An ultra-lightweight efficient network for image-based plant disease and pest infection detection

Abstract

Plant diseases and pest infections are major factors that undermine the growth of plants along with their life cycle. Optical image-based plant disease detection provides an efficient and low cost way for real-time plant growth monitoring and management. In recent years, the thriving development of deep learning techniques in a variety of communities has validated its great performance in image interpretation and understanding. Existing deep learning-based methods for plant disease classification mostly adopt convolutional neural networks (CNNs) that have been originally developed for general image classification purposes. These CNN architectures consist of a very large volume of training parameters, which severely hinders its applicability under scenarios requiring fast and flexible deployment on compact devices with limited computation powers. In this paper, an ultra-lightweight efficient network (ULEN) is proposed targeting image-based plant disease and pest infection detection. The proposed network consists of two parts, a deep feature extraction module that adopts residual depth-wise convolution and a classification module receiving multi-scale features enhanced by a spatial pyramid pooling layer. The network is constructed in a very compact design with approximately only 100 000 parameters, which greatly favors the demand for a lightweight model for practical needs. Two publicly available plant datasets collected at the indoor and outdoor environments were tested on two compact devices to validate its applicability under different scenarios. Compared with the state-of-the-art architectures, the proposed network showed superior performance with the least computation complexity and compelling classification accuracy.

Plant phenotyping relevance

植物画像から病害・害虫感染状態を推定する軽量画像解析ネットワークを開発し、公開データセットと実機で性能・適用性を検証しており、植物状態の取得手法が中心である。

Code and data availability

The paper's experiments are built entirely on two public plant image datasets: the PlantVillage dataset (54,306 leaf images, 38 disease/plant classes) and the Cassava leaf disease dataset (21,397 field-collected images). Both are publicly available and are the direct inputs to the paper's plant disease classification/б