A methodology of weed-crop classification based on autonomous models choosing and ensemble

Neural networks play an important role in crop-weed classification have high accuracy more than 95%. Manually choosing models and fine-tuning are laborious, yet it is indispensable in most traditional practices and researches. Moreover, classic training metric are not thoroughly compatible with farming tasks, that a model still have a noticeable chance of miss classifying crop to weed while it reach higher accuracy even more than 99%. In this paper we demonstrate a methodology of weed-crop classification based on autonomous models choosing and ensemble that could make models choosing and tunning automatically, and improve the prediction with high accuracy(>99% for both data set) in specific class with low risk in incorrect predicting.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Rafael Rieder,et al.  Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review , 2018, Comput. Electron. Agric..

[3]  Flavio B. P. Malavazi,et al.  LiDAR-only based navigation algorithm for an autonomous agricultural robot , 2018, Comput. Electron. Agric..

[4]  Andreas Kamilaris,et al.  Deep learning in agriculture: A survey , 2018, Comput. Electron. Agric..

[5]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[6]  Qingquan Song,et al.  Auto-Keras: An Efficient Neural Architecture Search System , 2018, KDD.

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Shay B. Cohen,et al.  Advances in Neural Information Processing Systems 25 , 2012, NIPS 2012.

[9]  Wen Zhang,et al.  A review on weed detection using ground-based machine vision and image processing techniques , 2019, Comput. Electron. Agric..

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Kevin Leyton-Brown,et al.  Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms , 2012, KDD.

[12]  Tristan Perez,et al.  A Rapidly Deployable Classification System using Visual Data for the Application of Precision Weed Management , 2018, Comput. Electron. Agric..

[13]  Joachim Hertzberg,et al.  Plant classification with In-Field-Labeling for crop/weed discrimination using spectral features and 3D surface features from a multi-wavelength laser line profile system , 2017, Comput. Electron. Agric..

[14]  M. Winter,et al.  Agriculture 4.0: Making it work for people, production, and the planet , 2021, Land Use Policy.