Deep learning approach for mango varieties identification using UAV imagery

Abstract

In this study, we propose a deep learning approach for the detection, variety identification, and health assessment of mango trees using UAV imagery. We used a DJI P4 Multispectral camera to collect images of mango orchards which were then used to train YOLOv5, YOLOv7, and Detectron2, three state-of-the-art object detection models. Our models were able to accurately detect trees in an image and classify the variety of the mango tree, as well as identify whether the tree is healthy or not. This approach can be useful for monitoring and managing mango orchards, as it allows for the efficient and accurate identification of tree variety and health status. This can be helpful for farmers as it can assist in early identification of diseased or unproductive trees, enabling timely action to be taken, such as providing targeted treatment or replacing the unproductive trees. Additionally, identifying the variety of the tree can help farmers in making better decision regarding harvesting, pruning and other orchard management tasks. The use of DJI P4 Multispectral camera enabled us to acquire both RGB and NDVI data, which helped us to differentiate the healthy trees from the unhealthy ones. The results of our study showed that the YOLOv5 model performed the best, achieving an overall accuracy of more than 80% in tree detection, variety identification and health assessment, demonstrating the potential of UAV imagery, multispectral sensor and deep learning in fruit orchard management. The proposed approach can be easily scaled and applied to other crop fields as well, providing farmers with a reliable and efficient tool for monitoring and management of their orchards.