Underwater image and video dehazing with pure haze region segmentation

作者：

Highlights：

• A semantic white-balancing approach for illuminant estimation that uses the dominant colour of the water is proposed.

• Pure haze regions are segmented and only slightly dehazed to avoid artefacts in these regions.

• Underwater image quality metrics are often biased by dehazed images that contain artefacts and false colours.

摘要

•A semantic white-balancing approach for illuminant estimation that uses the dominant colour of the water is proposed.•Pure haze regions are segmented and only slightly dehazed to avoid artefacts in these regions.•Underwater image quality metrics are often biased by dehazed images that contain artefacts and false colours.

论文关键词：Dehazing,Image processing,Segmentation,Underwater,White balancing,Video processing

论文评审过程：Received 14 February 2017, Revised 19 May 2017, Accepted 15 August 2017, Available online 24 August 2017, Version of Record 19 March 2018.

论文官网地址：https://doi.org/10.1016/j.cviu.2017.08.003