Self-supervised Learning for Hyperspectral Images of Trees

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rahman, Moqsadur, Kumar, Saurav, Palmate, Santosh S., Hossain, M. Shahriar
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914025962471424
author Rahman, Moqsadur
Kumar, Saurav
Palmate, Santosh S.
Hossain, M. Shahriar
author_facet Rahman, Moqsadur
Kumar, Saurav
Palmate, Santosh S.
Hossain, M. Shahriar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05630
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-supervised Learning for Hyperspectral Images of Trees
Rahman, Moqsadur
Kumar, Saurav
Palmate, Santosh S.
Hossain, M. Shahriar
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title Self-supervised Learning for Hyperspectral Images of Trees
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2509.05630