Challenges in Hyperspectral Imaging for Autonomous Driving: The HSI-Drive Case

TL;DR

This paper discusses the challenges of applying hyperspectral imaging in autonomous driving, focusing on technical issues like lighting, motion, and computational constraints, and analyzes various techniques using the HSI-Drive dataset.

Contribution

It provides an analysis of hyperspectral imaging challenges in autonomous driving and evaluates different techniques with experimental results from the HSI-Drive dataset.

Findings

Identification of key challenges in HSI for AD

Evaluation of techniques using HSI-Drive data

Insights into real-time HSI processing constraints

Abstract

The use of hyperspectral imaging (HSI) in autonomous driving (AD), while promising, faces many challenges related to the specifics and requirements of this application domain. On the one hand, non-controlled and variable lighting conditions, the wide depth-of-field ranges, and dynamic scenes with fast-moving objects. On the other hand, the requirements for real-time operation and the limited computational resources of embedded platforms. The combination of these factors determines both the criteria for selecting appropriate HSI technologies and the development of custom vision algorithms that leverage the spectral and spatial information obtained from the sensors. In this article, we analyse several techniques explored in the research of HSI-based vision systems with application to AD, using as an example results obtained from experiments using data from the most recent version of the HSI-Drive dataset.