Investigation on combinations of colour indices and threshold techniques in vegetation segmentation for volunteer potato control in sugar beet

Abstract Robust vegetation segmentation is required for a vision-based weed control robot in an agricultural field operation. The output of vegetation segmentation is a fundamental element in the subsequent process of weed/crop discrimination as well as weed control actuation. Given the abundance of colour indices and thresholding techniques, it is still far from clear how to choose a proper threshold technique in combination with a colour index for vegetation segmentation under agricultural field conditions. In this research, the performance of 40 combinations of eight colour indices and five thresholding techniques found in the literature was assessed to identify which combination works the best given varying field conditions in terms of illumination intensity, shadow presence and plant size. It was also assessed whether it was better to use one specific combination at all times or whether the combination should be adapted to the field conditions at hand. A clear difference in performance, represented in terms of MA (Modified Accuracy) which indicates the harmonic mean of relative vegetation area error and balanced accuracy, was observed among various combinations under the given conditions. On the image dataset that was used in this study, CIVE+Kapur (Colour Index of Vegetation Extraction+Max Entropy threshold) showed the best performance while VEG+Kapur (Vegetative Index+Max Entropy threshold) showed the worst. Adapting the combination to the given conditions yielded a slightly higher performance than when using a single combination for all (in this case CIVE+Kapur). Consistent results were obtained when validated on a different independent image dataset. Although a slightly higher performance was achieved when adapting the combination to the field conditions, this slight improvement seems not to outweigh the potential investment in sensor technology and software that are needed in practice to accurately determine the different conditions in the field. Therefore, the expected advantage of adapting the combination to the field condition is not large.

[1]  Eldert J. van Henten,et al.  Improved vegetation segmentation with ground shadow removal using an HDR camera , 2018, Precision Agriculture.

[2]  N. D. Tillett,et al.  Automated Crop and Weed Monitoring in Widely Spaced Cereals , 2006, Precision Agriculture.

[3]  Alberto Tellaeche,et al.  Analysis of natural images processing for the extraction of agricultural elements , 2010, Image Vis. Comput..

[4]  Gonzalo Pajares,et al.  A Multilevel Thresholding algorithm using electromagnetism optimization , 2014, Neurocomputing.

[5]  Gonzalo Pajares,et al.  Discrete wavelets transform for improving greenness image segmentation in agricultural images , 2015, Comput. Electron. Agric..

[6]  Hong Ye,et al.  Image Bi-Level Thresholding Based on Gray Level-Local Variance Histogram , 2017, Entropy.

[7]  David Jones,et al.  Intensified fuzzy clusters for classifying plant, soil, and residue regions of interest from color images , 2004 .

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

[9]  T. W. Ridler,et al.  Picture thresholding using an iterative selection method. , 1978 .

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

[11]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[12]  Wei Guo,et al.  Illumination invariant segmentation of vegetation for time series wheat images based on decision tree model , 2013 .

[13]  Gonzalo Pajares,et al.  Support Vector Machines for crop/weeds identification in maize fields , 2012, Expert Syst. Appl..

[14]  Lss Reddy,et al.  INVESTIGATIONS ON ENTROPY BASED THRESHOLD METHODS , 2013 .

[15]  S. Filin,et al.  Plant growth parameter estimation from sparse 3D reconstruction based on highly-textured feature points , 2013, Precision Agriculture.

[16]  J. M. González-Esquiva,et al.  Optimal color space selection method for plant/soil segmentation in agriculture , 2016, Comput. Electron. Agric..

[17]  Zhenghong Yu,et al.  Crop feature extraction from images with probabilistic superpixel Markov random field , 2015, Comput. Electron. Agric..

[18]  Poonamdeep Kaur,et al.  Performance Evaluation of Various Thresholding Methods using Canny Edge Detector , 2013 .

[19]  Edward Jones,et al.  A survey of image processing techniques for plant extraction and segmentation in the field , 2016, Comput. Electron. Agric..

[20]  Bülent Sankur,et al.  Survey over image thresholding techniques and quantitative performance evaluation , 2004, J. Electronic Imaging.

[21]  Gonzalo Pajares,et al.  Automatic expert system based on images for accuracy crop row detection in maize fields , 2013, Expert Syst. Appl..

[22]  G. Meyer,et al.  Color indices for weed identification under various soil, residue, and lighting conditions , 1994 .

[23]  Brian L. Steward,et al.  SHAPE AND SIZE ANALYSIS OF CORN PLANT CANOPIES FOR PLANT POPULATION AND SPACING SENSING , 2005 .

[24]  Andrew K. C. Wong,et al.  A new method for gray-level picture thresholding using the entropy of the histogram , 1985, Comput. Vis. Graph. Image Process..

[25]  Alberto Tellaeche,et al.  A vision-based method for weeds identification through the Bayesian decision theory , 2008, Pattern Recognit..

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

[27]  Josef Kittler,et al.  Minimum error thresholding , 1986, Pattern Recognit..

[28]  Ashish Kumar Bhandari,et al.  Modified artificial bee colony based computationally efficient multilevel thresholding for satellite image segmentation using Kapur's, Otsu and Tsallis functions , 2015, Expert Syst. Appl..

[29]  Henry Leung,et al.  Chaotic spread spectrum watermarking for remote sensing images , 2004, J. Electronic Imaging.

[30]  Gonzalo Pajares,et al.  Automatic expert system for weeds/crops identification in images from maize fields , 2013, Expert Syst. Appl..

[31]  J. Marchant,et al.  Shadow-invariant classification for scenes illuminated by daylight. , 2000, Journal of the Optical Society of America. A, Optics, image science, and vision.

[32]  A. T. Nieuwenhuizen,et al.  Performance evaluation of an automated detection and control system for volunteer potatoes in sugar beet fields , 2010 .

[33]  Paul L. Rosin,et al.  Evaluation of global image thresholding for change detection , 2003, Pattern Recognit. Lett..

[34]  Joni-Kristian Kämäräinen,et al.  Thresholding-based detection of fine and sparse details , 2005, MVA.