Automated Counting of Rice Panicle by Applying Deep Learning Model to Images from Unmanned Aerial Vehicle Platform
文献类型： 外文期刊
作者： Zhou, Chengquan 1 ; Ye, Hongbao 1 ; Hu, Jun 1 ; Shi, Xiaoyan 1 ; Hua, Shan 1 ; Yue, Jibo 2 ; Xu, Zhifu 1 ; Yang, Guijun 2 ;
作者机构： 1.ZAAS, Inst Agr Equipment, Hangzhou 310000, Zhejiang, Peoples R China
2.Minist Agr China, Beijing Res Ctr Informat Technol Agr, Key Lab Quantitat Remote Sensing Agr, Beijing 100089, Peoples R China
3.Minist Agr, Key Lab Agriinformat, Beijing 100089, Peoples R China
关键词： rice panicle counting; UAV platform; deep learning; yield estimation
期刊名称：SENSORS （ 影响因子：3.576； 五年影响因子：3.735 ）
ISSN： 1424-8220
年卷期： 2019 年 19 卷 14 期
页码：
收录情况： SCI
摘要： The number of panicles per unit area is a common indicator of rice yield and is of great significance to yield estimation, breeding, and phenotype analysis. Traditional counting methods have various drawbacks, such as long delay times and high subjectivity, and they are easily perturbed by noise. To improve the accuracy of rice detection and counting in the field, we developed and implemented a panicle detection and counting system that is based on improved region-based fully convolutional networks, and we use the system to automate rice-phenotype measurements. The field experiments were conducted in target areas to train and test the system and used a rotor light unmanned aerial vehicle equipped with a high-definition RGB camera to collect images. The trained model achieved a precision of 0.868 on a held-out test set, which demonstrates the feasibility of this approach. The algorithm can deal with the irregular edge of the rice panicle, the significantly different appearance between the different varieties and growing periods, the interference due to color overlapping between panicle and leaves, and the variations in illumination intensity and shading effects in the field. The result is more accurate and efficient recognition of rice-panicles, which facilitates rice breeding. Overall, the approach of training deep learning models on increasingly large and publicly available image datasets presents a clear path toward smartphone-assisted crop disease diagnosis on a global scale.
- 相关文献
作者其他论文 更多>>
-
An automated lightweight approach for detecting dead fish in a recirculating aquaculture system
作者：Zhou, Chengquan;Wang, Chenye;Sun, Dawei;Hu, Jun;Ye, Hongbao;Wang, Chenye
关键词：YOLO; Dead fish; RAS; Image processing; Lightweight framework
-
Insights into the Metabolite Differentiation Mechanism Between Chinese Dry-Cured Fatty Ham and Lean Ham Through UPLC-MS/MS-Based Untargeted Metabolomics
作者：Xie, Ruoyu;Liu, Yaqiong;Wu, Xiaoli;Hu, Jun;Chen, Wenxuan;Zhao, Ke;Li, Huanhuan;Chen, Lihong;Zhang, Jin;Du, Hongying
关键词：fatty ham; lean ham; Chinese dry-cured ham; untargeted metabolomics; UPLC-MS/MS; differential metabolite
-
TDR-Transformer: A transformer neural network model to determine soil relative permittivity variations along a time domain reflectometry sensor waveguide
作者：Wang, Zhuangji;Timlin, Dennis;Fleisher, David;Sun, Wenguang;Beegum, Sahila;Reddy, Vangimalla R.;Wang, Zhuangji;Tully, Katherine;Gong, Xiaofei;Kojima, Yuki;Hua, Shan;Sun, Wenguang;Beegum, Sahila;Horton, Robert
关键词：Time Domain Reflectometry (TDR); TDR waveform interpretation; Nonuniform relative permittivity (epsilon r ); Transformer neural network; Machine learning
-
Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep Learning
作者：Li, Jiangtao;Yang, Xiaolian;Ye, Hongbao;Zhou, Chengquan;Li, Zhuo;Wei, Qiquan;Li, Chen;Sun, Dawei;Ye, Hongbao;Zhou, Chengquan;Li, Chen;Sun, Dawei
关键词：Chinese mitten crab;
Eriocheir sinensis ; grading; machine learning; YOLO -
CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture Systems
作者：Shao, Wei;Shao, Wei;Zhou, Chengquan;Sun, Dawei;Li, Chen;Ye, Hongbao;Zhou, Chengquan;Sun, Dawei;Li, Chen;Ye, Hongbao
关键词：aquaculture; BiGRU; convolutional neural network (CNN); fault detection; transformer
-
Nondestructive detection of multiple dried squid qualities by hyperspectral imaging combined with 1D-KAN-CNN
作者：Hu, Jun;Sun, Dawei;Zhou, Hongkui;Lou, Weidong;Zhang, Jin;Zhou, Chengquan;Chen, Wenxuan;Jiang, Yuanhao;Zhou, Chengquan;Chen, Wenxuan
关键词：Dried squid; Quality assessment; Kolmogorov-Arnold network; Wavelength selection; Hyperspectral imaging
-
A Novel Multinozzle Targeting Pollination Robot for Clustered Kiwifruit Flowers Based on Air-Liquid Dual-Flow Spraying
作者：Gao, Changqing;He, Leilei;Ding, Yusong;Murengami, Bryan Gilbert;Li, Rui;Fu, Longsheng;Chen, Jinyong;Chen, Jinyong;Zhou, Chengquan;Ye, Hongbao;Zhou, Chengquan;Ye, Hongbao
关键词：clustered kiwifruit flowers; multinozzle end-effector-optimal; pollination robot; spray parameters
