Abstract
BackgroundImage-based plant phenotyping facilitates the extraction of traits noninvasively by analyzing large number of plants in a relatively short period of time. It has the potential to compute advanced phenotypes by considering the whole plant as a single object (holistic phenotypes) or as individual components, i.e., leaves and the stem (component phenotypes), to investigate the biophysical characteristics of the plants. The emergence timing, total number of leaves present at any point of time and the growth of individual leaves during vegetative stage life cycle of the maize plants are significant phenotypic expressions that best contribute to assess the plant vigor. However, image-based automated solution to this novel problem is yet to be explored.ResultsA set of new holistic and component phenotypes are introduced in this paper. To compute the component phenotypes, it is essential to detect the individual leaves and the stem. Thus, the paper introduces a novel method to reliably detect the leaves and the stem of the maize plants by analyzing 2-dimensional visible light image sequences captured from the side using a graph based approach. The total number of leaves are counted and the length of each leaf is measured for all images in the sequence to monitor leaf growth. To evaluate the performance of the proposed algorithm, we introduce University of Nebraska–Lincoln Component Plant Phenotyping Dataset (UNL-CPPD) and provide ground truth to facilitate new algorithm development and uniform comparison. The temporal variation of the component phenotypes regulated by genotypes and environment (i.e., greenhouse) are experimentally demonstrated for the maize plants on UNL-CPPD. Statistical models are applied to analyze the greenhouse environment impact and demonstrate the genetic regulation of the temporal variation of the holistic phenotypes on the public dataset called Panicoid Phenomap-1.ConclusionThe central contribution of the paper is a novel computer vision based algorithm for automated detection of individual leaves and the stem to compute new component phenotypes along with a public release of a benchmark dataset, i.e., UNL-CPPD. Detailed experimental analyses are performed to demonstrate the temporal variation of the holistic and component phenotypes in maize regulated by environment and genetic variation with a discussion on their significance in the context of plant science.
Highlights
Image-based plant phenotyping facilitates the extraction of traits noninvasively by analyzing large number of plants in a relatively short period of time
Holistic phenotyping analysis We focus our study on the 32 genotypes of maize, and analyzed three holistic phenotypes extracted from the images: plant aerial density, bi-angular convex-hull area ratio and plant aspect ratio
There are the following three observations. (a) For some plants (e.g., Plant_016 − 20+ ), the plant-level accuracy for University of Nebraska–Lincoln (UNL)-CPPD-II is higher than that of UNL-CPPDI. This is attributed to the fact that these plant sequences contain more images in UNL-CPPD-II compared to its smaller version (UNL-CPPD-I) but none of the additional images has crossovers. (b) In contrast, if most of the additional images of UNL-CPPD-II for a sequence have selfocclusions and leaf crossovers, the accuracy is decreased (e.g., Plant-ID: Plant_063 − 32† ). (c) The plant-level accuracy remains fairly similar for both UNL-CPPD-I and UNL-CPPD-II (e.g., Plant_104 − 24‡)
Summary
Image-based plant phenotyping facilitates the extraction of traits noninvasively by analyzing large number of plants in a relatively short period of time. It has the potential to compute advanced phenotypes by considering the whole plant as a single object (holistic phenotypes) or as individual components, i.e., leaves and the stem (component phenotypes), to investigate the biophysical characteristics of the plants. Image-based plant phenotyping refers to the proximal sensing and quantification of plant traits based on analyzing their images captured at regular intervals with precision It facilitates the analysis of a large number of plants in a relatively short period of time with no or little manual intervention to compute diverse phenotypes. Component-based analysis requires first identifying and distinguishing specific structures of a plant such as leaves, stem, or floral organs, and either quantifies properties of these structures individually or quantifies relationships between them. The development of effective component based plant phenotypes is important since they have the potential to improve our understanding of plant growth and development at a higher resolution
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
