High throughput phenotyping of cotton plant height using depth images under field conditions

Abstract Plant height is an important phenotypic trait that can be used not only as an indicator of overall plant growth but also a parameter to calculate advanced traits such as biomass and yield. Currently, cotton plant height is primarily measured manually, which is laborious and has become a bottleneck for cotton research and breeding programs. The goal of this research was to develop and evaluate a high throughput phenotyping (HTP) system using depth images for measuring cotton plant height under field conditions. For this purpose, a Kinect-v2 camera was evaluated in a static configuration to obtain a performance baseline and in a dynamic configuration to measure plant height in the field. In the static configuration, the camera was mounted on a partially covered wooden frame and oriented towards nadir to acquire depth images of potted cotton plants. Regions of interest of plants were manually selected in the depth images to calculate plant height. In the dynamic configuration, the Kinect-v2 camera was installed inside a partially covered metal-frame that was attached to a high-clearance tractor equipped with real time kinematic GPS. A six-step algorithm was developed to measure the maximum and average heights of individual plots by using the depth images acquired by the system. System performance was evaluated on 108 plots of cotton plants. Results showed that the Kinect-v2 camera could acquire valid depth images of cotton plants under field conditions, when a shaded environment was provided. The plot maximum and average heights calculated by the proposed algorithm were strongly correlated (adjusted R2 = 0.922–0.987) with those measured manually with accuracies of over 92%. The average processing time was 0.01 s to calculate the heights of a plot that typically has 34 depth images, indicating that the proposed algorithm was computationally efficient. Therefore, these results confirmed the ability of the HTP system with depth images to measure cotton plant height under field conditions accurately and rapidly. Furthermore, the imaging-based system has great potential for measuring more complicated geometric traits of plants, which can significantly advance field-based HTP system development in general.

[1]  P. Hietz,et al.  Small plants, large plants: the importance of plant size for the physiological ecology of vascular epiphytes. , 2001, Journal of experimental botany.

[2]  Ulrich Schurr,et al.  Future scenarios for plant phenotyping. , 2013, Annual review of plant biology.

[3]  Lei Zhang,et al.  A LIDAR-based crop height measurement system for Miscanthus giganteus , 2012 .

[4]  Arno Ruckelshausen,et al.  BreedVision — A Multi-Sensor Platform for Non-Destructive Field-Based Phenotyping in Plant Breeding , 2013, Sensors.

[5]  Qamar Uz Zaman,et al.  Performance evaluation of multiple ground based sensors mounted on a commercial wild blueberry harvester to sense plant height, fruit yield and topographic features in real-time , 2013 .

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

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

[8]  Sebastian Riedel,et al.  Automated Analysis of Barley Organs Using 3D Laser Scanning: An Approach for High Throughput Phenotyping , 2014, Sensors.

[9]  I. Xenarios,et al.  Measuring the diurnal pattern of leaf hyponasty and growth in Arabidopsis - a novel phenotyping approach using laser scanning. , 2012, Functional plant biology : FPB.

[10]  D. Tilman,et al.  Global food demand and the sustainable intensification of agriculture , 2011, Proceedings of the National Academy of Sciences.

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

[12]  K. Omasa,et al.  3D lidar imaging for detecting and understanding plant responses and canopy structure. , 2006, Journal of experimental botany.

[13]  Jeffrey W. White,et al.  Field-based phenomics for plant genetics research , 2012 .

[14]  Daniel Moura,et al.  In-field crop row phenotyping from 3D modeling performed using Structure from Motion , 2015, Comput. Electron. Agric..

[15]  Jean-Luc Jannink,et al.  Genomic selection in plant breeding: from theory to practice. , 2010, Briefings in functional genomics.

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

[17]  Sagi Filin,et al.  Estimating plant growth parameters using an energy minimization-based stereovision model , 2013 .

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

[19]  Jeffrey W. White,et al.  Development and evaluation of a field-based high-throughput phenotyping platform. , 2013, Functional plant biology : FPB.

[20]  AndújarDionisio,et al.  Using depth cameras to extract structural parameters to assess the growth state and yield of cauliflower crops , 2016 .

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

[22]  Alexander Putz,et al.  Rapid determination of leaf area and plant height by using light curtain arrays in four species with contrasting shoot architecture , 2014, Plant Methods.

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

[24]  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.

[25]  L. Xiong,et al.  Plant phenomics and high-throughput phenotyping: accelerating rice functional genomics using multidisciplinary technologies. , 2013, Current opinion in plant biology.

[26]  K. H. Kjaer,et al.  3D Laser Triangulation for Plant Phenotyping in Challenging Environments , 2015, Sensors.

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

[28]  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..

[29]  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..

[30]  J. Araus,et al.  Field high-throughput phenotyping: the new crop breeding frontier. , 2014, Trends in plant science.

[31]  Yi Lin,et al.  LiDAR: An important tool for next-generation phenotyping technology of high potential for plant phenomics? , 2015, Comput. Electron. Agric..