Agriculture.

This dataset has been curated to support the development and evaluation of lightweight object detection algorithms for precision pesticide spraying in orchard environments. It comprises annotated images captured in diverse natural lighting and occlusion conditions typical of real-world agricultural fields. The dataset includes high-resolution RGB images along with corresponding bounding box annotations in YOLO format, identifying key targets. All annotations are manually verified to ensure label accuracy.

Plant diseases remain a significant threat to global agriculture, necessitating rapid and

accurate detection to minimize crop loss. This paper presents a lightweight, end-to-end system for plant

leaf disease detection and severity estimation, optimized for real-time field deployment. We propose a

custom Convolutional Neural Network (CNN), built using PyTorch, trained on the PlantVillage dataset

to classify leaves as healthy or diseased with a test accuracy of 92.06%. To enhance its practical relevance,