SpectralZoom: Efficient Segmentation with an Adaptive Hyperspectral Camera

TL;DR

SpectralZoom introduces an adaptive hyperspectral camera combined with a ViT-based segmentation algorithm, significantly reducing data size and computational load while maintaining high segmentation accuracy in various applications.

Contribution

The paper presents a novel adaptive hyperspectral camera design and a ViT-based segmentation method that together optimize data capture and processing efficiency.

Findings

Achieves accurate segmentation with reduced data footprint.

Demonstrates effectiveness on real hardware platform.

Reduces computational load compared to traditional methods.

Abstract

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.