TITLE:
A Systematic Review on Maize Northern Corn Leaf Blight Detection Using AI Models and Aerial Field Images
AUTHORS:
Tashinga Gerald Machingauta, Mayumbo Nyirenda
KEYWORDS:
Review, Northern Corn Leaf Blight, Drone Imagery, AI Model, Computer Vision
JOURNAL NAME:
Advances in Artificial Intelligence and Robotics Research,
Vol.2 No.3,
July
28,
2026
ABSTRACT: Northern corn leaf blight (NCLB) or Northern Leaf Blight (NLB) disease remains a global challenge, affecting maize production. Detecting this disease earlier reduces the severity of the disease before it has a devastating impact on crop yield. Recent technological advancements in agriculture have revolutionized crop disease detection and monitoring by leveraging computer vision algorithms for disease detection and UAVs for capturing high-resolution aerial images. However, aerial imagery for NCLB disease is associated with specific challenges, such as occlusion and small object detection problems, which might affect AI model performance accuracy. Therefore, this systematic literature review (SLR) tries to understand the state-of-the-art techniques and methods used to mitigate occlusion and small object detection problems. The study adopts Kitchenham’s systematic literature review guidelines to select primary studies for the synthesis analysis. A Boolean search string was utilized on Google Scholar to extract primary studies, and out of 174 studies indexed on Google Scholar, only 7 were selected based on inclusion criteria. The SLR highlighted the AI architectural progression from heavily parameterized CNNs to lightweight models fused with attention modules.