A longan yield estimation approach based on UAV images and deep learning
Longan yield estimation is an important practice before longan harvests. Statistical longan yield data can provide an important reference for market pricing and improving harvest efficiency and can directly determine the economic benefits of longan orchards. At present, the statistical work concerni...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-03-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1132909/full |
| _version_ | 1811159563393564672 |
|---|---|
| author | Denghui Li Denghui Li Xiaoxuan Sun Xiaoxuan Sun Xiaoxuan Sun Yuhang Jia Zhongwei Yao Peiyi Lin Yingyi Chen Haobo Zhou Zhengqi Zhou Kaixuan Wu Linlin Shi Jun Li Jun Li |
| author_facet | Denghui Li Denghui Li Xiaoxuan Sun Xiaoxuan Sun Xiaoxuan Sun Yuhang Jia Zhongwei Yao Peiyi Lin Yingyi Chen Haobo Zhou Zhengqi Zhou Kaixuan Wu Linlin Shi Jun Li Jun Li |
| author_sort | Denghui Li |
| collection | DOAJ |
| description | Longan yield estimation is an important practice before longan harvests. Statistical longan yield data can provide an important reference for market pricing and improving harvest efficiency and can directly determine the economic benefits of longan orchards. At present, the statistical work concerning longan yields requires high labor costs. Aiming at the task of longan yield estimation, combined with deep learning and regression analysis technology, this study proposed a method to calculate longan yield in complex natural environment. First, a UAV was used to collect video images of a longan canopy at the mature stage. Second, the CF-YD model and SF-YD model were constructed to identify Cluster_Fruits and Single_Fruits, respectively, realizing the task of automatically identifying the number of targets directly from images. Finally, according to the sample data collected from real orchards, a regression analysis was carried out on the target quantity detected by the model and the real target quantity, and estimation models were constructed for determining the Cluster_Fruits on a single longan tree and the Single_Fruits on a single Cluster_Fruit. Then, an error analysis was conducted on the data obtained from the manual counting process and the estimation model, and the average error rate regarding the number of Cluster_Fruits was 2.66%, while the average error rate regarding the number of Single_Fruits was 2.99%. The results show that the method proposed in this paper is effective at estimating longan yields and can provide guidance for improving the efficiency of longan fruit harvests. |
| first_indexed | 2024-04-10T05:43:18Z |
| format | Article |
| id | doaj.art-91c5caec3ffc4be3bdc0313c2c505789 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-10T05:43:18Z |
| publishDate | 2023-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-91c5caec3ffc4be3bdc0313c2c5057892023-03-06T05:21:03ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-03-011410.3389/fpls.2023.11329091132909A longan yield estimation approach based on UAV images and deep learningDenghui Li0Denghui Li1Xiaoxuan Sun2Xiaoxuan Sun3Xiaoxuan Sun4Yuhang Jia5Zhongwei Yao6Peiyi Lin7Yingyi Chen8Haobo Zhou9Zhengqi Zhou10Kaixuan Wu11Linlin Shi12Jun Li13Jun Li14College of Engineering, South China Agricultural University, Guangzhou, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, Guangzhou, ChinaKey Laboratory of South China Agricultural Plant Molecular Analysis and Genetic Improvement, Guangdong Provincial Key Laboratory of Applied Botany, South China Botanical Garden, Chinese Academy of Sciences, Guangzhou, ChinaSouth China National Botanical Garden, Guangzhou, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, Guangzhou, ChinaLongan yield estimation is an important practice before longan harvests. Statistical longan yield data can provide an important reference for market pricing and improving harvest efficiency and can directly determine the economic benefits of longan orchards. At present, the statistical work concerning longan yields requires high labor costs. Aiming at the task of longan yield estimation, combined with deep learning and regression analysis technology, this study proposed a method to calculate longan yield in complex natural environment. First, a UAV was used to collect video images of a longan canopy at the mature stage. Second, the CF-YD model and SF-YD model were constructed to identify Cluster_Fruits and Single_Fruits, respectively, realizing the task of automatically identifying the number of targets directly from images. Finally, according to the sample data collected from real orchards, a regression analysis was carried out on the target quantity detected by the model and the real target quantity, and estimation models were constructed for determining the Cluster_Fruits on a single longan tree and the Single_Fruits on a single Cluster_Fruit. Then, an error analysis was conducted on the data obtained from the manual counting process and the estimation model, and the average error rate regarding the number of Cluster_Fruits was 2.66%, while the average error rate regarding the number of Single_Fruits was 2.99%. The results show that the method proposed in this paper is effective at estimating longan yields and can provide guidance for improving the efficiency of longan fruit harvests.https://www.frontiersin.org/articles/10.3389/fpls.2023.1132909/fullyield estimationUAV imageconvolutional neural networkimage analysisregression analysis |
| spellingShingle | Denghui Li Denghui Li Xiaoxuan Sun Xiaoxuan Sun Xiaoxuan Sun Yuhang Jia Zhongwei Yao Peiyi Lin Yingyi Chen Haobo Zhou Zhengqi Zhou Kaixuan Wu Linlin Shi Jun Li Jun Li A longan yield estimation approach based on UAV images and deep learning Frontiers in Plant Science yield estimation UAV image convolutional neural network image analysis regression analysis |
| title | A longan yield estimation approach based on UAV images and deep learning |
| title_full | A longan yield estimation approach based on UAV images and deep learning |
| title_fullStr | A longan yield estimation approach based on UAV images and deep learning |
| title_full_unstemmed | A longan yield estimation approach based on UAV images and deep learning |
| title_short | A longan yield estimation approach based on UAV images and deep learning |
| title_sort | longan yield estimation approach based on uav images and deep learning |
| topic | yield estimation UAV image convolutional neural network image analysis regression analysis |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1132909/full |
| work_keys_str_mv | AT denghuili alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT denghuili alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT xiaoxuansun alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT xiaoxuansun alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT xiaoxuansun alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT yuhangjia alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT zhongweiyao alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT peiyilin alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT yingyichen alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT haobozhou alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT zhengqizhou alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT kaixuanwu alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT linlinshi alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT junli alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT junli alonganyieldestimationapproachbasedonuavimagesanddeeplearning AT denghuili longanyieldestimationapproachbasedonuavimagesanddeeplearning AT denghuili longanyieldestimationapproachbasedonuavimagesanddeeplearning AT xiaoxuansun longanyieldestimationapproachbasedonuavimagesanddeeplearning AT xiaoxuansun longanyieldestimationapproachbasedonuavimagesanddeeplearning AT xiaoxuansun longanyieldestimationapproachbasedonuavimagesanddeeplearning AT yuhangjia longanyieldestimationapproachbasedonuavimagesanddeeplearning AT zhongweiyao longanyieldestimationapproachbasedonuavimagesanddeeplearning AT peiyilin longanyieldestimationapproachbasedonuavimagesanddeeplearning AT yingyichen longanyieldestimationapproachbasedonuavimagesanddeeplearning AT haobozhou longanyieldestimationapproachbasedonuavimagesanddeeplearning AT zhengqizhou longanyieldestimationapproachbasedonuavimagesanddeeplearning AT kaixuanwu longanyieldestimationapproachbasedonuavimagesanddeeplearning AT linlinshi longanyieldestimationapproachbasedonuavimagesanddeeplearning AT junli longanyieldestimationapproachbasedonuavimagesanddeeplearning AT junli longanyieldestimationapproachbasedonuavimagesanddeeplearning |