a Unified
ilysis and
id Cover
onditional
E Geosci.
] Science
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B3, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
MULTI TIMES IMAGES FUSION BASED ON WAVELET THEORY
S. Rokhsari*, A. Abed-Elmdoust 5, M. Karimi *
* GIS Division, Department of Surveying and Geomatic Eng, College of Eng., University of Tehran, Iran -
so_rokhsari@yahoo.com
"Research Associate, School of Civil ‚College of Eng., University of Tehran, Iran-armaghanabed@ut.ac.ir
“Department of Surveying and Geomatic Eng., Shahid Rajaee university, Tehran, Iran-raha@yahoo.com
Commission VI, WG VI/4
KEY WORDS: Traffic camera, Image fusion, Wavelet.
ABSTRACT
The development of new monitoring systems and the increasing interest of researchers in obtaining reliable measurements have
leaded to the development of automatic monitoring moving objects. One way to ensure monitoring object is to use multi time’s
image fusion. Image fusion is a sub area of the more general topic of data fusion. Image fusion can be roughly defined as the process
of combining multiple input images into an image, which contains the ‘relevant’ information from the inputs. The aim of image
fusion is to integrate complementary and redundant information from multiple images to create a composite that contains a better
fused image than any of the individual source images. Main purpose of the former is to increase both the spectral and spatial
resolution of images by combining multiple images.
In this paper we tried to use this theory for moving object tracking, so with the usage of multi images that are obtained in different
times and combination of them with this theory we identify the path of movement of moving object so this result could help us to
implement automatic systems that that could monitor objects automatically without human interventation.
So in this paper first we will discuss the principal of fusion and its famous method (wavelet theory) and all process that involved for
doing a fusion process.
1. INTRODUCTION Tracking moving object
A lot of low and high level image processing algorithms have to | |
be developed to meet all the requirements of an intelligent
monitoring system. The performance of the system will depend
; va : ; ; different times
on the reliable recognition of moving object, their adequate
description and the knowledge of how to combine these -
P ; [Image preparation
parameters with information from other sources to solve the MEE
problems of monitoring objects.
So here we want to use image fusion method to identify
movement path of a moving object so for doing this process we
Selection of best form of
used steps like below:
-Image acquisition in different times and preparation of them
wavelet
: s Selection of level of
Finally section.4 will show the result of fusion so fusion result decomposition
will show us the path of moving object so the result could us to
In this step we obtained images in different times so these
sequence images will show the movement of object in different
monitoring moving obj ects Identification of path of
Figure.1 shows the steps of process for multi images fusion for more
tracking moving object
times then we tried to prepare them so in section.] and 2 we
discussed the principal of fusion for tracking moving object and
in section.2 I discussed the steps such as registration and
sampling and histogram matching for preparation of input
images.
-Using the best method for multi images fusion
For fusion of multi images we used wavelet theory as an
important theory for multi image fusion for tracking moving
object, so saection.3 will demonstrates the principal of fusion
theory for integration of multi images and section.4
demonstrates the principal of famous methods for fusion.
Figure.1: The steps of process for multi images fusion for
tracking moving object
