Threat recognition in complex environments: Gated viewer images fused with thermal ir images and an introduction of contextual dimming
conference paper
The defense and security community have to cope with threats in complex environments that are merged in the scene context. The aim of this study is to investigate if fusion of Gated Viewer images with traditional thermal IR images provides a solution for threat recognition (with context understanding) in complex environments; and if contextual dimming of the background (based on important information) improves threat recognition. An Image Quality Metric is used to select a fusion method. Contextual dimming is compared to global (uniformly) and local (object boundary) dimming methods. A Dimming Quality Metric is designed in order to define the preferred amount of dimming. The metrics are validated through human observer experiments. In this study we find that a simple pixel based weighted fusion scheme already provides improved threat recognition. We also find that contextual dimming improves this even more
Topics
TNO Identifier
574787
Source title
Vol OPTRO-2014-2966218
Pages
1-12
Files
To receive the publication files, please send an e-mail request to TNO Repository.