TomatoDIFF: On-plant Tomato Segmentation with Denoising Diffusion Models

TL;DR

TomatoDIFF is a new diffusion-based model that achieves state-of-the-art accuracy in segmenting on-plant tomatoes, even in occluded conditions, supported by a new comprehensive dataset of greenhouse tomato images.

Contribution

The paper introduces TomatoDIFF, a novel diffusion model for tomato segmentation, and presents Tomatopia, a large dataset for training and evaluating such models.

Findings

TomatoDIFF outperforms existing methods in challenging environments.

The new dataset, Tomatopia, provides high-quality annotations for tomato segmentation.

Diffusion models can effectively handle occlusions in fruit segmentation tasks.

Abstract

Artificial intelligence applications enable farmers to optimize crop growth and production while reducing costs and environmental impact. Computer vision-based algorithms in particular, are commonly used for fruit segmentation, enabling in-depth analysis of the harvest quality and accurate yield estimation. In this paper, we propose TomatoDIFF, a novel diffusion-based model for semantic segmentation of on-plant tomatoes. When evaluated against other competitive methods, our model demonstrates state-of-the-art (SOTA) performance, even in challenging environments with highly occluded fruits. Additionally, we introduce Tomatopia, a new, large and challenging dataset of greenhouse tomatoes. The dataset comprises high-resolution RGB-D images and pixel-level annotations of the fruits.