Efficient airlight estimation for defogging

  • Yeejin Lee
  • , Changyoung Han
  • , Junseong Park
  • , Seungkyu Park
  • , Truong Q. Nguyen

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

1 Scopus citations

Abstract

This paper presents a new technique to efficiently estimate atmospheric light of visibility restoration algorithms from a hardware implementation perspective. The quality of defogged images depends on the accuracy of estimated atmospheric light, where it is typically estimated from the brightest portion of foggy images. In most existing algorithms, long execution time and large memory resources are required to find the largest intensity values on hardware platform. We explore an efficient method to measure atmospheric light by detecting sky region.

Original languageEnglish
Title of host publicationISOCC 2014 - International SoC Design Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages154-155
Number of pages2
ISBN (Electronic)9781479951260
DOIs
StatePublished - 16 Apr 2015
Event11th International SoC Design Conference, ISOCC 2014 - Jeju, Korea, Republic of
Duration: 3 Nov 20146 Nov 2014

Publication series

NameISOCC 2014 - International SoC Design Conference

Conference

Conference11th International SoC Design Conference, ISOCC 2014
Country/TerritoryKorea, Republic of
CityJeju
Period3/11/146/11/14

Keywords

  • advanced driver assistance systems
  • airligh estimation
  • defogging/dehazing
  • FPGA implementation
  • image enhancement/restoration

Fingerprint

Dive into the research topics of 'Efficient airlight estimation for defogging'. Together they form a unique fingerprint.

Cite this