Evaluation of Vineyard Cropping Systems Using On-Board RGB-Depth Perception

A non-destructive measuring technique was applied to test major vine geometric traits on measurements collected by a contactless sensor. Three-dimensional optical sensors have evolved over the past decade, and these advancements may be useful in improving phenomics technologies for other crops, such as woody perennials. Red, green and blue-depth (RGB-D) cameras, namely Microsoft Kinect, have a significant influence on recent computer vision and robotics research. In this experiment an adaptable mobile platform was used for the acquisition of depth images for the non-destructive assessment of branch volume (pruning weight) and related to grape yield in vineyard crops. Vineyard yield prediction provides useful insights about the anticipated yield to the winegrower, guiding strategic decisions to accomplish optimal quantity and efficiency, and supporting the winegrower with decision-making. A Kinect v2 system on-board to an on-ground electric vehicle was capable of producing precise 3D point clouds of vine rows under six different management cropping systems. The generated models demonstrated strong consistency between 3D images and vine structures from the actual physical parameters when average values were calculated. Correlations of Kinect branch volume with pruning weight (dry biomass) resulted in high coefficients of determination (R2 = 0.80). In the study of vineyard yield correlations, the measured volume was found to have a good power law relationship (R2 = 0.87). However due to low capability of most depth cameras to properly build 3-D shapes of small details the results for each treatment when calculated separately were not consistent. Nonetheless, Kinect v2 has a tremendous potential as a 3D sensor in agricultural applications for proximal sensing operations, benefiting from its high frame rate, low price in comparison with other depth cameras, and high robustness.

[1]  Peter Dalgaard,et al.  R Development Core Team (2010): R: A language and environment for statistical computing , 2010 .

[2]  Angela Ribeiro,et al.  On-Ground Vineyard Reconstruction Using a LiDAR-Based Automated System , 2020, Sensors.

[3]  Roland Gerhards,et al.  Potential use of ground-based sensor technologies for weed detection. , 2014, Pest management science.

[4]  Theofanis Gemtos,et al.  Using laser scanner to map pruning wood in vineyards , 2013 .

[5]  J. R. Rosell-Polo,et al.  Advances in Structured Light Sensors Applications in Precision Agriculture and Livestock Farming , 2015 .

[6]  José M. Bengochea-Guevara,et al.  Comparing UAV-Based Technologies and RGB-D Reconstruction Methods for Plant Height and Biomass Monitoring on Grass Ley , 2019, Sensors.

[7]  Jinhai Cai,et al.  High-throughput 3D modelling of plants for phenotypic analysis , 2012, IVCNZ '12.

[8]  Joan Ramón Rosell Polo,et al.  A tractor-mounted scanning LIDAR for the non-destructive measurement of vegetative volume and surface area of tree-row plantations: A comparison with conventional destructive measurements , 2009 .

[9]  Scott D. Roth,et al.  Ray casting for modeling solids , 1982, Comput. Graph. Image Process..

[10]  Martin Weis,et al.  An Ultrasonic System for Weed Detection in Cereal Crops , 2012, Sensors.

[11]  Jose A. Jiménez-Berni,et al.  High Throughput Determination of Plant Height, Ground Cover, and Above-Ground Biomass in Wheat with LiDAR , 2018, Front. Plant Sci..

[12]  Peter Christiansen,et al.  FieldSAFE: Dataset for Obstacle Detection in Agriculture , 2017, Sensors.

[13]  Dan Wu,et al.  Estimating Changes in Leaf Area, Leaf Area Density, and Vertical Leaf Area Profile for Mango, Avocado, and Macadamia Tree Crowns Using Terrestrial Laser Scanning , 2018, Remote. Sens..

[14]  Jordi Llorens,et al.  Kinect v2 Sensor-Based Mobile Terrestrial Laser Scanner for Agricultural Outdoor Applications , 2017, IEEE/ASME Transactions on Mechatronics.

[15]  Angela Ribeiro,et al.  A Low-Cost Approach to Automatically Obtain Accurate 3D Models of Woody Crops , 2017, Sensors.

[16]  Jordi Llorens,et al.  Georeferenced LiDAR 3D Vine Plantation Map Generation , 2011, Sensors.

[17]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[18]  L. G. Santesteban,et al.  Precision viticulture and advanced analytics. A short review. , 2019, Food chemistry.

[19]  Marc Levoy,et al.  A volumetric method for building complex models from range images , 1996, SIGGRAPH.

[20]  José Dorado,et al.  Influence of Wind Speed on RGB-D Images in Tree Plantations , 2017, Sensors.

[21]  Qi Wu,et al.  A Post-Rectification Approach of Depth Images of Kinect v2 for 3D Reconstruction of Indoor Scenes , 2017, ISPRS Int. J. Geo Inf..

[22]  Samuel Williams,et al.  A Robot System for Pruning Grape Vines , 2017, J. Field Robotics.

[23]  Gérard G. Medioni,et al.  Object modelling by registration of multiple range images , 1992, Image Vis. Comput..

[24]  Guy Shani,et al.  Comparing RGB-D Sensors for Close Range Outdoor Agricultural Phenotyping , 2018, Sensors.

[25]  Cecilia Sik-Lányi,et al.  Suitability of the Kinect Sensor and Leap Motion Controller—A Literature Review , 2019, Sensors.

[26]  Angela Ribeiro,et al.  Aerial imagery or on-ground detection? An economic analysis for vineyard crops , 2019, Comput. Electron. Agric..

[27]  Henry Medeiros,et al.  A robotic vision system to measure tree traits , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[28]  Roland Siegwart,et al.  Kinect v2 for mobile robot navigation: Evaluation and modeling , 2015, 2015 International Conference on Advanced Robotics (ICAR).

[29]  J. Léon,et al.  High-precision laser scanning system for capturing 3D plant architecture and analysing growth of cereal plants , 2014 .

[30]  José Dorado,et al.  Using depth cameras to extract structural parameters to assess the growth state and yield of cauliflower crops , 2016, Comput. Electron. Agric..

[31]  Wenbing Zhao,et al.  A Survey of Applications and Human Motion Recognition with Microsoft Kinect , 2015, Int. J. Pattern Recognit. Artif. Intell..

[32]  Didier Stricker,et al.  Comparison of Kinect V1 and V2 Depth Images in Terms of Accuracy and Precision , 2016, ACCV Workshops.

[33]  Herbert Edelsbrunner,et al.  Three-dimensional alpha shapes , 1992, VVS.

[34]  Matthias Nießner,et al.  Real-time 3D reconstruction at scale using voxel hashing , 2013, ACM Trans. Graph..

[35]  Xu Wang,et al.  Field-based high-throughput phenotyping of plant height in sorghum using different sensing technologies , 2018, Plant Methods.

[36]  Alexandre Escolà,et al.  A Method to Obtain Orange Crop Geometry Information Using a Mobile Terrestrial Laser Scanner and 3D Modeling , 2017, Remote. Sens..

[37]  Livio Pinto,et al.  Calibration of Kinect for Xbox One and Comparison between the Two Generations of Microsoft Sensors , 2015, Sensors.

[38]  Joaquim J. Sousa,et al.  Vineyard properties extraction combining UAS-based RGB imagery with elevation data , 2018 .

[39]  Elise Lachat,et al.  Assessment and Calibration of a RGB-D Camera (Kinect v2 Sensor) Towards a Potential Use for Close-Range 3D Modeling , 2015, Remote. Sens..