A Survey on Crop Leaf Disease Detection Using Digital and Remote Sensing Imaging Techniques

Abstract

Securing agricultural productivity and food security from serious threats is made possible through timely and reliable disease detection. The early detection of leaf disease is revolutionized by the recent advancements in imaging technology like digital imaging and remote sensing (RS) integrated with Artificial intelligence (AI). High- resolution, close-range visual data was offered by digital imaging, and it is crucial for detecting subtle symptoms in various applications. Large-scale monitoring over fields was facilitated by the RS platforms like drones and satellites, and it may help the farmers in offering actionable insights. Modern methods for crop leaf disease detection was reviewed in this study by analysing various imaging techniques like pre-processing, feature extraction (FE), classification techniques, and deep learning (DL) advancements. The datasets included, risks, and performance metrics utilized are all discussed in this review. The field of disease surveillance using AI and multimodal imaging has shown advancements in facilitating scalable, and real-time disease surveillance, and it is also highlighted in this review. The future paths for precision agriculture are guided by conclusion of the study, as it offers insights regarding present research gaps

Plant phenotyping relevance

作物葉の病徴を画像から検出する手法について、画像処理・特徴抽出・分類・深層学習・データセット・性能指標を体系的に扱うレビューであり、植物表現型取得手法が中心です。

Code and data availability

This is a literature survey on crop leaf disease detection. It reports no original phenotyping measurements or computational analysis of its own, presents no author code, models, or data deposits, and only references third-party datasets (PlantVillage, Cassava, DeepWeeds, etc.) as cited prior work, which do not qualify

No evidence-backed public reproduction asset is currently recorded.