Object-Based Image Analysis Applied to Low Altitude Aerial Imagery for Potato Plant Trait Retrieval and Pathogen Detection

There is a growing demand in both food quality and quantity, but as of now, one-third of all food produced for human consumption is lost due to pests and other pathogens accounting for roughly 40% of pre-harvest loss in potatoes. Pathogens in potato plants, like the Erwinia bacteria and the PVYNTN virus for example, exhibit symptoms of varying severity that are not easily captured by pixel-based classes (as these ignore shape, texture, and context in general). The aim of this research is to develop an object-based image analysis (OBIA) method for trait retrieval of individual potato plants that maximizes information output from Unmanned Aerial Vehicle (UAV) RGB very high resolution (VHR) imagery and its derivatives, to be used for disease detection of the Solanum tuberosum. The approach proposed can be split in two steps: (1) object-based mapping of potato plants using an optimized implementation of large scale mean-shift segmentation (LSMSS), and (2) classification of disease using a random forest (RF) model for a set of morphological traits computed from their associative objects. The approach was proven viable as the associative RF model detected presence of Erwinia and PVY pathogens with a maximum F1 score of 0.75 and an average Matthews Correlation Coefficient (MCC) score of 0.47. It also shows that low-altitude imagery acquired with a commercial UAV is a viable off-the-shelf tool for precision farming, and potato pathogen detection.

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

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

[3]  Robert C. Weih,et al.  OBJECT-BASED CLASSIFICATION VS . PIXEL-BASED CLASSIFICATION : COMPARITIVE IMPORTANCE OF MULTI-RESOLUTION IMAGERY , 2010 .

[4]  Gerrit Polder,et al.  Potato Virus Y Detection in Seed Potatoes Using Deep Learning on Hyperspectral Images , 2019, Front. Plant Sci..

[5]  Geoffrey J. Hay,et al.  An object-specific image-texture analysis of H-resolution forest imagery☆ , 1996 .

[6]  Lei Tian,et al.  Environmentally adaptive segmentation algorithm for outdoor image segmentation , 1998 .

[7]  A. Hamilton,et al.  Identification of the onset of disease within a potato crop using a UAV equipped with un-modified and modified commercial off-the-shelf digital cameras , 2017 .

[8]  C. Hollier,et al.  Crop losses due to diseases and their implications for global food production losses and food security , 2012, Food Security.

[9]  Danny Pascale,et al.  A Review of RGB Color Spaces , 2003 .

[10]  Kristian Kersting,et al.  Quantitative and qualitative phenotyping of disease resistance of crops by hyperspectral sensors: seamless interlocking of phytopathology, sensors, and machine learning is needed! , 2019, Current opinion in plant biology.

[11]  Juha Suomalainen,et al.  A Lightweight Hyperspectral Mapping System and Photogrammetric Processing Chain for Unmanned Aerial Vehicles , 2014, Remote. Sens..

[12]  H. Turral,et al.  The state of the world's land and water resources for food and agriculture : managing systems at risk , 2011 .

[13]  Dirk Tiede,et al.  Geobia Achievements and Spatial Opportunities in the Era of Big Earth Observation Data , 2019, ISPRS Int. J. Geo Inf..

[14]  Dong-Chen He,et al.  Automatic fuzzy object-based analysis of VHSR images for urban objects extraction , 2013 .

[15]  Advances in Very-High-Resolution Remote Sensing , .

[16]  Geoffrey J. Hay,et al.  Image objects and geographic objects , 2008 .

[17]  M. Hirafuji,et al.  Field phenotyping system for the assessment of potato late blight resistance using RGB imagery from an unmanned aerial vehicle , 2016 .

[18]  Adel Hafiane,et al.  Deep leaning approach with colorimetric spaces and vegetation indices for vine diseases detection in UAV images , 2018, Comput. Electron. Agric..

[19]  Lin Liu,et al.  Object-Based Mangrove Species Classification Using Unmanned Aerial Vehicle Hyperspectral Images and Digital Surface Models , 2018, Remote. Sens..

[20]  R. Singh,et al.  Discussion paper: The naming of Potato virus Y strains infecting potato , 2007, Archives of Virology.

[21]  Chengjun Liu,et al.  Comparative assessment of content-based face image retrieval in different color spaces , 2005, Int. J. Pattern Recognit. Artif. Intell..

[22]  Reza Ehsani,et al.  Review: A review of advanced techniques for detecting plant diseases , 2010 .

[23]  Ian K Toth,et al.  Soft rot erwiniae: from genes to genomes. , 2003, Molecular plant pathology.

[24]  Alan H. Strahler,et al.  On the nature of models in remote sensing , 1986 .

[25]  W. Maes,et al.  Perspectives for Remote Sensing with Unmanned Aerial Vehicles in Precision Agriculture. , 2019, Trends in plant science.

[26]  Sabri Boughorbel,et al.  Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric , 2017, PloS one.

[27]  Daniela M. Witten,et al.  An Introduction to Statistical Learning: with Applications in R , 2013 .

[28]  Wei Su,et al.  Textural and local spatial statistics for the object‐oriented classification of urban areas using high resolution imagery , 2008 .

[29]  Madodomzi Mafanya,et al.  Evaluating pixel and object based image classification techniques for mapping plant invasions from UAV derived aerial imagery: Harrisia pomanensis as a case study , 2017 .

[30]  Julien Michel,et al.  Stable Mean-Shift Algorithm and Its Application to the Segmentation of Arbitrarily Large Remote Sensing Images , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[31]  Jayme Garcia Arnal Barbedo,et al.  Digital image processing techniques for detecting, quantifying and classifying plant diseases , 2013, SpringerPlus.

[32]  Richard J. Prokop,et al.  A survey of moment-based techniques for unoccluded object representation and recognition , 1992, CVGIP Graph. Model. Image Process..

[33]  J. M. Molina-Martínez,et al.  Study and comparison of color models for automatic image analysis in irrigation management applications , 2015 .

[34]  David W. Scott,et al.  Scott's rule , 2010 .

[35]  H. Kile,et al.  Bandwidth Selection in Kernel Density Estimation , 2010 .

[36]  W. Mackaness,et al.  Lecture Notes in Geoinformation and Cartography , 2006 .

[37]  Jianhua Gong,et al.  UAV Remote Sensing for Urban Vegetation Mapping Using Random Forest and Texture Analysis , 2015, Remote. Sens..

[38]  M. Baatz,et al.  Progressing from object-based to object-oriented image analysis , 2008 .

[39]  Sofia Bajocco,et al.  A bibliometric analysis on the use of unmanned aerial vehicles in agricultural and forestry studies , 2019, International Journal of Remote Sensing.

[40]  Thomas Blaschke,et al.  Geographic Object-Based Image Analysis – Towards a new paradigm , 2014, ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing.

[41]  Jorge Torres-Sánchez,et al.  An automatic object-based method for optimal thresholding in UAV images: Application for vegetation detection in herbaceous crops , 2015, Comput. Electron. Agric..

[42]  Stefan Lang,et al.  Object-based image analysis for remote sensing applications: modeling reality – dealing with complexity , 2008 .