Enhancing Agricultural Efficiency: Deep Learning-Based Soil Crack Detection for Water Irrigation

Abstract

The escalating demand for agricultural precision and environmental monitoring underscores the necessity for effective soil crack detection methods. This study explores the feasibility of employing a Raspberry Pi-powered camera system and deep learning image recognition to detect soil cracks and control agricultural irrigation. The purpose is to develop a soil crack detection system using deep learning techniques, sustain plant growth process, increase productivity, and optimize water irrigation practice. Our approach leverages TensorFlow to craft a convolutional neural network tailored specifically for execution on a Raspberry Pi 3B+. A dataset comprises manually captured images and is trained with the InceptionV3 model categorized into crack or nocrack classes. The accuracy is achieved ranging from 97% to 99%. These results underscore deep learning image recognition models on Raspberry Pi for cost-effective soil crack monitoring and controlling the plants watering system.