Coverage Estimation of Droplets Sprayed on Water-Sensitive Papers Based on Domain-Adaptive Segmentation

Unmanned aerial spraying systems (UASSs) are widely used today for the effective control of pests affecting crops, and more advanced UASS techniques are now being developed. To evaluate such systems, artificial targets are typically used to assess droplet coverage through image processing. To evalua...

Full description

Saved in:
Bibliographic Details
Main Authors: Dae-Hyun Lee, Baek-Gyeom Seong, Seung-Yun Baek, Chun-Gu Lee, Yeong-Ho Kang, Xiongzhe Han, Seung-Hwa Yu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/8/11/670
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217662635835392
author Dae-Hyun Lee
Baek-Gyeom Seong
Seung-Yun Baek
Chun-Gu Lee
Yeong-Ho Kang
Xiongzhe Han
Seung-Hwa Yu
author_facet Dae-Hyun Lee
Baek-Gyeom Seong
Seung-Yun Baek
Chun-Gu Lee
Yeong-Ho Kang
Xiongzhe Han
Seung-Hwa Yu
author_sort Dae-Hyun Lee
collection DOAJ
description Unmanned aerial spraying systems (UASSs) are widely used today for the effective control of pests affecting crops, and more advanced UASS techniques are now being developed. To evaluate such systems, artificial targets are typically used to assess droplet coverage through image processing. To evaluate performance accurately, high-quality binary image processing is necessary; however, this involves labor for sample collection, transportation, and storage, as well as the risk of potential contamination during the process. Therefore, rapid assessment in the field is essential. In the present study, we evaluated droplet coverage on water-sensitive papers (WSPs) under field conditions. A dataset was constructed consisting of paired training examples, each comprising source and target data. The source data were high-quality labeled images obtained from WSP samples through image processing, while the target data were aligned RoIs within field images captured in situ. Droplet coverage estimation was performed using an encoder–decoder model, trained on the labeled images, with features adapted to field images via self-supervised learning. The results indicate that the proposed method detected droplet coverage in field images with an error of less than 5%, demonstrating a strong correlation between measured and estimated values (R<sup>2</sup> = 0.99). The method proposed in this paper enables immediate and accurate evaluation of the performance of UASSs in situ.
format Article
id doaj-art-ccf61cb7d2a04cb69bd071cafcc73c72
institution OA Journals
issn 2504-446X
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-ccf61cb7d2a04cb69bd071cafcc73c722025-08-20T02:07:59ZengMDPI AGDrones2504-446X2024-11-0181167010.3390/drones8110670Coverage Estimation of Droplets Sprayed on Water-Sensitive Papers Based on Domain-Adaptive SegmentationDae-Hyun Lee0Baek-Gyeom Seong1Seung-Yun Baek2Chun-Gu Lee3Yeong-Ho Kang4Xiongzhe Han5Seung-Hwa Yu6Department of Biosystems Machinery Engineering, Chungnam National University, Daejeon 34134, Republic of KoreaDepartment of Biosystems Machinery Engineering, Chungnam National University, Daejeon 34134, Republic of KoreaDepartment of Biosystems Machinery Engineering, Chungnam National University, Daejeon 34134, Republic of KoreaDepartment of Agriculture Engineering, National Institute of Agricultural Sciences, Jeonju 54875, Republic of KoreaDepartment of Crops and Food, Jeonbuk State Agricultural Research and Extension Services, Iksan 54591, Republic of KoreaDepartment of Biosystems Engineering, Kangwon National University, Chuncheon 24341, Republic of KoreaDepartment of Agriculture Engineering, National Institute of Agricultural Sciences, Jeonju 54875, Republic of KoreaUnmanned aerial spraying systems (UASSs) are widely used today for the effective control of pests affecting crops, and more advanced UASS techniques are now being developed. To evaluate such systems, artificial targets are typically used to assess droplet coverage through image processing. To evaluate performance accurately, high-quality binary image processing is necessary; however, this involves labor for sample collection, transportation, and storage, as well as the risk of potential contamination during the process. Therefore, rapid assessment in the field is essential. In the present study, we evaluated droplet coverage on water-sensitive papers (WSPs) under field conditions. A dataset was constructed consisting of paired training examples, each comprising source and target data. The source data were high-quality labeled images obtained from WSP samples through image processing, while the target data were aligned RoIs within field images captured in situ. Droplet coverage estimation was performed using an encoder–decoder model, trained on the labeled images, with features adapted to field images via self-supervised learning. The results indicate that the proposed method detected droplet coverage in field images with an error of less than 5%, demonstrating a strong correlation between measured and estimated values (R<sup>2</sup> = 0.99). The method proposed in this paper enables immediate and accurate evaluation of the performance of UASSs in situ.https://www.mdpi.com/2504-446X/8/11/670unmanned aerial spraying system (UASS)droplet coveragewater-sensitive paper (WSP)deep neural networksdomain adaptationself-supervised contrastive learning
spellingShingle Dae-Hyun Lee
Baek-Gyeom Seong
Seung-Yun Baek
Chun-Gu Lee
Yeong-Ho Kang
Xiongzhe Han
Seung-Hwa Yu
Coverage Estimation of Droplets Sprayed on Water-Sensitive Papers Based on Domain-Adaptive Segmentation
Drones
unmanned aerial spraying system (UASS)
droplet coverage
water-sensitive paper (WSP)
deep neural networks
domain adaptation
self-supervised contrastive learning
title Coverage Estimation of Droplets Sprayed on Water-Sensitive Papers Based on Domain-Adaptive Segmentation
title_full Coverage Estimation of Droplets Sprayed on Water-Sensitive Papers Based on Domain-Adaptive Segmentation
title_fullStr Coverage Estimation of Droplets Sprayed on Water-Sensitive Papers Based on Domain-Adaptive Segmentation
title_full_unstemmed Coverage Estimation of Droplets Sprayed on Water-Sensitive Papers Based on Domain-Adaptive Segmentation
title_short Coverage Estimation of Droplets Sprayed on Water-Sensitive Papers Based on Domain-Adaptive Segmentation
title_sort coverage estimation of droplets sprayed on water sensitive papers based on domain adaptive segmentation
topic unmanned aerial spraying system (UASS)
droplet coverage
water-sensitive paper (WSP)
deep neural networks
domain adaptation
self-supervised contrastive learning
url https://www.mdpi.com/2504-446X/8/11/670
work_keys_str_mv AT daehyunlee coverageestimationofdropletssprayedonwatersensitivepapersbasedondomainadaptivesegmentation
AT baekgyeomseong coverageestimationofdropletssprayedonwatersensitivepapersbasedondomainadaptivesegmentation
AT seungyunbaek coverageestimationofdropletssprayedonwatersensitivepapersbasedondomainadaptivesegmentation
AT chungulee coverageestimationofdropletssprayedonwatersensitivepapersbasedondomainadaptivesegmentation
AT yeonghokang coverageestimationofdropletssprayedonwatersensitivepapersbasedondomainadaptivesegmentation
AT xiongzhehan coverageestimationofdropletssprayedonwatersensitivepapersbasedondomainadaptivesegmentation
AT seunghwayu coverageestimationofdropletssprayedonwatersensitivepapersbasedondomainadaptivesegmentation