Monitoring of Soybean Maturity Using UAV Remote Sensing and Deep Learning
文献类型: 外文期刊
第一作者: Zhang, Shanxin
作者: Zhang, Shanxin;Feng, Hao;Han, Shaoyu;Shi, Zhengkai;Xu, Haoran;Yue, Jibo;Han, Shaoyu;Liu, Yang;Feng, Haikuan;Zhou, Chengquan;Liu, Yang;Feng, Haikuan;Zhou, Chengquan
作者机构:
关键词: unmanned aerial vehicle; soybean; convolutional neural network; deep learning
期刊名称:AGRICULTURE-BASEL ( 影响因子:3.6; 五年影响因子:3.6 )
ISSN:
年卷期: 2023 年 13 卷 1 期
页码:
收录情况: SCI
摘要: Soybean breeders must develop early-maturing, standard, and late-maturing varieties for planting at different latitudes to ensure that soybean plants fully utilize solar radiation. Therefore, timely monitoring of soybean breeding line maturity is crucial for soybean harvesting management and yield measurement. Currently, the widely used deep learning models focus more on extracting deep image features, whereas shallow image feature information is ignored. In this study, we designed a new convolutional neural network (CNN) architecture, called DS-SoybeanNet, to improve the performance of unmanned aerial vehicle (UAV)-based soybean maturity information monitoring. DS-SoybeanNet can extract and utilize both shallow and deep image features. We used a high-definition digital camera on board a UAV to collect high-definition soybean canopy digital images. A total of 2662 soybean canopy digital images were obtained from two soybean breeding fields (fields F1 and F2). We compared the soybean maturity classification accuracies of (i) conventional machine learning methods (support vector machine (SVM) and random forest (RF)), (ii) current deep learning methods (InceptionResNetV2, MobileNetV2, and ResNet50), and (iii) our proposed DS-SoybeanNet method. Our results show the following: (1) The conventional machine learning methods (SVM and RF) had faster calculation times than the deep learning methods (InceptionResNetV2, MobileNetV2, and ResNet50) and our proposed DS-SoybeanNet method. For example, the computation speed of RF was 0.03 s per 1000 images. However, the conventional machine learning methods had lower overall accuracies (field F2: 63.37-65.38%) than the proposed DS-SoybeanNet (Field F2: 86.26%). (2) The performances of the current deep learning and conventional machine learning methods notably decreased when tested on a new dataset. For example, the overall accuracies of MobileNetV2 for fields F1 and F2 were 97.52% and 52.75%, respectively. (3) The proposed DS-SoybeanNet model can provide high-performance soybean maturity classification results. It showed a computation speed of 11.770 s per 1000 images and overall accuracies for fields F1 and F2 of 99.19% and 86.26%, respectively.
分类号:
- 相关文献
作者其他论文 更多>>
-
Accurate genomic selection using low-density SNP panels preselected by maximum likelihood estimation
作者:Qu, Shiyu;Lu, Sheng;Liu, Yang;Li, Ming;Chen, Songlin;Qu, Shiyu;Lu, Sheng;Liu, Yang;Li, Ming;Chen, Songlin;Qu, Shiyu;Lu, Sheng;Liu, Yang;Li, Ming;Chen, Songlin;Chen, Songlin
关键词:Maximum likelihood estimation; Genomic selection; SNP pre-selection; MLE-rank
-
Disturbance mitigation of thiencarbazone-methyl•isoxaflutole on bacterial communities through nitrification inhibitor and attapulgite
作者:Wang, Yonglu;Zhang, Fengsong;Liao, Xiaoyong;Yang, Xiao;Wang, Yonglu;Zhang, Guixiang;Wen, Jiongxin;Ju, Xiaorong;Xu, Can;Zhang, Liyun;Wei, Chaojun;Shi, Pengge;Liu, Yang;Lan, Ying
关键词:Maize production; Black soil; Herbicides; Toxic effects; Soil microflora
-
Development of a 20 K SNP array for the leopard coral grouper, Plectropomus leopardus
作者:Zhou, Qian;Lu, Sheng;Liu, Yang;Chen, Songlin;Zhou, Qian;Lu, Sheng;Liu, Yang;Chen, Songlin;Zhou, Bo;Zhou, Qian;Chen, Songlin
关键词:Leopard coral grouper; Plectropomus leopardus; SNP array; Aquaculture
-
Evaluation of regulatory capacity of three lactic acid bacteria on the growth performance, non-specific immunity, and intestinal microbiota of the sea cucumber Apostichopus japonicus
作者:Liu, Longzhen;Liu, Yang;Qin, Guangcai;Wei, Cong;Li, Yongmei;Cui, Liang;Tian, Xiangli;Liu, Longzhen
关键词:Growth performance; Non-specific immunity; Intestinal microbiota; Probiotics; Apostichopus japonicus
-
Constructing carbon-based materials loaded with MOFs to realize efficient anaerobic digestion of rural organic waste
作者:Ye, Xiaomei;Jia, Zhaoyan;Liu, Yang;Wang, Chengcheng;Cao, Chunhui;Zhang, Yingpeng;Han, Ting;Wang, Li;Guo, Ting;Xi, Yonglan;Ye, Xiaomei;Jia, Zhaoyan;Liu, Yang;Wang, Chengcheng;Cao, Chunhui;Zhang, Yingpeng;Han, Ting;Wang, Li;Guo, Ting;Xi, Yonglan;Ye, Xiaomei;Jia, Zhaoyan;Liu, Yang;Wang, Chengcheng;Cao, Chunhui;Zhang, Yingpeng;Han, Ting;Wang, Li;Guo, Ting;Xi, Yonglan;Wang, Chengcheng;Cao, Chunhui;Xi, Yonglan;Xi, Yonglan
关键词:Anaerobic digestion; Metal-organic frameworks; Ammonia nitrogen inhibition; CSTR; Rural organic waste
-
Development of an RPA-based CRISPR/Cas12a assay in combination with a lateral flow strip for rapid detection of toxigenic Fusarium verticillioides in maize
作者:Liang, Xiaoyan;Xi, Kaifei;Guo, Wei;Zhang, Xiu;Liu, Yang;Liang, Xiaoyan;Jijakli, M. Haissam
关键词:Fusarium verticillioides; Recombinase polymerase amplification (RPA); Cas12a; Lateral flow detection; Maize
-
First record of Alternaria tenuissima causing Aloe barbadensis leaf blight and leaf spot disease in Beijing, China
作者:Ahmad, Tanvir;Nie, Chengrong;Liu, Yang;Liu, Yang;Cao, Changyu;Xiao, Ying;Yu, Xi
关键词:Aloe barbadensis; Leaf blight and spot; Alternaria tenuissima; Pathogen