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

facebooktwittermailshare

FAST NEAR INFRARED FUSION-BASED ADAPTIVE ENHANCEMENT OF VISIBLE

Abstract: 

Visible (VS) and near infra-red (NIR) band sensors provide digital
images that capture complementary spectral radiations from a
scene. Since NIR radiations propagate well through haze, mist, or
fog, the captured NIR image contains better scene details compared
to the VS image in such cases. However, NIR radiations are material
dependent and provide little information about color or texture of
the scene’s objects. To exploit the complementary details provided
by VS and NIR images, we propose a fusion approach that adaptively
injects missing spatial details to the VS image from the NIR
image while preserving the spectral contents of the VS image. The
spatial details are adaptively weighted based on the relative difference
between local contrasts of the NIR and the VS images. Thus,
the proposed approach prevents unnecessary modification of colors
or amplification of scene details that result in an unrealistic fused
image. Moreover, the proposed approach is non-iterative, fast with
a low complexity of O(n), and suitable to be implemented on embedded
cameras’ hardware. Experimental fusion results obtained on
natural NIR and VS image pairs show the effectiveness of the proposed
approach compared with two alternatives.

up
0 users have voted:

Paper Details

Authors:
Ahmed Elliethy, Hussein Aly
Submitted On:
10 November 2017 - 12:44pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Hussein A. Aly
Paper Code:
1351
Document Year:
2017
Cite

Document Files

presentation

(13 downloads)

Keywords

Additional Categories

Subscribe

[1] Ahmed Elliethy, Hussein Aly, "FAST NEAR INFRARED FUSION-BASED ADAPTIVE ENHANCEMENT OF VISIBLE", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2296. Accessed: Jan. 22, 2018.
@article{2296-17,
url = {http://sigport.org/2296},
author = {Ahmed Elliethy; Hussein Aly },
publisher = {IEEE SigPort},
title = {FAST NEAR INFRARED FUSION-BASED ADAPTIVE ENHANCEMENT OF VISIBLE},
year = {2017} }
TY - EJOUR
T1 - FAST NEAR INFRARED FUSION-BASED ADAPTIVE ENHANCEMENT OF VISIBLE
AU - Ahmed Elliethy; Hussein Aly
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2296
ER -
Ahmed Elliethy, Hussein Aly. (2017). FAST NEAR INFRARED FUSION-BASED ADAPTIVE ENHANCEMENT OF VISIBLE. IEEE SigPort. http://sigport.org/2296
Ahmed Elliethy, Hussein Aly, 2017. FAST NEAR INFRARED FUSION-BASED ADAPTIVE ENHANCEMENT OF VISIBLE. Available at: http://sigport.org/2296.
Ahmed Elliethy, Hussein Aly. (2017). "FAST NEAR INFRARED FUSION-BASED ADAPTIVE ENHANCEMENT OF VISIBLE." Web.
1. Ahmed Elliethy, Hussein Aly. FAST NEAR INFRARED FUSION-BASED ADAPTIVE ENHANCEMENT OF VISIBLE [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2296