Multispectral Vineyard Segmentation: A Deep Learning approach

TL;DR

This study evaluates deep learning and unsupervised methods for vineyard segmentation using multimodal aerial imagery, finding deep networks outperform classical methods and that RGB images often suffice for effective segmentation.

Contribution

It provides a comprehensive comparison of deep segmentation networks and unsupervised methods on multimodal vineyard datasets, highlighting the effectiveness of deep learning and the sufficiency of RGB data.

Findings

Deep learning networks outperform classical methods.

Multimodal data slightly improves segmentation performance.

RGB images often match or exceed multispectral performance.

Abstract

Digital agriculture has evolved significantly over the last few years due to the technological developments in automation and computational intelligence applied to the agricultural sector, including vineyards which are a relevant crop in the Mediterranean region. In this work, a study is presented of semantic segmentation for vine detection in real-world vineyards by exploring state-of-the-art deep segmentation networks and conventional unsupervised methods. Camera data have been collected on vineyards using an Unmanned Aerial System (UAS) equipped with a dual imaging sensor payload, namely a high-definition RGB camera and a five-band multispectral and thermal camera. Extensive experiments using deep-segmentation networks and unsupervised methods have been performed on multimodal datasets representing four distinct vineyards located in the central region of Portugal. The reported results indicate that SegNet, U-Net, and ModSegNet have equivalent overall performance in vine segmentation. The results also show that multimodality slightly improves the performance of vine segmentation, but the NIR spectrum alone generally is sufficient on most of the datasets. Furthermore, results suggest that high-definition RGB images produce equivalent or higher performance than any lower resolution multispectral band combination. Lastly, Deep Learning (DL) networks have higher overall performance than classical methods. The code and dataset are publicly available at https://github.com/Cybonic/DL_vineyard_segmentation_study.git