An open, scalable, and flexible framework for automated aerial measurement of field experiments

Abstract

Unoccupied areal vehicles (UAVs or drones) are increasingly used in field research. Drones capable of routinely and consistently capturing high quality imagery of experimental fields have become relatively inexpensive. However, converting these images into scientifically useable data has become a bottleneck. A number of tools exist to support this workflow, but there is no framework for making these tools interopreable, sharable, and scalable. Here we present an initial draft of the Drone Processing Pipeline (DPP), a framework for processing agricultural research imagery that supports best practices and interoperability. DPP emphasizes open software and data that can be shared among and used in whole or part by the research community. We are building the DPP as a distributed, scalable, and flexible pipeline for converting drone imagery into orthomosaics, point clouds, and plot level statistics. Our intent is not to replace, but to integrate components from the emerging ecosystem of utilities with a focus on end-to-end automation and scalability. The initial focus of DPP is the measurements of experimental plots in field research. In the future we expect that standardization will enable new scientific discovery by facilitating collaboration and sharing of software and data. Our vision is to create a processing pipeline that is open, flexible, extensible, portable, and automated. With modern tools, deploying a pipeline on a laptop or HPC should only take a single command. Running a pipeline and publishing data should require only input data and a defined workflow.

Unoccupied aerial systems imagery for phenotyping in cotton, maize, soybean, and wheat breeding

“…Researchers have developed several solutions addressing these challenges. A few examples of semiautomated and automated analysis of UAS data for small-plot research include ImageBreed (Morales et al, 2020), pheno-image analysis (Selvaraj et al, 2020), FIELDImageR (Matias et al, 2020), drone processing pipeline (Schnaufer et al, 2020), R/UAS tools , and Bison-Fly (Matias et al, 2022). These overall processes are further discussed and compared in their respective papers and will not be described here.…”

FIELDimageR.Extra: Advancing user experience and computational efficiency for analysis of orthomosaic from agricultural field trials

“…The use of unmanned aerial vehicles (UAVs) in agriculture has grown significantly, allowing for efficient monitoring and valuable information extraction using various image capturing sensors (Cruzan et al., 2016; Schnaufer et al., 2020; Shi et al., 2016). Alongside this progress, there has been a marked increase in the development of open‐source geographic information system (GIS) tools tailored for processing, manipulating, and integrating spatial and non‐spatial data (Anderson & Murray, 2020; Matias et al., 2020; Morales et al., 2020; Tresch et al., 2019).…”

High-Throughput Phenotyping of Soybean Maturity Using Time Series UAV Imagery and Convolutional Neural Networks

“…Systems for data management, including user-friendly components for data modeling and integration, are fundamental for the adoption of these technologies [14]. The phenotyping pipeline also has to include metadata and integrate other sources of information following best practices and interoperability guidelines [20].…”