Mobile low-cost 3D camera maize crop height measurements under field conditions

To tackle global challenges such as food supply and renewable energy provision, the improvement of efficiency and productivity in agriculture is of high importance. Site-specific information about crop height plays an important role in reaching these goals. Crop height can be derived with a variety of approaches including the analysis of three-dimensional (3D) geodata. Crop height values derived from 3D geodata of maize (1.88 and 2.35 m average height) captured with a low-cost 3D camera were examined. Data were collected with a unique measurement setup including the mobile mounting of the 3D camera, and data acquisition under field conditions including wind and sunlight. Furthermore, the data were located in a global co-ordinate system with a straightforward approach, which can strongly reduce computational efforts and which can subsequently support near real-time data processing in the field. Based upon a comparison between crop height values derived from 3D geodata captured with the low-cost approach, and high-end terrestrial laser scanning reference data, minimum RMS and standard deviation values of 0.13 m (6.91% of average crop height), and maximum R2 values of 0.79 were achieved. It can be concluded that the crop height measurements derived from data captured with the introduced setup can provide valuable input for tasks such as biomass estimation. Overall, the setup is considered to be a valuable extension for agricultural machines which will provide complementary crop height measurements for various agricultural applications.

[1]  U. Meier,et al.  Growth stages of mono- and dicotyledonous plants , 1997 .

[2]  Gottfried Mandlburger,et al.  Beyond 3-D: The New Spectrum of Lidar Applications for Earth and Ecological Sciences , 2016 .

[3]  Y. Miao,et al.  Transferability of Models for Estimating Paddy Rice Biomass from Spatial Plant Height Data , 2015 .

[4]  Pablo Prieto,et al.  LiDAR and thermal images fusion for ground-based 3D characterisation of fruit trees , 2016 .

[5]  Chaoyang Wu,et al.  Airborne LiDAR technique for estimating biomass components of maize: A case study in Zhangye City, Northwest China , 2015 .

[6]  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..

[7]  G. Grenzdörffer.  Crop height determination with UAS point clouds , 2014 .

[8]  P. Reich,et al.  New handbook for standardised measurement of plant functional traits worldwide , 2013 .

[9]  Noboru Noguchi,et al.  Development and application of a wheel-type robot tractor , 2016 .

[10]  P. Lancashire,et al.  A uniform decimal code for growth stages of crops and weeds , 1991 .

[11]  Norbert Pfeifer,et al.  OPALS - A framework for Airborne Laser Scanning data analysis , 2014, Comput. Environ. Urban Syst..

[12]  Andreas Kolb,et al.  Kinect range sensing: Structured-light versus Time-of-Flight Kinect , 2015, Comput. Vis. Image Underst..

[13]  O. E. Krips,et al.  Automated video tracking of thrips behavior to assess host-plant resistance in multiple parallel two-choice setups , 2016, Plant Methods.

[14]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[15]  D. Ehlert,et al.  Suitability of a laser rangefinder to characterize winter wheat , 2010, Precision Agriculture.

[16]  Christian Riess,et al.  A Comparative Error Analysis of Current Time-of-Flight Sensors , 2016, IEEE Transactions on Computational Imaging.

[17]  Qin Zhang,et al.  Precision Agriculture Technology for Crop Farming , 2015 .

[18]  J. Eitel,et al.  LiDAR based biomass and crop nitrogen estimates for rapid, non-destructive assessment of wheat nitrogen status , 2014 .

[19]  Görres Grenzdörffer,et al.  Imagine All the Plants: Evaluation of a Light-Field Camera for On-Site Crop Growth Monitoring , 2016, Remote. Sens..

[20]  A. Walter,et al.  Terrestrial 3D laser scanning to track the increase in canopy height of both monocot and dicot crop species under field conditions , 2016, Plant Methods.

[21]  M. Dalponte,et al.  Hail defoliation assessment in corn (Zea mays L.) using airborne LiDAR , 2016 .

[22]  Dani Martínez,et al.  A Proposal for Automatic Fruit Harvesting by Combining a Low Cost Stereovision Camera and a Robotic Arm , 2014, Sensors.

[23]  Wouter Saeys,et al.  Estimation of the crop density of small grains using LiDAR sensors. , 2009 .

[24]  Pablo González de Santos,et al.  Reducing fuel consumption in weed and pest control using robotic tractors , 2015, Comput. Electron. Agric..

[25]  Pedro Arias,et al.  Metrological comparison between Kinect I and Kinect II sensors , 2015 .

[26]  Yu Jiang,et al.  High throughput phenotyping of cotton plant height using depth images under field conditions , 2016, Comput. Electron. Agric..

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

[28]  F. Marinello,et al.  Application of the Kinect sensor for dynamic soil surface characterization , 2015, Precision Agriculture.

[29]  Bernhard Höfle,et al.  Simulating an Autonomously Operating Low-Cost Static Terrestrial LiDAR for Multitemporal Maize Crop Height Measurements , 2016, Remote. Sens..

[30]  Irena Hajnsek,et al.  Retrieval of agricultural crop height from space: A comparison of SAR techniques , 2016 .

[31]  K. D. Mankoff,et al.  The Kinect: a low‐cost, high‐resolution, short‐range 3D camera , 2013 .

[32]  Dirk Hoffmeister,et al.  A Comparison of UAV- and TLS-derived Plant Height for Crop Monitoring: Using Polygon Grids for the Analysis of Crop Surface Models (CSMs) , 2016 .

[33]  Simon Bennertz,et al.  Combining UAV-based plant height from crop surface models, visible, and near infrared vegetation indices for biomass monitoring in barley , 2015, Int. J. Appl. Earth Obs. Geoinformation.

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

[35]  Honggang Bu,et al.  Use of corn height measured with an acoustic sensor improves yield estimation with ground based active optical sensors , 2016, Comput. Electron. Agric..

[36]  Yuhong Yang,et al.  Simplification of leaf surfaces from scanned data: Effects of two algorithms on leaf morphology , 2016, Comput. Electron. Agric..

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

[38]  Paul A. Beardsley,et al.  Underwater 3D capture using a low-cost commercial depth camera , 2016, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

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

[40]  B. Höfle,et al.  Direct derivation of maize plant and crop height from low-cost time-of-flight camera measurements , 2016, Plant Methods.

[41]  E. G. Smith,et al.  Site-Specific Herbicide Decision Model to Maximize Profit in Winter Wheat , 2003, Precision Agriculture.