Automatic detection of fruits in coffee crops from aerial images

A big challenge in the precision agriculture is the detection of fruits in coffee crops on agricultural environments. This paper presents a comparison of four features set to detect the red fruits (mature) in Coffee plants. An Unmanned Aerial Vehicle (UAV) is used to obtain high-resolution RGB images of a coffee hall. The proposed methodology enables the extraction of visual features from image regions and uses supervised Machine Learning (ML) techniques to classify areas as coffee fruits and non-fruits (e.g. branches and leaves). Several ML methods were compared using the test data achieved from a Coffee plantation. Experimental results show that the ANN model is more reliable than other ML methods for accurately identifying coffee fruits.

[1]  Geoffrey I. Webb.  Lazy Learning , 2010, Encyclopedia of Machine Learning.

[2]  Salah Sukkarieh,et al.  Orchard fruit segmentation using multi-spectral feature learning , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Sanjiv Singh,et al.  Yield estimation in vineyards by visual grape detection , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  L. Johnson,et al.  FEASIBILITY OF MONITORING COFFEE FIELD RIPENESS WITH AIRBORNE MULTISPECTRAL IMAGERY , 2004 .

[5]  Won Suk Lee,et al.  Green citrus detection using fast Fourier transform (FFT) leakage , 2012, Precision Agriculture.

[6]  G. Rabatel,et al.  Grape berry calibration by computer vision using elliptical model fitting , 2007 .

[7]  G. Dunn,et al.  Yield prediction from digital image analysis: A technique with potential for vineyard assessments prior to harvest , 2008 .

[8]  P. Hardin,et al.  An Unmanned Aerial Vehicle for Rangeland Photography , 2005 .

[9]  Salah Sukkarieh,et al.  A Feature Learning Based Approach for Automated Fruit Yield Estimation , 2013, FSR.

[10]  Qi Wang,et al.  Automated Crop Yield Estimation for Apple Orchards , 2012, ISER.

[11]  David W. Aha,et al.  Lazy Learning , 1997, Springer Netherlands.

[12]  Victor S. Lempitsky,et al.  N4-Fields: Neural Network Nearest Neighbor Fields for Image Transforms , 2014, ArXiv.

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Dennis Jarvis,et al.  Estimation of mango crop yield using image analysis - Segmentation method , 2013 .

[15]  Salah Sukkarieh,et al.  A Pipeline for Trunk Detection in Trellis Structured Apple Orchards , 2015, J. Field Robotics.

[16]  Ronan Collobert,et al.  Recurrent Convolutional Neural Networks for Scene Labeling , 2014, ICML.

[17]  Yael Edan,et al.  Computer vision for fruit harvesting robots - state of the art and challenges ahead , 2012, Int. J. Comput. Vis. Robotics.

[18]  K. Madhava Krishna,et al.  Plantation monitoring and yield estimation using autonomous quadcopter for precision agriculture , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Seishi Ninomiya,et al.  On Plant Detection of Intact Tomato Fruits Using Image Analysis and Machine Learning Methods , 2014, Sensors.

[20]  Stephen Nuske,et al.  Texture-based fruit detection via images using the smooth patterns on the fruit , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Fabio Tozeto Ramos,et al.  Automatic detection of Ceratocystis wilt in Eucalyptus crops from aerial images , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[22]  Ronan Collobert,et al.  Recurrent Convolutional Neural Networks for Scene Parsing , 2013, ArXiv.

[23]  Christian Germain,et al.  A new approach on Early Estimation of Vineyard Yield: Site specific counting of berries by using a Smartphone , 2011 .

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