Tiller estimation method using deep neural networks

被引:2
作者
Kinose, Rikuya [1 ]
Utsumi, Yuzuko [1 ,2 ]
Iwamura, Masakazu [1 ,2 ]
Kise, Koichi [1 ,2 ]
机构
[1] Osaka Prefecture Univ, Grad Sch Engn, Sakai, Japan
[2] Osaka Metropolitan Univ, Grad Sch Informat, Sakai, Japan
关键词
tiller number estimation; deep neural network (DNN); pretext task; self-supervised learning; regression; SYSTEM; WHEAT;
D O I
10.3389/fpls.2022.1016507
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
This paper describes a method based on a deep neural network (DNN) for estimating the number of tillers on a plant. A tiller is a branch on a grass plant, and the number of tillers is one of the most important determinants of yield. Traditionally, the tiller number is usually counted by hand, and so an automated approach is necessary for high-throughput phenotyping. Conventional methods use heuristic features to estimate the tiller number. Based on the successful application of DNNs in the field of computer vision, the use of DNN-based features instead of heuristic features is expected to improve the estimation accuracy. However, as DNNs generally require large volumes of data for training, it is difficult to apply them to estimation problems for which large training datasets are unavailable. In this paper, we use two strategies to overcome the problem of insufficient training data: the use of a pretrained DNN model and the use of pretext tasks for learning the feature representation. We extract features using the resulting DNNs and estimate the tiller numbers through a regression technique. We conducted experiments using side-view whole plant images taken with plan backgroud. The experimental results show that the proposed methods using a pretrained model and specific pretext tasks achieve better performance than the conventional method.
引用
收藏
页数:11
相关论文
共 37 条
[1]   DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning [J].
Aich, Shubhra ;
Josuttes, Anique ;
Ovsyannikov, Ilya ;
Strueby, Keegan ;
Ahmed, Imran ;
Duddu, Hema Sudhakar ;
Pozniak, Curtis ;
Shirtliffe, Steve ;
Stavness, Ian .
2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018), 2018, :323-332
[2]   Leaf Counting with Deep Convolutional and Deconvolutional Networks [J].
Aich, Shubhra ;
Stavness, Ian .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017), 2017, :2080-2089
[3]   Automated estimation of tiller number in wheat by ribbon detection [J].
Boyle, R. D. ;
Corke, F. M. K. ;
Doonan, J. H. .
MACHINE VISION AND APPLICATIONS, 2016, 27 (05) :637-646
[4]  
Deng J., RetinaFace: Single-stage Dense Face Localisation in the Wild
[5]   Deep learning-based automatic detection of productive tillers in rice [J].
Deng, Ruoling ;
Jiang, Yu ;
Tao, Ming ;
Huang, Xunan ;
Bangura, Kemoh ;
Liu, Chuang ;
Lin, Jingchuan ;
Qi, Long .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2020, 177
[6]   Leveraging multiple datasets for deep leaf counting [J].
Dobrescu, Andrei ;
Giuffrida, Mario Valerio ;
Tsaftaris, Sotirios A. .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017), 2017, :2072-2079
[7]   A Versatile Phenotyping System and Analytics Platform Reveals Diverse Temporal Responses to Water Availability in Setaria [J].
Fahlgren, Noah ;
Feldman, Maximilian ;
Gehan, Malia A. ;
Wilson, Melinda S. ;
Shyu, Christine ;
Bryant, Douglas W. ;
Hill, Steven T. ;
McEntee, Colton J. ;
Warnasooriya, Sankalpi N. ;
Kumar, Indrajit ;
Ficor, Tracy ;
Turnipseed, Stephanie ;
Gilbert, Kerrigan B. ;
Brutnell, Thomas P. ;
Carrington, James C. ;
Mockler, Todd C. ;
Baxter, Ivan .
MOLECULAR PLANT, 2015, 8 (10) :1520-1535
[8]  
Frangi AF, 1998, LECT NOTES COMPUT SC, V1496, P130, DOI 10.1007/BFb0056195
[9]   ChronoRoot: High-throughput phenotyping by deep segmentation networks reveals novel temporal parameters of plant root system architecture [J].
Gaggion, Nicolas ;
Ariel, Federico ;
Daric, Vladimir ;
Lambert, Eric ;
Legendre, Simon ;
Roule, Thomas ;
Camoirano, Alejandra ;
Milone, Diego H. ;
Crespi, Martin ;
Blein, Thomas ;
Ferrante, Enzo .
GIGASCIENCE, 2021, 10 (07)
[10]  
Gidaris Spyros., 2018, ICLR