Potato crop stress identification in aerial images using deep learning‐based object detection. (24th September 2021)

• Record Type: Journal Article
• Authors: Butte, Sujata; Vakanski, Aleksandar; Duellman, Kasia; Wang, Haotian; Mirkouei, Amin
• Is Part Of: Agronomy Journal. Volume 113:Number 5(2021)
• Page Start: 3991
• Page End: 4002
• Publication Date: 2021-09-24
• Subjects: Agronomy -- Periodicals; 630
• DOI: 10.1002/agj2.20841
• Languages: English
• ISSNs: 0002-1962

Abstract

Abstract: Recent research on the application of remote sensing and deep learning‐based analysis in precision agriculture demonstrated a potential for improved crop management and reduced environmental impacts of agricultural production. Despite the promising results, the practical relevance of these technologies for field deployment requires novel algorithms that are customized for analysis of agricultural images and robust to implementation on natural field imagery. The paper presents an approach for analyzing aerial images of a potato ( Solanum tuberosum L.) crop using deep neural networks. The main objective is to demonstrate automated spatial recognition of healthy vs. stressed crop at a plant level. Specifically, we examine premature plant senescence resulting in drought stress on 'Russet Burbank' potato plants. We propose a novel deep learning (DL) model for detecting crop stress, named Retina‐UNet‐Ag. The proposed architecture is a variant of Retina‐UNet and includes connections from low‐level semantic representation maps to the feature pyramid network. The paper also introduces a dataset of aerial field images acquired with a Parrot Sequoia camera. The dataset includes manually annotated bounding boxes of healthy and stressed plant regions. Experimental validation demonstrated the ability for distinguishing healthy and stressed plants in field images, achieving an average dice score coefficient (DSC) of 0.74. A comparison to related state‐of‐the‐art DL models for object detection revealed that the presented approach is effective for this task. The proposed method is conducive toward the assessment and recognition of potato crop stress in aerial field images collected under natural conditions. Core Ideas: New deep learning method for identification of drought stress in potato plants. Implemented on images collected under natural field conditions by a low‐flying unmanned aerial vehicle. The approach modifies the feature pyramid network used in object detection models. Connections to low‐level semantical information from the encoding path introduced. The generated dataset of potato field images has been posted for open public access.