English

Self-supervised Learning for Hyperspectral Images of Trees

Computer Vision and Pattern Recognition 2025-09-09 v1 Artificial Intelligence Machine Learning

Abstract

Aerial remote sensing using multispectral and RGB imagers has provided a critical impetus to precision agriculture. Analysis of the hyperspectral images with limited or no labels is challenging. This paper focuses on self-supervised learning to create neural network embeddings reflecting vegetation properties of trees from aerial hyperspectral images of crop fields. Experimental results demonstrate that a constructed tree representation, using a vegetation property-related embedding space, performs better in downstream machine learning tasks compared to the direct use of hyperspectral vegetation properties as tree representations.

Keywords

Cite

@article{arxiv.2509.05630,
  title  = {Self-supervised Learning for Hyperspectral Images of Trees},
  author = {Moqsadur Rahman and Saurav Kumar and Santosh S. Palmate and M. Shahriar Hossain},
  journal= {arXiv preprint arXiv:2509.05630},
  year   = {2025}
}
R2 v1 2026-07-01T05:24:12.200Z