Assessment of Stress on Plants Through Neural Networks

Abstract

Among the many problems that cost growers money, plant stress is a major one. Applications of the traditional methods for identifying stressed plants are limited by the time and effort required to perform the identification. Effective, quick solutions are needed immediately. Changes in precision agriculture using deep learning and big data are being sparked by advancements in cutting-edge sensing and machine learning techniques. In this paper, we surveyed recent advances in deep learning techniques for use in analyzing images for the diagnosis of crop stress. We compiled recent sensor technology and deep learning principles used for plant stress phenotyping. Additionally, we surveyed several deep learning applications/functions that are intertwined with plant stress imaging, such as classification, object detection, and segmentation. Additionally, we summed up the issues plaguing plant phenotyping today and talked about potential future directions for improvement.