vegetated areas and their "condition," and it remains the most
well-known and used index to detect live green plant canopies
in multispectral remote sensing data. Once the feasibility to
detect vegetation had been demonstrated, users tended to also
use the NDVI to quantify the photosynthetic capacity of plant
canopies. The NDVI is calculated from these individual
measurements as follows (NASA) :
NDVI = NIR —VIS
NIR - VIS
These spectral reflectances are themselves ratios of the reflected
over the incoming radiation in each spectral band individually;
hence they take on values between 0.0 and 1.0. By design, the
NDVI itself thus varies between -1.0 and +1.0. It should be
noted that NDVI is functionally, but not linearly, equivalent to
the simple infrared/red ratio (NIR/VIS).
There are many methods that can be used for image
segmentation. The NDVI is one of the most widely used indices
for differentiating between vegetation and non-vegetation areas
in remote sensing (ZHANG et al., 2006). For the NDVI, the
threshold for vegetation extraction is usually positive and near
to zero, it may vary from 0.05 to 0.15. Human supervision is
helpful for selecting the best threshold from typical imagery.
For our test data, non-vegetation areas are not well removed
with a threshold of 0.0, while many areas are falsely removed
with a threshold of 0.2. The best result is obtained with a
threshold of 0.1.
(D
2.2 Vegetation segment and removal of RGB image
In the traditional multispectral remote sensing which is
achieved by aeronautics and space platforms, the Red and Near-
infrared (NIR) bands. However, especially in the ground
platform, NIR band is little utilized by compute vision and
digital photogrammetry which usually only take RBG bands
into account. Therefore, it is important to recognize vegetation
occlusion in the ground close-range scene of buildings based on
visible light RGB images.
CIE L*a*b is very popular for image segmentation in computer
vision. This is based directly on CIE XYZ (1931) and is another
attempt to linearise the perceptibility of unit vector colour
differences. Again, it is non-linear, and the conversions are still
reversible. Colouring information is referred to the colour of the
white point of the system, subscript n. The non-linear
relationships for L* a* and b* are the same as for CIELUV and
are intended to mimic the logarithmic response of the eye (Ford
and Roberts, 1998).
Vihite
L* 100
7 Yellow
+b"
d
Black
L'sfü
Figure 1. Definition of CIE L*a*b
The CIELAB color scale is an approximately uniform color
scale. In a uniform color scale, the differences between points
plotted in the color space correspond to visual differences
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
between the colors plotted. The CIELAB color space is
organized in a cube form. The L* axis runs from top to bottom.
The maximum for L* is 100, which represents a perfect
reflecting diffuser. The minimum for L* is zero, which
represents black. The a* and b* axes have no specific numerical
limits. Positive a* is red. Negative a* is green. Positive b* is
yellow. Negative b* is blue. Figl is a diagram representing the
CIELAB color space (HunterLab, 2008).
The CIE XYZ colour space was presented by CIE in 1931 (SEII
2002). Three axes X, Y and Z are orthogonally defined by the
basic colours R, G and B (red, green and blue). Generally, only
points in the surface X+Y+Z=1 are considered. Each RGB point
can be transformed into colour space CIE XYZ as follows (SEII
2002):
X]| [0.412291 0.357664 0.180209] | R
Y |=| 0.212588 0.715329 0.072084 |-|G| ©)
Z | |0.019326 0.119221 0.949102 | | B
The component L represents the light Lightness with value from
0 to 100. The components a* and b* represent colour: a* varies
from green (with value -120) to red (with value + 120), b*
varies from blue (with value -120) to yellow (with value + 120).
Those can be written as:
Lz116-(/ Y Y^ —16 i£f0.008856 « (Y / Y,)
L=903.3-(Y/Y,) else 3)
a=500-(F(X/X,)-F@/Y,))
ba200-(F(Y /YM-F(2/2,)
Where (X, Y, Z) is the point to be converted, which can be
obtained from Eq. (2). Let p represents X/X,, Y/Y, and Z/Z,
respectively, then:
F(p)z p^ ifp>0.008856 @
F(p)27.787. p-16/116 else
(X, Y, Z, is the tristimulus values for the illuminant
(HunterLab, 2008), which is also called white point. Here
illuminant can be: X,,70.312779, Y,-0.329184 , Z, —0.358037
(ZHANG et al, 2006). Other parameters can be (Ford and
Roberts, 1998; HunterLab, 2008):
3
* É Jy 3
AL 7 sample ~ “standard
* * *
Aa = ample T C tandard
* * *
Ab zb, u^ (5)
sample standard
AE" =NAL? + Aa” + Ab”
AC = € ie i C ned
h,, = arctan(b' / a^)
Where:
C za 5"
+ A L* means sample is lighter or darker than standard; + À a*
means sample is redder or greener than standard; — ^ b* means
sample is yellower or bluer than standard
Many experiments have been carried out to compare the
performance of image segmentation between NDVI and CIE
L*a*b (ZHANG et al., 2006). So the CIE L*a*b approach is
used for vegetation segment and removal. Another reason is that
using CIE L*a*b, vegetation can also be extracted from visible
light RGB images because the component a* is negative for
vegetation in standard visible light RGB imagery and close to -
120 for green vegetation. To segment RGB imagery with CIE
L*a*b, a* from -0.15 to -0.05 should be applied as a threshold.
Th