Saved in:
Bibliographic Details
Main Authors: Arnold, Jackson, Rossi, Sophia, Petrosino, Chloe, Mitchell, Ethan, Koppal, Sanjeev J.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.04287
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913380303896576
author Arnold, Jackson
Rossi, Sophia
Petrosino, Chloe
Mitchell, Ethan
Koppal, Sanjeev J.
author_facet Arnold, Jackson
Rossi, Sophia
Petrosino, Chloe
Mitchell, Ethan
Koppal, Sanjeev J.
contents Hyperspectral image segmentation is crucial for many fields such as agriculture, remote sensing, biomedical imaging, battlefield sensing and astronomy. However, the challenge of hyper and multi spectral imaging is its large data footprint. We propose both a novel camera design and a vision transformer-based (ViT) algorithm that alleviate both the captured data footprint and the computational load for hyperspectral segmentation. Our camera is able to adaptively sample image regions or patches at different resolutions, instead of capturing the entire hyperspectral cube at one high resolution. Our segmentation algorithm works in concert with the camera, applying ViT-based segmentation only to adaptively selected patches. We show results both in simulation and on a real hardware platform demonstrating both accurate segmentation results and reduced computational burden.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04287
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SpectralZoom: Efficient Segmentation with an Adaptive Hyperspectral Camera
Arnold, Jackson
Rossi, Sophia
Petrosino, Chloe
Mitchell, Ethan
Koppal, Sanjeev J.
Computer Vision and Pattern Recognition
Robotics
Hyperspectral image segmentation is crucial for many fields such as agriculture, remote sensing, biomedical imaging, battlefield sensing and astronomy. However, the challenge of hyper and multi spectral imaging is its large data footprint. We propose both a novel camera design and a vision transformer-based (ViT) algorithm that alleviate both the captured data footprint and the computational load for hyperspectral segmentation. Our camera is able to adaptively sample image regions or patches at different resolutions, instead of capturing the entire hyperspectral cube at one high resolution. Our segmentation algorithm works in concert with the camera, applying ViT-based segmentation only to adaptively selected patches. We show results both in simulation and on a real hardware platform demonstrating both accurate segmentation results and reduced computational burden.
title SpectralZoom: Efficient Segmentation with an Adaptive Hyperspectral Camera
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2406.04287