Biology subjects

Zare, A.

Publications and source records attributed to Zare, A..

21 records · Page 2Linked to original sources

bioRxiv2019

RhizoVision Crown: An Integrated Hardware and Software Platform for Root Crown Phenotyping

Root crown phenotyping measures the top portion of crop root systems and can be used for marker-assisted breeding, genetic mapping, and understanding how roots influence soil resource acquisition. Several imaging protocols and image analysis programs exist, but they are not optimized for high-throughput, repeatable, and robust root crown phenotyping. The RhizoVision Crown platform integrates an imaging unit, image capture software, and image analysis software that are optimized for reliable extraction of measurements from large numbers of root crowns. The hardware platform utilizes a back light and a monochrome machine vision camera to capture root crown silhouettes. RhizoVision Imager and RhizoVision Analyzer are free, open-source software that streamline image capture and image analysis with intuitive graphical user interfaces. RhizoVision Analyzer was physically validated using copper wire and features were extensively validated using 10,464 ground-truth simulated images of dicot and monocot root systems. This platform was then used to phenotype soybean and wheat root crowns. A total of 2,799 soybean (Glycine max) root crowns of 187 lines and 1,753 wheat (Triticum aestivum) root crowns of 186 lines were phenotyped. Principal component analysis indicated similar correlations among features in both species. The maximum heritability was 0.74 in soybean and 0.22 in wheat, indicating differences in species and populations need to be considered. The integrated RhizoVision Crown platform facilitates high-throughput phenotyping of crop root crowns, and sets a standard by which open plant phenotyping platforms can be benchmarked.

plant biology↗

bioRxiv2019

Individual tree-crown detection in RGB imagery using self-supervised deep learning neural networks

Remote sensing can transform the speed, scale, and cost of biodiversity and forestry surveys. Data acquisition currently outpaces the ability to identify individual organisms in high resolution imagery. We outline an approach for identifying tree-crowns in RGB imagery while using a semi-supervised deep learning detection network. Individual crown delineation has been a long-standing challenge in remote sensing and available algorithms produce mixed results. We show that deep learning models can leverage existing Light Detection and Ranging (LIDAR)-based unsupervised delineation to generate trees that are used for training an initial RGB crown detection model. Despite limitations in the original unsupervised detection approach, this noisy training data may contain information from which the neural network can learn initial tree features. We then refine the initial model using a small number of higher-quality hand-annotated RGB images. We validate our proposed approach while using an open-canopy site in the National Ecological Observation Network. Our results show that a model using 434,551 self-generated trees with the addition of 2848 hand-annotated trees yields accurate predictions in natural landscapes. Using an intersection-over-union threshold of 0.5, the full model had an average tree crown recall of 0.69, with a precision of 0.61 for the visually-annotated data. The model had an average tree detection rate of 0.82 for the field collected stems. The addition of a small number of hand-annotated trees improved the performance over the initial self-supervised model. This semi-supervised deep learning approach demonstrates that remote sensing can overcome a lack of labeled training data by generating noisy data for initial training using unsupervised methods and retraining the resulting models with high quality labeled data.

ecology↗

bioRxiv2018

A novel multi-perspective imaging platform (M-PIP) for phenotyping soybean root crowns in the field increases throughput and separation ability of genotype root properties

BackgroundRoot crown phenotyping has linked root properties to shoot mass, nutrient uptake, and yield in the field, which increases the understanding of soil resource acquisition and presents opportunities for breeding. The original methods using manual measurements have been largely supplanted by image-based approaches. However, most image-based systems have been limited to one or two perspectives and rely on segmentation from grayscale images. An efficient high-throughput root crown phenotyping system is introduced that takes images from five perspectives simultaneously, constituting the Multi-Perspective Imaging Platform (M-PIP). A segmentation procedure using the Expectation-Maximization Gaussian Mixture Model (EM-GMM) algorithm was developed to distinguish plant root pixels from background pixels in color images and using hardware acceleration (CPU and GPU). Phenes were extracted using MatLab scripts. Placement of excavated root crowns for image acquisition was standardized and is ergonomic. The M-PIP was tested on 24 soybean [Glycine max (L.) Merr.] cultivars released between 1930 and 2005.\n\nResultsRelative to previous reports of imaging throughput, this system provides greater throughput with sustained rates of 1.66 root crowns min-1. The EM-GMM segmentation algorithm with hardware acceleration was able to segment images in 10 s, faster than previous methods, and the output images were consistently better connected with less loss of fine detail. Image-based phenes had similar heritabilities as manual measures with the greatest effect sizes observed for Maximum Radius and Fine Radius Frequency. Correlations were also noted, especially among the manual Complexity score and phenes such as number of roots and Total Root Length. Averaging phenes across perspectives generally increased heritability, and no single perspective consistently performed better than others. Angle-based phenes, Fineness Index, Maximum Width, Holes, Solidity and Width-to-Depth Ratio were the most sensitive to perspective with decreased correlations among perspectives.\n\nConclusionThe substantial heritabilities measured for many phenes suggest that they are potentially useful for breeding. Multiple perspectives together often produced the greatest heritabilities, and no single perspective consistently performed better than others. Thus, as illustrated here for soybean, multiple perspectives may be beneficial for root crown phenotyping systems. This system can contribute to breeding efforts that incorporate under-utilized root phenotypes to increase food security and sustainability.

physiology↗