Publication
Statistics of Infrared Images
Abstract
The proliferation of low-cost infrared cameras gives us a new angle for attacking many unsolved vision problems by leveraging a larger range of the electromagnetic spectrum. A first step to utilizing these images is to explore the statistics of infrared images and compare them to the corresponding statistics in the visible spectrum. In this paper, we analyze the power spectra as well as the marginal and joint wavelet coefficient distributions of datasets of indoor and outdoor images. We note that infrared images have noticeably less texture indoors where temperatures are more homogenous. The joint wavelet statistics also show strong correlation between object boundaries in IR and visible images, leading to high potential for vision applications using a combined statistical model.
Download publicationRelated Resources
See what’s new.
2012
A Classification of Opening Posts in Commercial Software Help ForumsThe opening posts in software help forums reflect the users’…
2010
On discrete Killing vector fields and patterns on surfacesSymmetry is one of the most important properties of a shape, unifying…
2014
Corticomotor Excitability of Arm Muscles Modulates According to Static Position and Orientation of the Upper LimbOBJECTIVE: We investigated how multi-joint changes in upper limb…
2013
A Practical Investigation into Achieving Bio-Plausibility in Evo-Devo Neural Microcircuits Feasible in an FPGAMany researchers has conjectured, argued, or in some cases…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us