Deakin University
Browse

File(s) under permanent embargo

Single image dehazing algorithm based on sky region segmentation

conference contribution
posted on 2019-01-01, 00:00 authored by W Li, W Jie, Somaiyeh MahmoudZadeh
In this paper a hybrid image defogging approach based on region segmentation is proposed to address the dark channel priori algorithm’s shortcomings in de-fogging the sky regions. The preliminary stage of the proposed approach focuses on segmentation of sky and non-sky regions in a foggy image taking the advantageous of Meanshift and edge detection with embedded confidence. In the second stage, an improved dark channel priori algorithm is employed to defog the non-sky region. Ultimately, the sky area is processed by DehazeNet algorithm, which relies on deep learning Convolutional Neural Networks. The simulation results show that the proposed hybrid approach in this research addresses the problem of color distortion associated with sky regions in foggy images. The approach greatly improves the image quality indices including entropy information, visibility ratio of the edges, average gradient, and the saturation percentage with a very fast computation time, which is a good indication of the excellent performance of this model.

History

Event

Advanced Data Mining and Applications. International Conference (15th : 2019 : Dalian, China)

Volume

11888

Series

Advanced Data Mining and Applications International Conference

Pagination

489 - 500

Publisher

Springer

Location

Dalian, China

Place of publication

Cham, Switzerland

Start date

2019-11-21

End date

2019-11-23

ISSN

0302-9743

eISSN

1611-3349

ISBN-13

9783030352301

Language

eng

Publication classification

E1 Full written paper - refereed

Editor/Contributor(s)

J Li, S Wang, S Qin, X Li, S Wang

Title of proceedings

ADMA 2019 : Proceedings of the 15th International Conference on Advanced Data Mining and Applications

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC