Influence of Wind Speed on RGB-D Images in Tree Plantations

Weather conditions can affect sensors’ readings when sampling outdoors. Although sensors are usually set up covering a wide range of conditions, their operational range must be established. In recent years, depth cameras have been shown as a promising tool for plant phenotyping and other related uses. However, the use of these devices is still challenged by prevailing field conditions. Although the influence of lighting conditions on the performance of these cameras has already been established, the effect of wind is still unknown. This study establishes the associated errors when modeling some tree characteristics at different wind speeds. A system using a Kinect v2 sensor and a custom software was tested from null wind speed up to 10 m·s−1. Two tree species with contrasting architecture, poplars and plums, were used as model plants. The results showed different responses depending on tree species and wind speed. Estimations of Leaf Area (LA) and tree volume were generally more consistent at high wind speeds in plum trees. Poplars were particularly affected by wind speeds higher than 5 m·s−1. On the contrary, height measurements were more consistent for poplars than for plum trees. These results show that the use of depth cameras for tree characterization must take into consideration wind conditions in the field. In general, 5 m·s−1 (18 km·h−1) could be established as a conservative limit for good estimations.

[1]  Brian Mirtich,et al.  Fast and Accurate Computation of Polyhedral Mass Properties , 1996, J. Graphics, GPU, & Game Tools.

[2]  Qin Zhang,et al.  A Review of Imaging Techniques for Plant Phenotyping , 2014, Sensors.

[3]  Lennart Nilsen,et al.  Using Ordinary Digital Cameras in Place of Near-Infrared Sensors to Derive Vegetation Indices for Phenology Studies of High Arctic Vegetation , 2016, Remote. Sens..

[4]  Thomas Butkiewicz Low-cost coastal mapping using Kinect v2 time-of-flight cameras , 2014, 2014 Oceans - St. John's.

[5]  José Dorado,et al.  An Approach to the Use of Depth Cameras for Weed Volume Estimation , 2016, Sensors.

[6]  Søren Balling Engelsen,et al.  High-throughput cereal metabolomics: Current analytical technologies, challenges and perspectives , 2014 .

[7]  Christian Messier,et al.  Assessing the Potential of Low-Cost 3D Cameras for the Rapid Measurement of Plant Woody Structure , 2013, Sensors.

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

[9]  Rafael Arnay,et al.  Using Kinect on an Autonomous Vehicle for Outdoors Obstacle Detection , 2016, IEEE Sensors Journal.

[10]  Lutz Plümer,et al.  Low-Cost 3D Systems: Suitable Tools for Plant Phenotyping , 2014, Sensors.

[11]  Praveen Kumar,et al.  Characterizing Vegetation Canopy Structure Using Airborne Remote Sensing Data , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Alexandre Escolà,et al.  Weed discrimination using ultrasonic sensors , 2011 .

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

[14]  A. Escolà,et al.  Ultrasonic and LIDAR Sensors for Electronic Canopy Characterization in Vineyards: Advances to Improve Pesticide Application Methods , 2011, Sensors.

[15]  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..

[16]  Michael Pflanz,et al.  Monitoring Agronomic Parameters of Winter Wheat Crops with Low-Cost UAV Imagery , 2016, Remote. Sens..

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

[18]  José Dorado,et al.  Matching the Best Viewing Angle in Depth Cameras for Biomass Estimation Based on Poplar Seedling Geometry , 2015, Sensors.

[19]  Gonzalo Pajares,et al.  Spatio-temporal analysis for obstacle detection in agricultural videos , 2016, Appl. Soft Comput..

[20]  Yu Jiang,et al.  An imaging-based system for high-throughput phenotyping of cotton plants under field conditions , 2016 .

[21]  Ning Wang,et al.  A Canopy Density Model for Planar Orchard Target Detection Based on Ultrasonic Sensors , 2017, Sensors.

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

[23]  Jidong Huang,et al.  Study on the use of Microsoft Kinect for robotics applications , 2012, Proceedings of the 2012 IEEE/ION Position, Location and Navigation Symposium.

[24]  Changying Li,et al.  Size estimation of sweet onions using consumer-grade RGB-depth sensor , 2014 .

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

[26]  Philippe Lucidarme,et al.  On the use of depth camera for 3D phenotyping of entire plants , 2012 .

[27]  H. Macher,et al.  FIRST EXPERIENCES WITH KINECT V2 SENSOR FOR CLOSE RANGE 3D MODELLING , 2015 .

[28]  George Azzari,et al.  Rapid Characterization of Vegetation Structure with a Microsoft Kinect Sensor , 2013, Sensors.

[29]  David Reiser,et al.  3-D Imaging Systems for Agricultural Applications—A Review , 2016, Sensors.

[30]  V. Rueda-Ayala,et al.  A LiDAR-Based System to Assess Poplar Biomass , 2016, Gesunde Pflanzen.

[31]  S. Chapman,et al.  Dynamic quantification of canopy structure to characterize early plant vigour in wheat genotypes , 2016, Journal of experimental botany.

[32]  Jayme Garcia Arnal Barbedo,et al.  A review on the main challenges in automatic plant disease identification based on visible range images , 2016 .

[33]  Ri-xian Cui,et al.  [Estimation of Winter Wheat Leaf Nitrogen Accumulation using Machine Learning Algorithm and Visible Spectral]. , 2016, Guang pu xue yu guang pu fen xi = Guang pu.

[34]  P. Javier Herrera,et al.  A Novel Approach for Weed Type Classification Based on Shape Descriptors and a Fuzzy Decision-Making Method , 2014, Sensors.

[35]  H. Fang,et al.  Estimation of canopy clumping index from MISR and MODIS sensors using the normalized difference hotspot and darkspot (NDHD) method: The influence of BRDF models and solar zenith angle , 2016 .

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

[37]  Derek D. Lichti,et al.  Performance Assessment and Calibration of the Kinect 2.0 Time-of-Flight Range Camera for Use in Motion Capture Applications , 2015 .

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

[39]  J. H. Zonta,et al.  Hemispherical photography to estimate biophysical variables of cotton , 2016 .

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

[41]  Michael P. Pound,et al.  Approaches to three-dimensional reconstruction of plant shoot topology and geometry. , 2016, Functional plant biology : FPB.