Single image dehazing with bright object handling

• Published in: IET computer vision Vol. 10; no. 8; pp. 817 - 827
• Main Authors: Riaz, Irfan, Fan, Xue, Shin, Hyunchul
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.12.2016; Wiley
• Subjects: Benchmarking; block-level haze thickness estimation; bright surface intensity value; bright-object handling capability; Channels; dark channel prior; DCP; DCP failure categorisation; Failure; haloes reduction; Handling; Haze; image fusion; image resolution; image restoration; local average haziness value; Luminous intensity; nonobvious failure; obvious failure; pixel-level haze thickness estimation; reliability map; reliability-guided fusion; Research Article; single image dehazing; Strategy; transmission estimation; transmission value; bright-object handling capability; transmission value; reliability-guided fusion; image fusion; DCP failure categorisation; dark channel prior; haloes reduction; block-level haze thickness estimation; single image dehazing; nonobvious failure; local average haziness value; DCP; pixel-level haze thickness estimation; image restoration; obvious failure; transmission estimation; image resolution; reliability map; bright surface intensity value
• ISSN: 1751-9632; 1751-9640; 1751-9640
• DOI: 10.1049/iet-cvi.2015.0451

This study addresses the shortcomings of the dark channel prior (DCP). The authors propose a new and efficient method for transmission estimation with bright-object handling capability. Based on the intensity value of a bright surface, they categorise DCP failures into two types: (i) obvious failure: occurs on surfaces that are brighter than ambient light. They show that, for these surfaces, altering the transmission value proportional to the brightness is better than the thresholding strategy; (ii) non-obvious failure: occurs on surfaces that are brighter than the neighbourhood average haziness value. Based on the observation that the transmission of a surface is loosely connected to its neighbours, the local average haziness value is used to recompute the transmission of such surfaces. This twofold strategy produces a better estimate of block and pixel-level haze thickness than DCP. To reduce haloes, a reliability map of block-level haze is generated. Then, via reliability-guided fusion of block- and pixel-level haze values, a high-quality refined transmission is obtained. Experimental results show that the authors’ method competes well with state-of-the-art methods in typical benchmark images while outperforming these methods in more challenging scenarios. The authors’ proposed reliability-guided fusion technique is about 60 times faster than other well-known DCP-based approaches.