Thin Cloud Removal for Single RGB Aerial Image. (16th January 2021)

• Record Type: Journal Article
• Authors: Song, Chengfang; Xiao, Chunxia; Zhang, Yeting; Sui, Haigang
• Is Part Of: Computer graphics forum. Volume 40:Number 1(2021)
• Page Start: 398
• Page End: 409
• Publication Date: 2021-01-16
• Subjects: thin cloud removal -- image recovery -- aerial image -- computational photography; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.14196
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: Acquired above variable clouds, aerial images contain the components of ground reflection and cloud effect. Due to the non‐uniformity, clouds in aerial images are even harder to remove than haze in terrestrial images. This paper proposes a divide‐and‐conquer scheme to remove the thin translucent clouds in a single RGB aerial image. Based on colour attenuation prior, we design a kind of veiling metric that indicates the local concentration of clouds effectively. By this metric, an aerial image containing thickness‐varied clouds is segmented into multiple regions. Each region is veiled by clouds of nearly‐equal concentration, and hence subject to common assumptions, such as boundary constraint on transmission. The atmospheric light in each region is estimated by the modified local colour‐line model and composed into a spatially‐varying airlight map for the entire image. Then scene transmission is estimated and further refined by a weighted L 1 ‐norm based contextual regularization. Finally, we recover ground reflection via the atmospheric scattering model. We verify our cloud removal method on a number of aerial images containing thin clouds and compare our results with classical single‐image dehazing methods and the state‐of‐the‐art learning‐based declouding method, respectively. Abstract : Acquired above variable clouds, aerial images contain the components of ground reflection and cloud effect. Based on colour attenuation prior, this paper designs a novel veiling metric to indicate the local concentration of cloud, and proposes a divide‐and‐conquer scheme to recover the ground reflection of cloudy aerial images effectively.