Comparing UAV-Based Technologies and RGB-D Reconstruction Methods for Plant Height and Biomass Monitoring on Grass Ley

Abstract

Pastures are botanically diverse and difficult to characterize. Digital modeling of pasture biomass and quality by non-destructive methods can provide highly valuable support for decision-making. This study aimed to evaluate aerial and on-ground methods to characterize grass ley fields, estimating plant height, biomass and volume, using digital grass models. Two fields were sampled, one timothy-dominant and the other ryegrass-dominant. Both sensing systems allowed estimation of biomass, volume and plant height, which were compared with ground truth, also taking into consideration basic economical aspects. To obtain ground-truth data for validation, 10 plots of 1 m2 were manually and destructively sampled on each field. The studied systems differed in data resolution, thus in estimation capability. There was a reasonably good agreement between the UAV-based, the RGB-D-based estimates and the manual height measurements on both fields. RGB-D-based estimation correlated well with ground truth of plant height ( R 2 > 0.80 ) for both fields, and with dry biomass ( R 2 = 0.88 ), only for the timothy field. RGB-D-based estimation of plant volume for ryegrass showed a high agreement ( R 2 = 0.87 ). The UAV-based system showed a weaker estimation capability for plant height and dry biomass ( R 2 < 0.6 ). UAV-systems are more affordable, easier to operate and can cover a larger surface. On-ground techniques with RGB-D cameras can produce highly detailed models, but with more variable results than UAV-based models. On-ground RGB-D data can be effectively analysed with open source software, which is a cost reduction advantage, compared with aerial image analysis. Since the resolution for agricultural operations does not need fine identification the end-details of the grass plants, the use of aerial platforms could result a better option in grasslands.

Development and Validation of a Model to Combine NDVI and Plant Height for High-Throughput Phenotyping of Herbage Yield in a Perennial Ryegrass Breeding Program

“…In the current study, the R 2 of plant height vs. log-transformed DHY was more variable (R 2 = 0.12-0.65) than NDVI across seasons. Moreover, correlations were slightly lower compared to previous results in the literature [13,55]. Specifically, lower accuracies were obtained from the spring 2018 experiments due to early flower initiation from drought stresses.…”

Canopy height measurements and non‐destructive biomass estimation of Lolium perenne swards using UAV imagery

“…Viljanen et al () used data from four harvesting dates (all in June) with 96 samples of a mixture of timothy and meadow fescue to generate multiple linear regression (MLR) and RF models. Finally, Rueda‐Ayala et al () compared an on‐ground system with an UAV in a limited number of plots ( n = 10) in two different species mixtures using simple linear regression models to estimate DMY and the UAV‐based system showed a lower capability in the estimation ( R 2 < .6). While these studies illustrate the potential of RGB and multispectral sensors to provide estimations of DMY of crops in general and forage grasses in particular, they were rather limited in the number of plots, conditions tested and/or growth stages considered, which may limit the general applicability of the results found.…”

High-Throughput Phenotyping Analysis of Potted Soybean Plants Using Colorized Depth Images Based on A Proximal Platform

“…The application of a Kinect sensor in the acquisition of soybean canopy information in natural light conditions could reduce costs and increase the utilization of imaging techniques in the field of phenotypic research, benefitting the plant science community [46,47]. The image acquisition platform has been demonstrated to be capable of using Kinect sensor for data collection in a high-throughput fashion under natural light conditions.…”