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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Aerial images are often degraded by space-varying motion blur andsimultaneous uneven illumination. To recover high-quality aerial image from itsnon-uniform version, we propose a novel patch-wise restoration approach basedon a key observation that the degree of blurring is inevitably affected by theilluminated conditions. A non-local Retinex model is developed to accuratelyestimate the reflectance component from the degraded aerial image. Thereafterthe uneven illumination is corrected well. And then non-uniform coupledblurring in the enhanced reflectance image is alleviated and transformedtowards uniform distribution, which will facilitate the subsequent deblurring.For constructing the multi-scale sparsified regularizer, the discrete shearlettransform is improved to better represent anisotropic image features in term ofdirectional sensitivity and selectivity. In addition, a new adaptive variant oftotal generalized variation is proposed for the structure-preservingregularizer. These complementary regularizers are elegantly integrated into anobjective function. The final deblurred image with uniform illumination can beextracted by applying the fast alternating direction scheme to solve thederived function. The experimental results demonstrate that our algorithm cannot only remove both the space-varying illumination and motion blur in theaerial image effectively but also recover the abundant details of aerial sceneswith top-level objective and subjective quality, and outperforms otherstate-of-the-art restoration methods.

Blind restoration for non-uniform aerial images using non-local Retinex model and shearlet-based higher-order regularization