculty of Management Science and Engineering, Karlsruhe University of Applied Sciences (HKA), Karlsruhe, GermanyFaculty of Management Science and Engineering, Karlsruhe University of Applied Sciences (HKA), Karlsruhe, GermanyFaculty of Management Science and Engineering, Karlsruhe University of Applied Sciences (HKA), Karlsruhe, GermanyFraunhofer Institute for Industrial Mathematics (ITWM), Kaiserslautern, GermanyThe decline of insect biomass, including pollinators, represents a significant ecological challenge, impacting both biodiversity and ecosystems. Effective monitoring of pollinator habitats, especially floral resources, is essential for addressing this issue. This study connects drone and deep learning technologies to their practical application in ecological research. It focuses on simplifying the application of these technologies. Updating an object detection toolbox to TensorFlow (TF) 2 enhanced performance and ensured compatibility with newer software packages, facilitating access to multiple object recognition models - Faster Region-based Convolutional Neural Network (Faster R-CNN), Single-Shot-Detector (SSD), and EfficientDet. The three object detection models were tested on two datasets of UAV images of flower-rich grasslands, to evaluate their application potential in practice. A practical guide for biologists to apply flower recognition to Unmanned Aerial Vehicle (UAV) imagery is also provided. The results showed that Faster RCNN had the best overall performance with a precision of 89.9% and a recall of 89%, followed by EfficientDet, which excelled in recall but at a lower precision. Notably, EfficientDet demonstrated the lowest model complexity, making it a suitable choice for applications requiring a balance between efficiency and detection performance. Challenges remain, such as detecting flowers in dense vegetation and accounting for environmental variability.https://www.frontiersin.org/articles/10.3389/fpls.2025.1498913/fullflower detectiondeep learningunmanned aerial vehicle (UAV)biodiversityremote sensing
spellingShingle Marie Schnalke
Jonas Funk
Andreas Wagner
Andreas Wagner
Bridging technology and ecology: enhancing applicability of deep learning and UAV-based flower recognition
Frontiers in Plant Science
flower detection
deep learning
unmanned aerial vehicle (UAV)
biodiversity
remote sensing
title Bridging technology and ecology: enhancing applicability of deep learning and UAV-based flower recognition
title_full Bridging technology and ecology: enhancing applicability of deep learning and UAV-based flower recognition
title_fullStr Bridging technology and ecology: enhancing applicability of deep learning and UAV-based flower recognition
title_full_unstemmed Bridging technology and ecology: enhancing applicability of deep learning and UAV-based flower recognition
title_short Bridging technology and ecology: enhancing applicability of deep learning and UAV-based flower recognition
title_sort bridging technology and ecology enhancing applicability of deep learning and uav based flower recognition
topic flower detection
deep learning
unmanned aerial vehicle (UAV)
biodiversity
remote sensing
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1498913/full
work_keys_str_mv AT marieschnalke bridgingtechnologyandecologyenhancingapplicabilityofdeeplearninganduavbasedflowerrecognition
AT jonasfunk bridgingtechnologyandecologyenhancingapplicabilityofdeeplearninganduavbasedflowerrecognition
AT andreaswagner bridgingtechnologyandecologyenhancingapplicabilityofdeeplearninganduavbasedflowerrecognition
AT andreaswagner bridgingtechnologyandecologyenhancingapplicabilityofdeeplearninganduavbasedflowerrecognition