Computer Vision and Deep Learning for Precise Agriculture: A Case Study of Lemon Leaf Image Classification

Abstract

Abstract Crop protection, an crucial field of precise agriculture, requires attention and improvement, as it secures sustainability and safety of crop and food production. There are various threats to crops in which pest is one of the severest. Computer vision technologies based on deep learning have shown great advantages on image classification as they enable real-time pest recognition on devices with cameras, such as drones. Thus, it is promising for pest monitoring and control and many DL models have been developed. Furthermore, early and accurate diagnosis is need as it minimizes pest damage. However, traditional models are limited on speed because the massive parameters require huge computing resource. In this work, we investigate the capability of lightweight model based on DL for the task of leaf disease classification on uncontrolled environment and compare it with traditional DL model. Lightweight models, in general, are designed to reduce computation on convolution layers with acceptable accuracy lose. We use an open database named LeLePhid, which contains lemon leave images, healthy or affected by aphid. The damage caused by aphid is general as the pest makes obvious changes to leaf outlooks. We focus on two typical DL models: the traditional, DenseNet and the lightweight, MobileNet, and discuss the balance between speed and accuracy, in order to support real-time analytics. Finally, we discuss the challenges and opportunities in practice.