Classification of Weeds and Crops at the Pixel-Level Using Convolutional Neural Networks and Data Augmentation

The Pixel-Level Classification of crops and weeds is an open problem in computer vision. The use of agrochemicals is necessary for effective weed control, but one of the great challenges of precision agriculture is to reduce their use while maintaining high crop yields. Recently, automated weed control techniques based on computer vision were developed despite experiencing difficulties in creating agricultural datasets. One possible solution to the small volume of data available is Data Augmentation. This paper investigates the impact of individual data augmentation transformations on the pixel-level classification of crops and weeds when using a Deep Learning model. It also investigates the influence of input image resolution on the classification performance and proposes a patch augmentation strategy. Results have shown that applying individual transformations can be valuable to the model, but gets outperformed by the combination of all transformations. This work also finds that higher resolution inputs can increase the classification performance when combined with augmentation techniques, and that patch augmentation can be a valuable asset when dealing with a small number of high-resolution images. The method reaches the mark of 83.44% in Average Dice Similarity Coefficient, an increase of 19.96% percentage points compared to the non-augmented model.

[1]  Roland Siegwart,et al.  weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming , 2017, IEEE Robotics and Automation Letters.

[2]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[3]  Jörn Ostermann,et al.  A Crop/Weed Field Image Dataset for the Evaluation of Computer Vision Based Precision Agriculture Tasks , 2014, ECCV Workshops.

[4]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling , 2015, CVPR 2015.

[5]  Bruno J. T. Fernandes,et al.  Extreme learning machine autoencoder for data augmentation , 2017, 2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI).

[6]  Ciro Potena,et al.  Automatic model based dataset generation for fast and accurate crop and weeds detection , 2016, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[7]  Wang Ping,et al.  Research on data augmentation for image classification based on convolution neural networks , 2017, 2017 Chinese Automation Congress (CAC).

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Cyrill Stachniss,et al.  WeedMap: A large-scale semantic weed mapping framework using aerial multispectral imaging and deep neural network for precision farming , 2018, Remote. Sens..

[10]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[11]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[12]  Takashi Matsubara,et al.  Data Augmentation Using Random Image Cropping and Patching for Deep CNNs , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[13]  Cyrill Stachniss,et al.  Joint Stem Detection and Crop-Weed Classification for Plant-Specific Treatment in Precision Farming , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[14]  Matheus Gutoski,et al.  The Effect of Data Augmentation on the Performance of Convolutional Neural Networks , 2018 .

[15]  Wolfram Burgard,et al.  Agricultural robot dataset for plant classification, localization and mapping on sugar beet fields , 2017, Int. J. Robotics Res..

[16]  Cyrill Stachniss,et al.  Real-Time Semantic Segmentation of Crop and Weed for Precision Agriculture Robots Leveraging Background Knowledge in CNNs , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[17]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[18]  Fabrício Martins Lopes,et al.  A Computer Vision Approach for Automatic Measurement of the Inter-plant Spacing , 2015, CIARP.

[19]  Nelson Marcelo Romero Aquino,et al.  Patch-Based Convolutional Neural Network for the Writer Classification Problem in Music Score Images , 2018 .

[20]  Luc Van Gool,et al.  Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection , 2016 .

[21]  Juntang Zhuang,et al.  LadderNet: Multi-path networks based on U-Net for medical image segmentation , 2018, ArXiv.

[22]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

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

[24]  Cyrill Stachniss,et al.  Fully Convolutional Networks With Sequential Information for Robust Crop and Weed Detection in Precision Farming , 2018, IEEE Robotics and Automation Letters.

[25]  Daniele Nardi,et al.  Crop and Weeds Classification for Precision Agriculture Using Context-Independent Pixel-Wise Segmentation , 2019, 2019 Third IEEE International Conference on Robotic Computing (IRC).