Automatic recovery of the atmospheric light in hazy images

Matan Sulami, Itamar Glatzer, Raanan Fattal, Mike Werman

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

216 Scopus citations

Abstract

Most image dehazing algorithms require, for their operation, the atmospheric light vector, A, which describes the ambient light in the scene. Existing methods either rely on user input or follow error-prone assumptions such as the gray-world assumption. In this paper we present a new automatic method for recovering the atmospheric light vector in hazy scenes given a single input image. The method first recovers the vector's orientation, Â = A//A//, by exploiting the abundance of small image patches in which the scene transmission and surface albedo are approximately constant. We derive a reduced formation model that describes the distribution of the pixels inside such patches as lines in RGB space and show how these lines are used for robustly extracting Â. We show that the magnitude of the atmospheric light vector, kAk, cannot be recovered using patches of constant transmission. We also show that errors in its estimation results in dehazed images that suffer from brightness biases that depend on the transmission level. This dependency implies that the biases are highly-correlated with the scene and are therefore hard to detect via local image analysis. We address this challenging problem by exploiting a global regularity which we observe in hazy images where the intensity level of the brightest pixels is approximately independent of their transmission value. To exploit this property we derive an analytic expression for the dependence that a wrong magnitude introduces and recover kAk by minimizing this particular type of dependence. We validate the assumptions of our method through a number of experiments as well as evaluate the expected accuracy at which our procedure estimates A as function of the transmission in the scene. Results show a more successful recovery of the atmospheric light vector compared to existing procedures.

Original languageAmerican English
Title of host publication2014 IEEE International Conference on Computational Photography, ICCP 2014
PublisherIEEE Computer Society
ISBN (Print)9781479951888
DOIs
StatePublished - 2014
Event2014 6th IEEE International Conference on Computational Photography, ICCP 2014 - Santa Clara, CA, United States
Duration: 2 May 20144 May 2014

Publication series

Name2014 IEEE International Conference on Computational Photography, ICCP 2014

Conference

Conference2014 6th IEEE International Conference on Computational Photography, ICCP 2014
Country/TerritoryUnited States
CitySanta Clara, CA
Period2/05/144/05/14

Fingerprint

Dive into the research topics of 'Automatic recovery of the atmospheric light in hazy images'. Together they form a unique fingerprint.

Cite this