Modern robotics has enabled the advancement in yield estimation for precision agriculture. However, when applied to the olive industry, the high variation of olive colors and their similarity to the background leaf canopy presents a challenge. Labeling several thousands of very dense olive grove images for segmentation is a labor-intensive task. This paper presents a novel approach to detecting olives without the need to manually label data. In this work, we present the world's first olive detection dataset comprised of synthetic and real olive tree images. This is accomplished by generating an auto-labeled photorealistic 3D model of an olive tree. Its geometry is then simplified for lightweight rendering purposes. In addition, experiments are conducted with a mix of synthetically generated and real images, yielding an improvement of up to 66% compared to when only using a small sample of real data. When access to real, human-labeled data is limited, a combination of mostly synthetic data and a small amount of real data can enhance olive detection.

Drones equipped with hyperspectral and thermal sensors will be deployed in Italy to spot trees infected with Xylella fastidiosa, the deadly bacterium that has been devastating the country's olive crops for almost a decade. The sensors will be able to detect almost indiscernible signs of early infection, such as very slight changes in colour to the leaves, allowing farmers to cull affected trees and prevent outbreaks. More than 300,000 trees will be examined using the new drone technology in the next few months.