Imaging methods for phenotyping of plant traits

Abstract

This chapter introduces the domain of image analysis, both in general and as applied to the problem of plant phenotyping. Images can be thought of as a measurement tool, and the automated processing of images allows for greater throughput, reliability and repeatability, at all scales of measurement (from microscopic to field level). This domain should be of increasing interest to plant scientists, as the cost of image-based sensors is dropping, and photographing plants on a daily or even minute-by-minute basis is now cost-effective. With such systems there is a possibility of tens of thousands of photographs being recorded, and so the job of analysing these images must now fall to computational methods. In this chapter, we provide an overview of recent work in image analysis for plant science and highlight some of the key techniques from computer vision that have been applied to date to the problem of phenotyping plants. We conclude with a description of the four main challenges for image analysis and plant science: Growth, occlusion, evaluation and low-cost sensor vision.