Field-Based High-Throughput Phenotyping for Maize Plant Using 3D LiDAR Point Cloud Generated With a “Phenomobile”

Abstract

With the rapid rising of global population, the demand for improving breeding techniques to greatly increase the worldwide crop production has become more and more urgent. Most researchers believe that the key to new breeding techniques lies in genetic improvement of crops, which leads to a large quantity of phenotyping spots. Unfortunately, current phenotyping solutions are not powerful enough to handle so many spots with satisfying speed and accuracy. As a result, high-throughput phenotyping is drawing more and more attention. In this paper, we propose a new field-based sensing solution to high-throughput phenotyping. We mount a LiDAR (Velodyne HDL64-S3) on a mobile robot, making the robot a “phenomobile.” We develop software for data collection and analysis under Robotic Operating System using open source components and algorithm libraries. Different from conducting phenotyping observations with an in-row and one-by-one manner, our new solution allows the robot to move around the parcel to collect data. Thus, the 3D and 360° view laser scanner can collect phenotyping data for a large plant group at the same time, instead of one by one. Furthermore, no touching interference from the robot would be imposed onto the crops. We conduct experiments for maize plant on two parcels. We implement point cloud merging with landmarks and Iterative Closest Points to cut down the time consumption. We then recognize and compute the morphological phenotyping parameters (row spacing and plant height) of maize plant using depth-band histograms and horizontal point density. We analyze the cloud registration and merging performances, the row spacing detection accuracy, and the single plant height computation accuracy. Experimental results verify the feasibility of the proposed solution.

Gene banks for wild and cultivated sunflower genetic resources

“…When equipped with digital cameras, UAVs can be used to estimate canopy surface and biomass (Liebisch et al, 2015) with multispectral cameras or hyperspectral sensors to characterize physiological processes such as chlorophyll fluorescence or nitrogen levels (Camino et al, 2018) or plant water status using thermal imaging (Gómez-Candón et al, 2016;Gonzalez-Dugo et al, 2015). For short crops, such as wheat, ground based phenotyping robot often termed "Phenomobile" have also been developed (Madec et al, 2017;Qiu et al, 2019). In addition to cameras similar to those on UAVs, they can carry heavy and energy-demanding sensors such as LiDAR and additional lights to be independent of natural sunlight varying in quality and quantity.…”

In‐Field Whole‐Plant Maize Architecture Characterized by Subcanopy Rovers and Latent Space Phenotyping

“…Though automated subcanopy phenotyping comes with some challenges, the potential for benefit to plant biology and plant breeding communities is immense and real. The capabilities of subcanopy rovers have been recognized by multiple groups (Mueller‐Sim et al, 2017; Kayacan et al, 2018; Stager et al, 2019), and the promise of lidar for in‐field characterization of plant architecture has also been recognized (Qiu et al, 2019; Su et al, 2019). By combining novel phenotyping and data analysis techniques, we have demonstrated that rover‐based phenotyping by lidar can produce LSPs that are heritable and contain information about plant architecture and plot‐level biomass distribution.…”

Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz)

“…To be constructive to breeding programs, phenotyping methods must be robust, automated, sensitive, and amenable to plot sizes. The ability to get more rapid growth responses of genetically different plants in the eld and transmit these responses to individual genes, novel technologies such as proximal sensing, robotics, integrated computational algorithms and robust automated aerial image analytical frameworks are urgently needed [7].…”