D d
, NH,
re and
ope
cipal
yonent
Ie.
UM V UM € wm
Heights (NH, calculated from the difference between the DSM
and the DTM data). Other auxiliary image data (bands) are
created to be used in the classification process. The auxiliary
bands are: the texture from the intensity data, and the slope
from both the DSM and the NH.
Several images are produced by combining two or more of the
created bands. The image band combinations can be
summarized as follows: bands of a) intensity and elevation, b)
intensity, elevation and texture, c) intensity, elevation, texture,
and slop.
The principal components are also created from the existing
four bands to reduce the number of existing bands by
eliminating the correlated ones. The classification analysis
includes both datasets; the one created directly from the original
LiDAR data (range and intensity), and the auxiliary datasets
extracted from the original data. Figure 1 illustrates the work
flow of the data preparation step.
2.2 Data Classification and Evaluation
The second part of the study work covers the classification
process and the classification assessment of the results. The
Maximum Likelihood classifier, as a supervised classification
algorithm, is used with the bands created directly from the
LiDAR data, and with the six band combinations mentioned
above. The classification and evaluation is repeated for bands
created from the PCA. The classification processes for all
datasets (different band combinations) are summarized as
follows:
1) Training signatures are identified for four different classes
(trees, grass, buildings, and roads).
2) Statistical assessments of the training signatures are done and
further enhancement to the selection of the training areas are
taken place, if required.
3) Maximum Likelihood algorithm is applied and the image
data is classified into the corresponding classes.
4) Assessment the results of the classification using ground
truth data and by performing evaluation using error matrix. The
classification process is evaluated using about 1000 reference
points, for each study area, that are randomly selected from the
original point cloud data to avoid the effect of the interpolation
on the accuracy of the ground truth. The well-distributed points
over the study area are randomly generated. The ground truth
information is collected from the ortho-rectefied aerial photo
provided with the LiDAR data. Finally, the accuracies achieved
from classification results of the different band combinations
are compared.
3. STUDY AREA AND DATA SETS
3.1 Study Area
A study area is chosen, which covers a part of the British
Columbia Institute of Technology (BCIT) located in the
Burnaby, British Columbia, Canada (122?59' W, 49?15"N). An
area of 500 m x 400 m is selected for the experimental work
because it contains a variety of the land cover features on the
ground including; buildings, parking areas, trees and open
spaces with grassy coverage, (Figure 2 ).
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B7, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
Figure 2: Study Area (British Colombia Institute of Technology,
Vancouver)
3.2 Data Sets
A Leica ALS50 sensor operating in 1.064 um wavelength and
0.33 mrad beam divergence is used for the LiDAR acquisition
mission on July 17, 2009 at local time 14:55. The flying height
for this mission was around 600m. The data acquired contains a
3D point cloud (x, y, and z coordinates) and linearized intensity
values (I) for each point.
c d
Figure 3: a) Geometrically Calibrated and Radiometrically
corrected Intensity Image, b) DSM, c) NH, and d) Ortho-rectified
Aerial Photo
The provided dataset for this experimental work is: an Ortho-
rectified aerial photo for the study area, and geometrically
calibrated and radiometrically corrected LiDAR data (including
x, y, z and I), the aerial photo is acquired at the same time of the
LiDAR data acquisition mission. The related geometrical
calibration and radiometrical correction works are illustrated in
Yan et. al. (2012). The LiDAR data (intensity and rang) are
converted to raster image with pixel size equals to 20 cm to
produce the intensity image and the DSM. The LIDAR points
fell on the ground are separated, and a DTM is produced using
these points with the same pixel size of 20 cm. The difference