Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A VIDEO DEHAZING SYSTEM BASED ON FAST AIRLIGHT ESTIMATION

Abstract: 

An efficient video dehazing system based on the dark channel prior (DCP) is proposed. For the proposed system, the original DCP-based dehazing method is modified in order to achieve a fast execution of the airlight estimation without noticeable degradation of the dehazing quality. The proposed system is implemented in a heterogeneous multi-processor system-on-chip, for which the overall dehazing process is described in OpenCL and synthesized into the custom circuitry targeting an FPGA. In average, the execution time of the overall dehazing is reduced by 41.3% by the fast execution of the airlight estimation when compared to that of the system based on the original method while the dehazing quality is maintained.

up
0 users have voted:

Paper Details

Authors:
Tae-Hwan Kim
Submitted On:
9 November 2017 - 10:27pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Yongmin Park
Paper Code:
#1584
Document Year:
2017
Cite

Document Files

GlobalSIP 2017 presentation.pdf

(82 downloads)

Subscribe

[1] Tae-Hwan Kim, "A VIDEO DEHAZING SYSTEM BASED ON FAST AIRLIGHT ESTIMATION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2281. Accessed: Jul. 23, 2018.
@article{2281-17,
url = {http://sigport.org/2281},
author = {Tae-Hwan Kim },
publisher = {IEEE SigPort},
title = {A VIDEO DEHAZING SYSTEM BASED ON FAST AIRLIGHT ESTIMATION},
year = {2017} }
TY - EJOUR
T1 - A VIDEO DEHAZING SYSTEM BASED ON FAST AIRLIGHT ESTIMATION
AU - Tae-Hwan Kim
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2281
ER -
Tae-Hwan Kim. (2017). A VIDEO DEHAZING SYSTEM BASED ON FAST AIRLIGHT ESTIMATION. IEEE SigPort. http://sigport.org/2281
Tae-Hwan Kim, 2017. A VIDEO DEHAZING SYSTEM BASED ON FAST AIRLIGHT ESTIMATION. Available at: http://sigport.org/2281.
Tae-Hwan Kim. (2017). "A VIDEO DEHAZING SYSTEM BASED ON FAST AIRLIGHT ESTIMATION." Web.
1. Tae-Hwan Kim. A VIDEO DEHAZING SYSTEM BASED ON FAST AIRLIGHT ESTIMATION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2281