Abstract
Computer vision models that can recognize plant diseases in the field would be valuable tools for disease management and resistance breeding. Generating enough data to train these models is difficult, however, since only trained experts can accurately identify symptoms. In this study, we describe and implement a two-step method for generating a large amount of high-quality training data with minimal expert input. First, experts located symptoms of northern leaf blight (NLB) in field images taken by unmanned aerial vehicles (UAVs), annotating them quickly at low resolution. Second, non-experts were asked to draw polygons around the identified diseased areas, producing high-resolution ground truths that were automatically screened based on agreement between multiple workers. We then used these crowdsourced data to train a convolutional neural network (CNN), feeding the output into a conditional random field (CRF) to segment images into lesion and non-lesion regions with accuracy of 0.9979 and F1 score of 0.7153. The CNN trained on crowdsourced data showed greatly improved spatial resolution compared to one trained on expert-generated data, despite using only one fifth as many expert annotations. The final model was able to accurately delineate lesions down to the millimeter level from UAV-collected images, the finest scale of aerial plant disease detection achieved to date. The two-step approach to generating training data is a promising method to streamline deep learning approaches for plant disease detection, and for complex plant phenotyping tasks in general.
Highlights
Machine learning models for object detection require a large amount of training data, typically generated by humans
All Mechanical Turk human intelligence tasks (HITs) consisted of one or more prompts to draw a single bounding polygon delineating the boundaries of a single lesion (Figure 2, top right), previously annotated with a line down the major axis by one of two human experts (Wiesner-Hanks et al, 2018)
Mechanical Turk (MTurk) workers drew 15,240 polygon annotations on 5,080 lesions, cropped from 752 parent images collected by the unmanned aerial vehicles (UAVs)
Summary
Machine learning models for object detection require a large amount of training data, typically generated by humans. Millimeter-Level Plant Disease Detection could accurately identify maize male flowers in images where they were clearly visible. Accurate identification of many plant features requires a certain level of expertise, . If only a handful of human experts are qualified and willing to generate training data, the process takes much longer than if tasks could be reliably performed by hundreds or thousands of non-experts. This places a burden on those experts and creates a bottleneck in the model training process
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
