Assessing thermal imagery integration into object detection methods on ground-based and air-based collection platforms
It provides baseline performance metrics and a dataset for multispectral object detection, addressing a gap for applications like surveillance or monitoring, but is incremental in nature.
This research tackled the problem of object detection in thermal and visible spectra by evaluating fused RGB-LWIR models on ground- and air-based platforms, finding that a ground-based blended model achieved a mAP of 98.4% and worked in both day and night conditions.
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.