TomatoDIFF: On-plant Tomato Segmentation with Denoising Diffusion Models
This work addresses the need for accurate fruit segmentation to optimize crop growth and yield estimation for farmers, representing a domain-specific advancement in agricultural computer vision.
The paper tackles the problem of segmenting on-plant tomatoes in agricultural settings by proposing TomatoDIFF, a diffusion-based model that achieves state-of-the-art performance, even with occluded fruits, and introduces Tomatopia, a new large dataset of greenhouse tomatoes with RGB-D images and pixel-level annotations.
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.