Visibility restoration of single image captured in dust and haze weather conditions

• Published in: Multidimensional systems and signal processing Vol. 31; no. 2; pp. 619 - 633
• Main Authors: Yang, Yan, Zhang, Chen, Liu, Longlong, Chen, Gaoke, Yue, Hui
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.04.2020; Springer Nature B.V
• Subjects: Artificial Intelligence; Circuits and Systems; Color matching; Computer vision; Dust; Electrical Engineering; Engineering; Fog; Haze; Histograms; Image enhancement; Image transmission; Restoration; Signal,Image and Speech Processing; Visibility; Weather; Image dehazing; Optical compensation; Dark channel prior; Bad weather; Visibility restoration
• ISSN: 0923-6082; 1573-0824
• DOI: 10.1007/s11045-019-00678-z

Inclement weather existence of fog, haze, and dust generally degrades the visibility of outdoor images. Bad visibility may cause failure in computer vision applications. Existing dehazing methods cannot work well on dust haze images. Such images appear yellowish due to the absorption of blue light by dust particles. In order to solve this problem, we propose an optical compensation method (OCM), which uses histogram matching to change the RGB color channel. In this method, take the red channel as a reference curve and then fit the color curves of the blue and green channels close to the red curve, thereby dust haze images are transformed into haze images. Furthermore, we develop a novel single image dehazing method based on Gaussian adaptive transmission (GAT). GAT uses a Gaussian function with a linear coefficient constraint to optimize the transmission, which can prevent halo artifacts near edges of depth discontinuity and obtaining a more accurate estimate of the transmission, especially in bright areas (e.g., sky). The experimental results show that OCM can eliminate the color cast of dust haze images, and GAT can enhance the visibility of dust haze images effectively.