English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning identification models have shown promise for identifying gasplumes in Longwave IR hyperspectral images of urban scenes, particularly when alarge library of gases are being considered. Because many gases have similarspectral signatures, it is important to properly estimate the signal from adetected plume. Typically, a scene's global mean spectrum and covariance matrixare estimated to whiten the plume's signal, which removes the background'ssignature from the gas signature. However, urban scenes can have many differentbackground materials that are spatially and spectrally heterogeneous. This canlead to poor identification performance when the global background estimate isnot representative of a given local background material. We use imagesegmentation, along with an iterative background estimation algorithm, tocreate local estimates for the various background materials that resideunderneath a gas plume. Our method outperforms global background estimation ona set of simulated and real gas plumes. This method shows promise in increasingdeep learning identification confidence, while being simple and easy to tunewhen considering diverse plumes.

Local Background Estimation for Improved Gas Plume Identification in Hyperspectral Images