Application of YOLOv5 for Point Label Based Object Detection of Black Pine Trees with Vitality Losses in UAV Data
Monitoring tree diseases in forests is crucial for managing pathogens, particularly as climate change and globalization lead to the emergence and spread of tree diseases. Object detection algorithms for monitoring tree diseases through remote sensing rely on bounding boxes to represent trees. Howeve...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-04-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/8/1964 |
_version_ | 1797603667767984128 |
---|---|
author | Peter Hofinger Hans-Joachim Klemmt Simon Ecke Steffen Rogg Jan Dempewolf |
author_facet | Peter Hofinger Hans-Joachim Klemmt Simon Ecke Steffen Rogg Jan Dempewolf |
author_sort | Peter Hofinger |
collection | DOAJ |
description | Monitoring tree diseases in forests is crucial for managing pathogens, particularly as climate change and globalization lead to the emergence and spread of tree diseases. Object detection algorithms for monitoring tree diseases through remote sensing rely on bounding boxes to represent trees. However, this approach may not be the most efficient. Our study proposed a solution to this challenge by applying object detection to unmanned aerial vehicle (UAV)-based imagery, using point labels that were converted into equally sized square bounding boxes. This allowed for effective and extensive monitoring of black pine (<i>Pinus nigra</i> L.) trees with vitality-related damages. To achieve this, we used the “You Only Look Once’’ version 5 (YOLOv5) deep learning algorithm for object detection, alongside a 16 by 16 intersection over union (IOU) and confidence threshold grid search, and five-fold cross-validation. Our dataset used for training and evaluating the YOLOv5 models consisted of 179 images, containing a total of 2374 labeled trees. Our experiments revealed that, for achieving the best results, the constant bounding box size should cover at least the center half of the tree canopy. Moreover, we found that YOLOv5s was the optimal model architecture. Our final model achieved competitive results for detecting damaged black pines, with a 95% confidence interval of the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mn>1</mn></msub></semantics></math></inline-formula> score of 67–77%. These results can possibly be improved by incorporating more data, which is less effort-intensive due to the use of point labels. Additionally, there is potential for advancements in the method of converting points to bounding boxes by utilizing more sophisticated algorithms, providing an opportunity for further research. Overall, this study presents an efficient method for monitoring forest health at the single tree level, using point labels on UAV-based imagery with a deep learning object detection algorithm. |
first_indexed | 2024-03-11T04:35:14Z |
format | Article |
id | doaj.art-aa17d24a13f94e548ceef6156797accd |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-11T04:35:14Z |
publishDate | 2023-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-aa17d24a13f94e548ceef6156797accd2023-11-17T21:10:07ZengMDPI AGRemote Sensing2072-42922023-04-01158196410.3390/rs15081964Application of YOLOv5 for Point Label Based Object Detection of Black Pine Trees with Vitality Losses in UAV DataPeter Hofinger0Hans-Joachim Klemmt1Simon Ecke2Steffen Rogg3Jan Dempewolf4Department of Silviculture and Mountain Forests, Bavarian State Institute of Forestry, Hans-Carl-von-Carlowitz-Platz 1, 85354 Freising, GermanyDepartment of Silviculture and Mountain Forests, Bavarian State Institute of Forestry, Hans-Carl-von-Carlowitz-Platz 1, 85354 Freising, GermanyDepartment of Silviculture and Mountain Forests, Bavarian State Institute of Forestry, Hans-Carl-von-Carlowitz-Platz 1, 85354 Freising, GermanyDepartment of Forestry, University of Applied Sciences Weihenstephan-Triesdorf, Hans-Carl-von-Carlowitz-Platz 3, 85354 Freising, GermanyDepartment of Silviculture and Mountain Forests, Bavarian State Institute of Forestry, Hans-Carl-von-Carlowitz-Platz 1, 85354 Freising, GermanyMonitoring tree diseases in forests is crucial for managing pathogens, particularly as climate change and globalization lead to the emergence and spread of tree diseases. Object detection algorithms for monitoring tree diseases through remote sensing rely on bounding boxes to represent trees. However, this approach may not be the most efficient. Our study proposed a solution to this challenge by applying object detection to unmanned aerial vehicle (UAV)-based imagery, using point labels that were converted into equally sized square bounding boxes. This allowed for effective and extensive monitoring of black pine (<i>Pinus nigra</i> L.) trees with vitality-related damages. To achieve this, we used the “You Only Look Once’’ version 5 (YOLOv5) deep learning algorithm for object detection, alongside a 16 by 16 intersection over union (IOU) and confidence threshold grid search, and five-fold cross-validation. Our dataset used for training and evaluating the YOLOv5 models consisted of 179 images, containing a total of 2374 labeled trees. Our experiments revealed that, for achieving the best results, the constant bounding box size should cover at least the center half of the tree canopy. Moreover, we found that YOLOv5s was the optimal model architecture. Our final model achieved competitive results for detecting damaged black pines, with a 95% confidence interval of the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mn>1</mn></msub></semantics></math></inline-formula> score of 67–77%. These results can possibly be improved by incorporating more data, which is less effort-intensive due to the use of point labels. Additionally, there is potential for advancements in the method of converting points to bounding boxes by utilizing more sophisticated algorithms, providing an opportunity for further research. Overall, this study presents an efficient method for monitoring forest health at the single tree level, using point labels on UAV-based imagery with a deep learning object detection algorithm.https://www.mdpi.com/2072-4292/15/8/1964point labelsstress detectionforest healthUAVdeep learningYOLOv5 |
spellingShingle | Peter Hofinger Hans-Joachim Klemmt Simon Ecke Steffen Rogg Jan Dempewolf Application of YOLOv5 for Point Label Based Object Detection of Black Pine Trees with Vitality Losses in UAV Data Remote Sensing point labels stress detection forest health UAV deep learning YOLOv5 |
title | Application of YOLOv5 for Point Label Based Object Detection of Black Pine Trees with Vitality Losses in UAV Data |
title_full | Application of YOLOv5 for Point Label Based Object Detection of Black Pine Trees with Vitality Losses in UAV Data |
title_fullStr | Application of YOLOv5 for Point Label Based Object Detection of Black Pine Trees with Vitality Losses in UAV Data |
title_full_unstemmed | Application of YOLOv5 for Point Label Based Object Detection of Black Pine Trees with Vitality Losses in UAV Data |
title_short | Application of YOLOv5 for Point Label Based Object Detection of Black Pine Trees with Vitality Losses in UAV Data |
title_sort | application of yolov5 for point label based object detection of black pine trees with vitality losses in uav data |
topic | point labels stress detection forest health UAV deep learning YOLOv5 |
url | https://www.mdpi.com/2072-4292/15/8/1964 |
work_keys_str_mv | AT peterhofinger applicationofyolov5forpointlabelbasedobjectdetectionofblackpinetreeswithvitalitylossesinuavdata AT hansjoachimklemmt applicationofyolov5forpointlabelbasedobjectdetectionofblackpinetreeswithvitalitylossesinuavdata AT simonecke applicationofyolov5forpointlabelbasedobjectdetectionofblackpinetreeswithvitalitylossesinuavdata AT steffenrogg applicationofyolov5forpointlabelbasedobjectdetectionofblackpinetreeswithvitalitylossesinuavdata AT jandempewolf applicationofyolov5forpointlabelbasedobjectdetectionofblackpinetreeswithvitalitylossesinuavdata |