A novel dehazing model for remote sensing images. (July 2018)

• Record Type: Journal Article
• Authors: Singh, Dilbag; Kumar, Vijay
• Is Part Of: Computers & electrical engineering. Volume 69(2018)
• Page Start: 14
• Page End: 27
• Publication Date: 2018-07
• Subjects: Dehazing -- Gradient profile prior -- Gradient-based guided image filter -- Modified restoration model; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2018.05.015
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: The visibility of remote sensing images taken in poor environmental conditions is often degraded due to the occurrence of fog, haze, mist, and smog. To restore these images, many visibility restoration techniques have been developed. However, the existing techniques perform poorly to remove the effect of haze from remote sensing images with a complex background and large haze gradient. In this paper, a gradient profile prior is proposed to remove the haze from remote sensing images. The coarse estimated atmospheric veil has been refined by using gradient-based guided image filter. Moreover, the visibility restoration model has also been modified to overcome the over saturation and color distortion problems. Extensive experiments have shown that the proposed dehazing technique outperforms the existing image dehazing techniques. The proposed technique has significantly improved the spatial and radiometric information of remote sensing images.