Weed detecting robot in sugarcane fields using fuzzy real time classifier

An image classification system is designed by extracting internal leaf textures.A novel fuzzy real-time classifier is developed to automatically classify weed and crop in sugarcane fields.Morphological operators are used to capture the morphological pattern of the crop and weed.A robot carrying Raspberry PI board, camera, motors and power system has been fabricated and tested.The hardware identifies the sugarcane crop from 9 different weed species with 92.9% accuracy. The objective of this research work is to propose a weed detecting robotic model for sugarcane fields that uses a fuzzy real time classifier on leaf textures. The differentiation between weed and crop and weed removal are the two challenging tasks for the farmers especially in the Indian sugarcane cultivation scenario. The automatic weed detection and removal becomes a vital task for improving the cost effectiveness and efficiency of the agricultural processes. The detection of weeds by the robotic model employs a Raspberry Pi based control system placed in a moving vehicle. An automated image classification system has been designed which extracts leaf textures and employs a fuzzy real-time classification technique. Morphological operators are applied to extract circular leaf patterns in different scales from the leaf images. An optimal set of features have been identified for the characterization of crops and weeds in sugarcane fields. A weed detecting robotic prototype is designed and developed using a Raspberry Pi micro controller and suitable input output subsystems such as cameras, small light sources and motors with power systems. The prototypes control incorporates the weed detection mechanism using a Raspbian operating system support and python programming. The designed robotic prototype correctly identifies the sugarcane crop among nine different weed species. The system detects weeds with 92.9% accuracy over a processing time of 0.02s.

[1]  D. K. Giles,et al.  Precision weed control system for cotton , 2002 .

[2]  Gonzalo Pajares,et al.  A new Expert System for greenness identification in agricultural images , 2013, Expert Syst. Appl..

[3]  Rajender Kumar,et al.  Weed management in sugarcane ratoon crop , 2014 .

[4]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[5]  G. Meyer,et al.  Verification of color vegetation indices for automated crop imaging applications , 2008 .

[6]  H. Bakker,et al.  Sugar Cane Cultivation and Management , 1999, Springer US.

[7]  K. Laws.  Textured Image Segmentation , 1980 .

[8]  Chris McCarthy,et al.  Preliminary evaluation of shape and colour image sensing for automated weed identification in sugarcane , 2012 .

[9]  R. Y. van der Weide,et al.  Innovation in mechanical weed control in crop rows , 2008 .

[10]  Xavier P. Burgos-Artizzu,et al.  utomatic segmentation of relevant textures in agricultural images , 2010 .

[11]  David C. Slaughter,et al.  Automated weed control in organic row crops using hyperspectral species identification and thermal micro-dosing , 2012 .

[12]  S. Christensen,et al.  Colour and shape analysis techniques for weed detection in cereal fields , 2000 .

[13]  Hamid Soltanian-Zadeh,et al.  Rotation-invariant multiresolution texture analysis using Radon and wavelet transforms , 2005, IEEE Transactions on Image Processing.

[14]  E. Franz,et al.  Shape description of completely-visible and partially-occluded leaves for identifying plants in digital images. , 2016 .

[15]  Xavier Maldague,et al.  Bayesian classification and unsupervised learning for isolating weeds in row crops , 2014, Pattern Analysis and Applications.

[16]  George E. Meyer,et al.  Machine vision detection parameters for plant species identification , 1999, Other Conferences.

[17]  Lei Tian,et al.  CLASSIFICATION OF BROADLEAF AND GRASS WEEDS USING GABOR WAVELETS AND AN ARTIFICIAL NEURAL NETWORK , 2003 .

[18]  Sohail Asghar,et al.  Segmentation of Crops and Weeds Using Supervised Learning Technique , 2015 .

[19]  Greenbot : A Solar Autonomous Robot to Uproot Weeds in a Grape Field , 2016 .

[20]  Zicheng Guo,et al.  Parallel thinning with two-subiteration algorithms , 1989, Commun. ACM.

[21]  K. G. Kshirsagar.  Impact of organic sugercane farming on economics and water use efficiency in Maharashtra , 2008 .

[22]  Jin-Young Jeong,et al.  AE—Automation and Emerging Technologies: Weed–plant Discrimination by Machine Vision and Artificial Neural Network , 2002 .

[23]  Wu Lanlan,et al.  Weed/corn seedling recognition by support vector machine using texture features , 2009 .

[24]  George E. Meyer,et al.  Shape features for identifying young weeds using image analysis , 1994 .

[25]  T. Bakker,et al.  An autonomous robot for weed control: design, navigation and control. , 2009 .