Detecting Olives with Synthetic or Real Data? Olive the Above

TL;DR

This paper introduces a novel olive detection method using a combined dataset of synthetic and real images, significantly reducing labeling effort and improving detection accuracy in precision agriculture.

Contribution

It presents the first olive detection dataset with synthetic and real images generated from a photorealistic 3D model, enabling effective detection without extensive manual labeling.

Findings

Up to 66% improvement using mixed synthetic and real data

Synthetic data can compensate for limited real labeled data

A lightweight rendering approach simplifies the 3D model for practical use

Abstract

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.