SpikeletFCN: Counting Spikelets from Infield Wheat Crop Images Using Fully Convolutional Networks

Currently, crop management through automatic monitoring is growing momentum, but presents various challenges. One key challenge is to quantify yield traits from images captured automatically. Wheat is one of the three major crops in the world with a total demand expected to exceed 850 million tons by 2050. In this paper we attempt estimation of wheat spikelets from high-definition RGB infield images using a fully convolutional model. We propose also the use of transfer learning and segmentation to improve the model. We report cross validated Mean Absolute Error (MAE) and Mean Square Error (MSE) of 53.0, 71.2 respectively on 15 real field images. We produce visualisations which show the good fit of our model to the task. We also concluded that both transfer learning and segmentation lead to a very positive impact for CNN-based models, reducing error by up to 89%, when extracting key traits such as wheat spikelet counts.

[1]  T. Pridmore,et al.  Plant Phenomics, From Sensors to Knowledge , 2017, Current Biology.

[2]  Xiaogang Wang,et al.  Cross-scene crowd counting via deep convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  A. Krzyżak,et al.  White Blood Cell Differential Counts Using Convolutional Neural Networks for Low Resolution Images , 2013, ICAISC.

[4]  Yoshua Bengio,et al.  Count-ception: Counting by Fully Convolutional Redundant Counting , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[5]  Tommy W. S. Chow,et al.  A neural-based crowd estimation by hybrid global learning algorithm , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[6]  Simon Griffiths,et al.  CropQuant : An automated and scalable field phenotyping platform for crop 1 monitoring and trait measurements to facilitate breeding and digital agriculture , 2017 .

[7]  Frédéric Baret,et al.  Ear density estimation from high resolution RGB imagery using deep learning technique , 2019, Agricultural and Forest Meteorology.

[8]  Andrew Zisserman,et al.  Learning To Count Objects in Images , 2010, NIPS.

[9]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[10]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Richard S. Zemel,et al.  End-to-End Instance Segmentation with Recurrent Attention , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Tony P. Pridmore,et al.  Deep Learning for Multi-task Plant Phenotyping , 2017, bioRxiv.

[13]  Zhiguo Cao,et al.  TasselNet: counting maize tassels in the wild via local counts regression network , 2017, Plant Methods.

[14]  J. Soussana,et al.  Adapting agriculture to climate change , 2007, Proceedings of the National Academy of Sciences.

[15]  C. A. Simon,et al.  Local government perspectives of federal land management in Nevada , 2003 .

[16]  Hai Tao,et al.  A Viewpoint Invariant Approach for Crowd Counting , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[17]  Sridha Sridharan,et al.  Crowd Counting Using Multiple Local Features , 2009, 2009 Digital Image Computing: Techniques and Applications.

[18]  Hamid Laga,et al.  Detection and analysis of wheat spikes using Convolutional Neural Networks , 2018, Plant Methods.

[19]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[20]  Richard F. Lyon,et al.  Neural Networks for Machine Learning , 2017 .

[21]  Ullrich Köthe,et al.  Learning to count with regression forest and structured labels , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[22]  Marimuthu Palaniswami,et al.  Internet of Things (IoT): A vision, architectural elements, and future directions , 2012, Future Gener. Comput. Syst..

[23]  Andrew Zisserman,et al.  Counting in the Wild , 2016, ECCV.

[24]  J. Bruinsma,et al.  World agriculture towards 2030/2050: the 2012 revision , 2012 .

[25]  S. Tsaftaris,et al.  Learning to Count Leaves in Rosette Plants , 2015 .

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