UAV imagery coupled deep learning approach for the development of an adaptive in-house web-based application for yield estimation in citrus orchard

• Published in: Measurement : journal of the International Measurement Confederation Vol. 234; p. 114786
• Main Authors: Subeesh, A., Prakash Kumar, Satya, Kumar Chakraborty, Subir, Upendar, Konga, Singh Chandel, Narendra, Jat, Dilip, Dubey, Kumkum, Modi, Rajesh U., Mazhar Khan, Mohammad
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.07.2024
• Subjects: Citrus; Computer vision; Deep learning; Precision horticulture; Web application; Yield estimation; Citrus; Deep learning; Computer vision; Yield estimation; Precision horticulture; Web application
• ISSN: 0263-2241; 1873-412X
• DOI: 10.1016/j.measurement.2024.114786

[Display omitted] •UAV imagery coupled deep learning approach was employed for citrus yield estimation.•Performance of object detection models was evaluated for fruits in a citrus orchard.•Fruit size estimation was carried out using traditional image processing and deep learning.•Yield of the orchard and fruit size was successfully modelled.•‘DeepYield’ is a web-based application developed for citrus yield estimation. Orchard yield estimation enables a farmer to make informed decisions. The limitations of visual inspection-based yield estimation approaches can be effectively addressed by the intervention of unmanned aerial vehicles (UAVs) and advanced image processing using deep learning algorithms. This study proposes a methodology combining deep learning-driven UAV imagery and an in-house web-based application, “DeepYield”; to measure yield in a citrus fruit orchard. The state-of-the-art deep learning object detection models SSD, Faster RCNN, YOLOv4, YOLOv5 and YOLOv7 were evaluated for detecting “harvest-ready” and “unripe” citrus fruits from the tree images. Fruit size estimation was carried out using traditional as well as deep learning-based image segmentation models. YOLOv7 outperformed other models with a mAP, Precision, Recall, and F1-Score of 86.48, 88.54, 83.66 and 86.03%, respectively. The developed solution was integrated into a web-based application as ‘DeepYield’ to enhance users’ convenience and equip them with an automated yield estimation solution.