Comparative Study on Hyperspectral Image Enhancement for Low Illumination Outdoor Scenes Images

Lee Yong Quan, Rohana Abdul Karim, Nurul Wahidah Arshad, Nor Farizan Zakaria, Wan Nur Azhani Binti W. Samsudin, Yasmin Abdul Wahab, Adhi Harmoko Saputro

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

1 Citation (Scopus)

Abstract

Hyperspectral image is rich with information because it contains spatial and spectral properties of specific objects. However, the image quality may be affected by low lighting conditions caused by non-uniform illumination environments, uncontrollable weather, which tends to darken outdoor scenes. Difficulty arises for high order image processing modalities such as detection, classification and tracking. In this paper, a comparative study was conducted to identify the most appropriate enhancement method for outdoor scenes. Four techniques were investigated: Bio-Inspired Multi-Exposure Fusion (BIMEF), Dehazing, Illumination Estimation, and Multi-deviation Fusion (MF). Experiments revealed that BIMEF is the best approach with the lowest lightness of error.

Original languageEnglish
Title of host publicationProceedings of the 6th International Conference on Electrical, Control and Computer Engineering, InECCE 2021
EditorsZainah Md. Zain, Mohd. Herwan Sulaiman, Amir Izzani Mohamed, Mohd. Shafie Bakar, Mohd. Syakirin Ramli
PublisherSpringer Science and Business Media Deutschland GmbH
Pages773-784
Number of pages12
ISBN (Print)9789811686894
DOIs
Publication statusPublished - 2022
Event6th International Conference on Electrical, Control and Computer Engineering, InECCE 2021 - Kuantan, Malaysia
Duration: 23 Aug 202123 Aug 2021

Publication series

NameLecture Notes in Electrical Engineering
Volume842
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference6th International Conference on Electrical, Control and Computer Engineering, InECCE 2021
Country/TerritoryMalaysia
CityKuantan
Period23/08/2123/08/21

Keywords

  • Enhancement
  • Hyperspectral
  • Low illumination

Fingerprint

Dive into the research topics of 'Comparative Study on Hyperspectral Image Enhancement for Low Illumination Outdoor Scenes Images'. Together they form a unique fingerprint.

Cite this