DeepCorn: A semi-supervised deep learning method for high-throughput image-based corn kernel counting and yield estimation

被引:48
作者
Khaki, Saeed [1 ]
Pham, Hieu [2 ]
Han, Ye [2 ]
Kuhl, Andy [2 ]
Kent, Wade [2 ]
Wang, Lizhi [1 ]
机构
[1] Iowa State Univ, Dept Ind & Mfg Syst Engn, Ames, IA 50011 USA
[2] Syngenta Seeds, Slater, IA USA
基金
美国国家科学基金会;
关键词
Corn kernel counting; Convolutional neural network; Semi-supervised learning; Deep learning; Yield estimation; CROWD; REGRESSION; NETWORK;
D O I
10.1016/j.knosys.2021.106874
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The success of modern farming and plant breeding relies on accurate and efficient collection of data. For a commercial organization that manages large amounts of crops, collecting accurate and consistent data is a bottleneck. Due to limited time and labor, accurately phenotyping crops to record color, head count, height, weight, etc. is severely limited. However, this information, combined with other genetic and environmental factors, is vital for developing new superior crop species that help feed the world's growing population. Recent advances in machine learning, in particular deep learning, have shown promise in mitigating this bottleneck. In this paper, we propose a novel deep learning method for counting on-ear corn kernels in-field to aid in the gathering of real-time data and, ultimately, to improve decision making to maximize yield. We name this approach DeepCorn, and show that this framework is robust under various conditions. DeepCorn estimates the density of corn kernels in an image of corn ears and predicts the number of kernels based on the estimated density map. DeepCorn uses a truncated VGG-16 as a backbone for feature extraction and merges feature maps from multiple scales of the network to make it robust against image scale variations. We also adopt a semi-supervised learning approach to further improve the performance of our proposed method. Our proposed method achieves the MAE and RMSE of 41.36 and 60.27 in the corn kernel counting task, respectively. Our experimental results demonstrate the superiority and effectiveness of our proposed method compared to other state-of-the-art methods. (c) 2021 Elsevier B.V. All rights reserved.
引用
收藏
页数:12
相关论文
共 72 条
[1]  
Abadi Martin, 2016, arXiv
[2]  
[Anonymous], 2008, Handbook of maize: its biology
[3]  
Berardi D., 2019, 2019 FALL M, V2019
[4]   CrowdNet: A Deep Convolutional Network for Dense Crowd Counting [J].
Boominathan, Lokesh ;
Kruthiventi, Srinivas S. S. ;
Babu, R. Venkatesh .
MM'16: PROCEEDINGS OF THE 2016 ACM MULTIMEDIA CONFERENCE, 2016, :640-644
[5]   Scale Aggregation Network for Accurate and Efficient Crowd Counting [J].
Cao, Xinkun ;
Wang, Zhipeng ;
Zhao, Yanyun ;
Su, Fei .
COMPUTER VISION - ECCV 2018, PT V, 2018, 11209 :757-773
[6]   Deep Clustering for Unsupervised Learning of Visual Features [J].
Caron, Mathilde ;
Bojanowski, Piotr ;
Joulin, Armand ;
Douze, Matthijs .
COMPUTER VISION - ECCV 2018, PT XIV, 2018, 11218 :139-156
[7]   Bayesian Poisson Regression for Crowd Counting [J].
Chan, Antoni B. ;
Vasconcelos, Nuno .
2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, :545-551
[8]  
Chandrakasan AP, 2008, SYMP VLSI CIRCUITS, P1
[9]   Scale Pyramid Network for Crowd Counting [J].
Chen, Xinya ;
Bin, Yanrui ;
Sang, Nong ;
Gao, Changxin .
2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, :1941-1950
[10]   X-FIDO: An Effective Application for Detecting Olive Quick Decline Syndrome with Deep Learning and Data Fusion [J].
Cruz, Albert C. ;
Luvisi, Andrea ;
De Bellis, Luigi ;
Ampatzidis, Yiannis .
FRONTIERS IN PLANT SCIENCE, 2017, 8