Transfer Learning and Object Detection for Improved Date Fruit Pest Recognition

摘要

With the growing presence of artificial intelligence (AI) technologies, smart agriculture has seen significant advances in recent years. The deployment of smart sensors, drones, and robotics integrated with AI algorithms in agricultural settings enables the acquisition and assessment of extensive agricultural data, including soil and crop health information, weather conditions, and pest infestation levels. This technological integration assists farmers in automating mundane agricultural activities, enhancing productivity, and implementing targeted interventions. Date farming is a large industry in Algeria that requires effective preservation strategies. Unfortunately, the cultivation of date palms is constantly threatened by numerous diseases and pests, resulting in substantial decreases in crop yield. Therefore, timely detection of insect infestations is crucial. In this context, our work focuses primarily on detecting and classifying the insects that attack date palm fruits. To achieve this, we employ transfer learning and object detection techniques. The developed model consistently demonstrates high performance in terms of accuracy, precision, and recall, indicating its reliability for real-world applications. It can detect harmful insects before they infect date palms. This early detection capability can greatly contribute to the implementation of timely intervention and preventive measures, effectively reducing crop losses.