Evaluation of Color Anomaly Detection in Multispectral Images For Synthetic Aperture Sensing

TL;DR

This paper evaluates unsupervised color anomaly detection methods in multispectral images from synthetic aperture sensing, emphasizing real-time search and rescue applications and the benefits of thermal channels and optimized color spaces.

Contribution

It demonstrates the impact of color space choice and thermal channels on anomaly detection performance in multispectral aerial imagery for rescue missions.

Findings

Thermal channels improve detection accuracy.

HSV and HLS outperform RGB in forest environments.

Color space choice affects detection quality.

Abstract

In this article, we evaluate unsupervised anomaly detection methods in multispectral images obtained with a wavelength-independent synthetic aperture sensing technique, called Airborne Optical Sectioning (AOS). With a focus on search and rescue missions that apply drones to locate missing or injured persons in dense forest and require real-time operation, we evaluate runtime vs. quality of these methods. Furthermore, we show that color anomaly detection methods that normally operate in the visual range always benefit from an additional far infrared (thermal) channel. We also show that, even without additional thermal bands, the choice of color space in the visual range already has an impact on the detection results. Color spaces like HSV and HLS have the potential to outperform the widely used RGB color space, especially when color anomaly detection is used for forest-like environments.