An opinion on imaging challenges in phenotyping field crops

Abstract

Almost all the world's food is grown in open fields, where plant phenotypes can be very different from those observed in greenhouses. Geneticists and agronomists studying food crops routinely detect, measure, and classify a wide variety of phenotypes in fields that contain many visually distinct types of a single crop. Augmenting humans in these tasks by automatically interpreting images raises some important and nontrivial challenges for research in computer vision. Nonetheless, the rewards for overcoming these obstacles could be exceptionally high for today's 7 billion people, let alone the 9.6 billion projected by 2050 (United Nations Department of Economic and Social Affairs, Population Division, World Population Prospects: The 2012 Revision). To stimulate dialog between researchers in computer vision and those in genetics and agronomy, we offer our views on three computational challenges that are central to many phenotyping tasks. These are disambiguating one plant from another; assigning an individual plant's organs to it; and identifying field phenotypes from those shown in archival images. We illustrate these challenges with annotated photographs of maize highlighting the regions of interest. We also describe some of the experimental, logistical, and photographic constraints on image collection and processing. While collecting the data sets needed for algorithmic experiments requires sustained collaboration and funding, the images we show and have posted should allow one to consider the problems, think of possible approaches, and decide on the next steps.

Back into the wild—Apply untapped genetic diversity of wild relatives for crop improvement

“…However, the development of a high-throughput phenotyping pipeline remains challenging, especially in the field (Kelly et al, 2016). Some of the genomic regions associated with domestication traits have enhanced our understanding of their genetic basis, and will encourage further investigation to see whether allelic variation in those regions in CWRs can additionally benefit crop improvement.…”

CropQuant: An automated and scalable field phenotyping platform for crop monitoring and trait measurements to facilitate breeding and digital agriculture

“…near-infrared laser lines and Light Detection and Ranging, LiDAR) and multi– or hyper-spectral sensors are applied to automate crop monitoring of a fixed number of pots or plots, either in the field 28,29 or in greenhouses 12,30 . Although these advances are making important contributions to the research domain, there are limitations and challenges associated with their usage such as high costs, restricted mobility and scalability, limited frequency of screening, and inadequate software tools for phenotypic analyses 31,32 . In particular, while satellite imagery and UAVs are capable of screening tens of thousands of plots at multiple locations, their applications are subject to civil aviation rules, low spatial resolution and bad weather conditions such as heavy rainfall, strong wind and cloud coverage.…”

Machine Learning for Plant Phenotyping Needs Image Processing

“…the image analysis process isolating the plant from background (e.g., soil) as Figure 1 When this is not the case, plant segmentation can be extremely complex because here the objects of interest may touch and overlap each other (known as occlusion), as in Figure 1(B). In the open field [6] this becomes exceedingly more complex: light variations, plant movements due to wind, and other factors are introduced, and background (e.g., other plants) may look like the subject of interest, as Figure 1(C) illustrates. Thus, the process of extracting information from image data is directly linked with the setup and the environment.…”