Cargando…

Rice Plant Counting, Locating, and Sizing Method Based on High-Throughput UAV RGB Images

Rice plant counting is crucial for many applications in rice production, such as yield estimation, growth diagnosis, disaster loss assessment, etc. Currently, rice counting still heavily relies on tedious and time-consuming manual operation. To alleviate the workload of rice counting, we employed an...

Descripción completa

Detalles Bibliográficos
Autores principales: Bai, Xiaodong, Liu, Pichao, Cao, Zhiguo, Lu, Hao, Xiong, Haipeng, Yang, Aiping, Cai, Zhe, Wang, Jianjun, Yao, Jianguo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AAAS 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10076056/
https://www.ncbi.nlm.nih.gov/pubmed/37040495
http://dx.doi.org/10.34133/plantphenomics.0020
_version_ 1785020053454848000
author Bai, Xiaodong
Liu, Pichao
Cao, Zhiguo
Lu, Hao
Xiong, Haipeng
Yang, Aiping
Cai, Zhe
Wang, Jianjun
Yao, Jianguo
author_facet Bai, Xiaodong
Liu, Pichao
Cao, Zhiguo
Lu, Hao
Xiong, Haipeng
Yang, Aiping
Cai, Zhe
Wang, Jianjun
Yao, Jianguo
author_sort Bai, Xiaodong
collection PubMed
description Rice plant counting is crucial for many applications in rice production, such as yield estimation, growth diagnosis, disaster loss assessment, etc. Currently, rice counting still heavily relies on tedious and time-consuming manual operation. To alleviate the workload of rice counting, we employed an UAV (unmanned aerial vehicle) to collect the RGB images of the paddy field. Then, we proposed a new rice plant counting, locating, and sizing method (RiceNet), which consists of one feature extractor frontend and 3 feature decoder modules, namely, density map estimator, plant location detector, and plant size estimator. In RiceNet, rice plant attention mechanism and positive–negative loss are designed to improve the ability to distinguish plants from background and the quality of the estimated density maps. To verify the validity of our method, we propose a new UAV-based rice counting dataset, which contains 355 images and 257,793 manual labeled points. Experiment results show that the mean absolute error and root mean square error of the proposed RiceNet are 8.6 and 11.2, respectively. Moreover, we validated the performance of our method with two other popular crop datasets. On these three datasets, our method significantly outperforms state-of-the-art methods. Results suggest that RiceNet can accurately and efficiently estimate the number of rice plants and replace the traditional manual method.
format Online
Article
Text
id pubmed-10076056
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher AAAS
record_format MEDLINE/PubMed
spelling pubmed-100760562023-04-06 Rice Plant Counting, Locating, and Sizing Method Based on High-Throughput UAV RGB Images Bai, Xiaodong Liu, Pichao Cao, Zhiguo Lu, Hao Xiong, Haipeng Yang, Aiping Cai, Zhe Wang, Jianjun Yao, Jianguo Plant Phenomics Research Article Rice plant counting is crucial for many applications in rice production, such as yield estimation, growth diagnosis, disaster loss assessment, etc. Currently, rice counting still heavily relies on tedious and time-consuming manual operation. To alleviate the workload of rice counting, we employed an UAV (unmanned aerial vehicle) to collect the RGB images of the paddy field. Then, we proposed a new rice plant counting, locating, and sizing method (RiceNet), which consists of one feature extractor frontend and 3 feature decoder modules, namely, density map estimator, plant location detector, and plant size estimator. In RiceNet, rice plant attention mechanism and positive–negative loss are designed to improve the ability to distinguish plants from background and the quality of the estimated density maps. To verify the validity of our method, we propose a new UAV-based rice counting dataset, which contains 355 images and 257,793 manual labeled points. Experiment results show that the mean absolute error and root mean square error of the proposed RiceNet are 8.6 and 11.2, respectively. Moreover, we validated the performance of our method with two other popular crop datasets. On these three datasets, our method significantly outperforms state-of-the-art methods. Results suggest that RiceNet can accurately and efficiently estimate the number of rice plants and replace the traditional manual method. AAAS 2023-01-30 2023 /pmc/articles/PMC10076056/ /pubmed/37040495 http://dx.doi.org/10.34133/plantphenomics.0020 Text en Copyright © 2023 Xiaodong Bai et al. https://creativecommons.org/licenses/by/4.0/Exclusive licensee Nanjing Agricultural University. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY 4.0) (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Research Article
Bai, Xiaodong
Liu, Pichao
Cao, Zhiguo
Lu, Hao
Xiong, Haipeng
Yang, Aiping
Cai, Zhe
Wang, Jianjun
Yao, Jianguo
Rice Plant Counting, Locating, and Sizing Method Based on High-Throughput UAV RGB Images
title Rice Plant Counting, Locating, and Sizing Method Based on High-Throughput UAV RGB Images
title_full Rice Plant Counting, Locating, and Sizing Method Based on High-Throughput UAV RGB Images
title_fullStr Rice Plant Counting, Locating, and Sizing Method Based on High-Throughput UAV RGB Images
title_full_unstemmed Rice Plant Counting, Locating, and Sizing Method Based on High-Throughput UAV RGB Images
title_short Rice Plant Counting, Locating, and Sizing Method Based on High-Throughput UAV RGB Images
title_sort rice plant counting, locating, and sizing method based on high-throughput uav rgb images
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10076056/
https://www.ncbi.nlm.nih.gov/pubmed/37040495
http://dx.doi.org/10.34133/plantphenomics.0020
work_keys_str_mv AT baixiaodong riceplantcountinglocatingandsizingmethodbasedonhighthroughputuavrgbimages
AT liupichao riceplantcountinglocatingandsizingmethodbasedonhighthroughputuavrgbimages
AT caozhiguo riceplantcountinglocatingandsizingmethodbasedonhighthroughputuavrgbimages
AT luhao riceplantcountinglocatingandsizingmethodbasedonhighthroughputuavrgbimages
AT xionghaipeng riceplantcountinglocatingandsizingmethodbasedonhighthroughputuavrgbimages
AT yangaiping riceplantcountinglocatingandsizingmethodbasedonhighthroughputuavrgbimages
AT caizhe riceplantcountinglocatingandsizingmethodbasedonhighthroughputuavrgbimages
AT wangjianjun riceplantcountinglocatingandsizingmethodbasedonhighthroughputuavrgbimages
AT yaojianguo riceplantcountinglocatingandsizingmethodbasedonhighthroughputuavrgbimages