Assessing thermal imagery integration into object detection methods on ground-based and air-based collection platforms

TL;DR

This paper evaluates the performance of fused RGB and thermal LWIR imagery for object detection on ground and air platforms, providing new benchmarks and a large labeled dataset for multispectral detection models.

Contribution

It introduces quantitative performance metrics for LWIR, RGB, and fused models, and presents a novel large dataset for multispectral object detection in diverse operational conditions.

Findings

RGB-LWIR fusion outperforms individual modalities with 98.4% mAP.

The fused model operates effectively during day and night.

A new dataset of 12,600 labeled images is provided for further research.

Abstract

Object detection models commonly deployed on uncrewed aerial systems (UAS) focus on identifying objects in the visible spectrum using Red-Green-Blue (RGB) imagery. However, there is growing interest in fusing RGB with thermal long wave infrared (LWIR) images to increase the performance of object detection machine learning (ML) models. Currently LWIR ML models have received less research attention, especially for both ground- and air-based platforms, leading to a lack of baseline performance metrics evaluating LWIR, RGB and LWIR-RGB fused object detection models. Therefore, this research contributes such quantitative metrics to the literature. The results found that the ground-based blended RGB-LWIR model exhibited superior performance compared to the RGB or LWIR approaches, achieving a mAP of 98.4%. Additionally, the blended RGB-LWIR model was also the only object detection model to work in both day and night conditions, providing superior operational capabilities. This research additionally contributes a novel labelled training dataset of 12,600 images for RGB, LWIR, and RGB-LWIR fused imagery, collected from ground-based and air-based platforms, enabling further multispectral machine-driven object detection research.