SPICY: towards automated phenotyping of large pepper plants in the greenhouse

Abstract

Most high-throughput systems for automated plant phenotyping involve a fixed recording cabinet to which plants are transported. However, important greenhouse plants like pepper are too tall to be transported. In this research we developed a system to automatically measure plant characteristics of tall pepper plants in the greenhouse. With a device equipped with multiple cameras, images of plants are recorded at a 5 cm interval over a height of 3 m. Two types of features are extracted: (1) features from a 3D reconstruction of the plant canopy; and (2) statistical features derived directly from RGB images. The experiment comprised 151 genotypes of a recombinant inbred population of pepper, to examine the heritability and quantitative trait loci (QTL) of the features. Features extracted from the 3D reconstruction of the canopy were leaf size and leaf angle, with heritabilities of 0.70 and 0.56 respectively. Three QTL were found for leaf size, and one for leaf angle. From the statistical features, plant height showed a good correlation (0.93) with manual measurements, and QTL were in accordance with QTL of manual measurements. For total leaf area, the heritability was 0.55, and two of the three QTL found by manual measurement were found by image analysis.

Phenotyping plants: genes, phenes and machines

“…This poses strong challenges upon the analysis, especially when it comes to computationally separating leaves from each other in an environment with natural variation in light levels. Van der Heijden et al (2012) combine traditional red-green-blue (RGB) cameras with a time-of-flight (TOF) camera, which can gauge depth by measuring the distance from the camera to the object. The information from both systems is linked to differentiate between different leaves.…”

Leaf segmentation in plant phenotyping: a collation study

“…Several specialized algorithms have been developed to measure whole-plant properties and particularly plant size [6,17,25,27,31,40,55,61]. Nondestructive measurement of a plant's projected leaf area (PLA), i.e., the counting of plant pixels from top-view images, is considered a good approximation of plant size for rosette plants and is currently used.…”

Validation of plant part measurements using a 3D reconstruction method suitable for high-throughput seedling phenotyping

“…These systems acquire a 2.5-dimensional (2.5D) model of plants. The depth can be measured by range cameras based on lasers (LIDAR) [20], by time-of-flight (ToF) cameras [8,[21][22][23], or using stereoscopic cameras [7,24]. Other systems use projectedlight cameras, such as Microsoft Kinect, to obtain 2.5D plant models as in [22].…”

“…3D geometrically accurate models of plants enable more accurate measurements and modelling of biological processes, such as, photosynthesis, yield prediction, and plant-growth modelling. Some non-invasive phenotyping systems make use of 2D hyperspectral imaging such as HyperART [6], or systems for measurement of structural parameters of plant canopies [7,8].…”