A Segment Anything Model Approach for Rice Seedlings Detection Based on UAV Images

Accurate estimation of regional rice yields is crucial for food security and efficient agricultural management. In this regard, the use of Unmanned Aerial Vehicles (UAVs) that have revolutionized crop monitoring by providing high-resolution images for precision agriculture, is beneficial. This study...

Full description

Saved in:
Bibliographic Details
Main Authors: H. Rezvan, M. J. Valadan Zoej, F. Youssefi
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-annals.copernicus.org/articles/X-G-2025/713/2025/isprs-annals-X-G-2025-713-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704533563801600
author H. Rezvan
M. J. Valadan Zoej
F. Youssefi
F. Youssefi
author_facet H. Rezvan
M. J. Valadan Zoej
F. Youssefi
F. Youssefi
author_sort H. Rezvan
collection DOAJ
description Accurate estimation of regional rice yields is crucial for food security and efficient agricultural management. In this regard, the use of Unmanned Aerial Vehicles (UAVs) that have revolutionized crop monitoring by providing high-resolution images for precision agriculture, is beneficial. This study explores the potential of Segment Anything Model (SAM) for detecting rice seedlings, focusing on determining the optimal approach and prompt for this task. We examined three SAM scenarios: automatic mask generation, bounding box prompt, and point prompt. Our evaluation criteria included processing time, visual interpretation, and accuracy indexes. The results demonstrated the effectiveness of SAM in rice seedling detection, highlighting the importance of selecting the appropriate prompt for specific agricultural applications. Our findings reveal that the point prompt method emerges as the preferred choice for rice seedling detection, offering superior accuracy and reliability. Specifically, it achieved mIoU and mDice scores of 94.57 % and 0.97, respectively. While the bounding box approach showed promise, despite slightly lower precision, it may still be suitable depending on application-specific requirements. Conversely, the automatic mask generation scenario proved unsuitable for this task due to its low accuracy and inability to effectively detect rice seedlings. The outcomes of this study serve as a baseline for evaluating SAM prompts, guiding future improvements and refinements to enhance its performance in real-world agricultural applications.
format Article
id doaj-art-015b7c300e284eecb333cde31cc70042
institution DOAJ
issn 2194-9042
2194-9050
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-015b7c300e284eecb333cde31cc700422025-08-20T03:16:43ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502025-07-01X-G-202571371910.5194/isprs-annals-X-G-2025-713-2025A Segment Anything Model Approach for Rice Seedlings Detection Based on UAV ImagesH. Rezvan0M. J. Valadan Zoej1F. Youssefi2F. Youssefi3Department of Photogrammetry and Remote Sensing, Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, IranDepartment of Photogrammetry and Remote Sensing, Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, IranDepartment of Photogrammetry and Remote Sensing, Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, IranInstitute of Artificial Intelligence, USX, Shaoxing University, 508 West Huancheng Road, Yuecheng District, Shaoxing, Zhejiang Province, Postal Code 312000, ChinaAccurate estimation of regional rice yields is crucial for food security and efficient agricultural management. In this regard, the use of Unmanned Aerial Vehicles (UAVs) that have revolutionized crop monitoring by providing high-resolution images for precision agriculture, is beneficial. This study explores the potential of Segment Anything Model (SAM) for detecting rice seedlings, focusing on determining the optimal approach and prompt for this task. We examined three SAM scenarios: automatic mask generation, bounding box prompt, and point prompt. Our evaluation criteria included processing time, visual interpretation, and accuracy indexes. The results demonstrated the effectiveness of SAM in rice seedling detection, highlighting the importance of selecting the appropriate prompt for specific agricultural applications. Our findings reveal that the point prompt method emerges as the preferred choice for rice seedling detection, offering superior accuracy and reliability. Specifically, it achieved mIoU and mDice scores of 94.57 % and 0.97, respectively. While the bounding box approach showed promise, despite slightly lower precision, it may still be suitable depending on application-specific requirements. Conversely, the automatic mask generation scenario proved unsuitable for this task due to its low accuracy and inability to effectively detect rice seedlings. The outcomes of this study serve as a baseline for evaluating SAM prompts, guiding future improvements and refinements to enhance its performance in real-world agricultural applications.https://isprs-annals.copernicus.org/articles/X-G-2025/713/2025/isprs-annals-X-G-2025-713-2025.pdf
spellingShingle H. Rezvan
M. J. Valadan Zoej
F. Youssefi
F. Youssefi
A Segment Anything Model Approach for Rice Seedlings Detection Based on UAV Images
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title A Segment Anything Model Approach for Rice Seedlings Detection Based on UAV Images
title_full A Segment Anything Model Approach for Rice Seedlings Detection Based on UAV Images
title_fullStr A Segment Anything Model Approach for Rice Seedlings Detection Based on UAV Images
title_full_unstemmed A Segment Anything Model Approach for Rice Seedlings Detection Based on UAV Images
title_short A Segment Anything Model Approach for Rice Seedlings Detection Based on UAV Images
title_sort segment anything model approach for rice seedlings detection based on uav images
url https://isprs-annals.copernicus.org/articles/X-G-2025/713/2025/isprs-annals-X-G-2025-713-2025.pdf
work_keys_str_mv AT hrezvan asegmentanythingmodelapproachforriceseedlingsdetectionbasedonuavimages
AT mjvaladanzoej asegmentanythingmodelapproachforriceseedlingsdetectionbasedonuavimages
AT fyoussefi asegmentanythingmodelapproachforriceseedlingsdetectionbasedonuavimages
AT fyoussefi asegmentanythingmodelapproachforriceseedlingsdetectionbasedonuavimages
AT hrezvan segmentanythingmodelapproachforriceseedlingsdetectionbasedonuavimages
AT mjvaladanzoej segmentanythingmodelapproachforriceseedlingsdetectionbasedonuavimages
AT fyoussefi segmentanythingmodelapproachforriceseedlingsdetectionbasedonuavimages
AT fyoussefi segmentanythingmodelapproachforriceseedlingsdetectionbasedonuavimages