You are using an outdated browser that does not fully support the intranda viewer.
As a result, some pages may not be displayed correctly.

We recommend you use one of the following browsers:

Full text

Fusion of sensor data, knowledge sources and algorithms for extraction and classification of topographic objects
Baltsavias, Emmanuel P.

te, 1999
International Archives of Photogrammetry and Remote Sensing, Vol. 32, Part 7-4-3 W6, Valladolid, Spain, 3-4 June, 1999
: number of
raging, when
deviation of
tosen. Each
with the
multi spectral
tg technique,
: differences
ission of the
the variation
; the objects
vith a high
illage left of
n the fused
•mation that
the spectral
ime of the
onfirms the
sification of
ied with the
r pattern of
ixel objects,
i a different
3ns did not
ctral image,
i some areas
w much the
y the fusion
image once
identical as
stimated by
i of and the
the original
le degraded
a 5x5 filter
iresents the
ges and the
;an (p.) and
bands. The
ilues of the
n the mean
ed. This is
rocess. IHS
values and
from the
latic image,
le standard
Fig. 2. Comparison of Fusion techniques, (a) original multispectral image, (b) panchromatic image,
(c) result of AIF. (d) result of IHS merging. (© Euromap 1997)
(a) (b) (c)
Fig. 3. Multispectral classification based on (a) original image, (b) AIF image, and (c) IHS image.