Video dehazing without flicker artifacts using adaptive temporal average

In this paper we propose an effective video dehazing technique to reduce flicker artifacts by using adaptive temporal average. When applying a dehazing method for still image to a video sequence, flicker artifacts may occur because atmospheric values calculated independently for each frame change fr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Do Kyoung Shin, Yong Min Kim, Ki Tae Park, Dong-Seok Lee, Wonju Choi, Young Shik Moon
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper we propose an effective video dehazing technique to reduce flicker artifacts by using adaptive temporal average. When applying a dehazing method for still image to a video sequence, flicker artifacts may occur because atmospheric values calculated independently for each frame change frame by frame. In existing approaches flicker artifacts are reduced by yielding highly correlated transmission values between adjacent frames. However, since flickering artifacts can also be caused by atmospheric light values which frequently change in a video sequence, it is necessary to effectively calculate atmospheric light values considering the correlation between adjacent frames. In this paper, we propose an approach to calculating atmospheric light values based on adaptive temporal averaging between adjacent frames. Experimental results have shown that the proposed method achieves better performance of video dehazing with less flicker artifact than existing methods.
ISSN:0747-668X
2159-1423
DOI:10.1109/ISCE.2014.6884454