ir 
he 
by 
d, 
ge 
he 
he 
dy 
to 
[a 
nd 
he 
he 
)]; 
  
Margin ~~) 
Separating 
  
Support Vectors A 
Figure 3. Classification using support vectors and separating 
hyperplane (Meyer, 2001). Hollow and solid dots 
represent two classes in feature space. 
An optimum hyperplane is determined using a training dataset, 
and its generalization ability is verified using a validation 
dataset. Training vectors x; are projected into a higher 
dimensional space by the function ÿ . SVM finds a linear 
separating hyperplane with the maximal margin in this higher 
dimensional space. The methodology for SVM implementation 
are well described by Karatzoglou and Meyer (2006) and 
Kavzoglu and Colkesen (Kavzoglu and Colkesen, 2009). The 
study used a polynomial kernel and employed ‘one-against-one’ 
technique to allow multi-class classification. The SVM 
algorithm was implemented in R open-source software (Chang 
and Lin, 2001; Meyer, 2001) 
2.6 Training data collection 
Spatially diffuse training data sets covering the study area were 
collected for two crop seasons, summer 2010 and winter 2011. 
A global positioning system and a laptop computer were used to 
record the dominant vegetation species at particular roadside 
locations. Nearly 50% of the data points collected for each crop 
season was utilised for SVM modelling and remaining data sets 
were used for validation purposes. 
2.7 Selection of input variables 
Three shape-based parameters, twenty-three textural parameters 
and ten spectral parameters of the objects were analysed to 
determine the appropriate set of input variables for the SVM 
model. A combination of random forest variable importance 
measures (Breiman, 2001; Liaw and Wiener, 2002) and 
repeated classification accuracy assessment procedure was 
carried out for model reduction and the selection of input 
variables. Based on this analysis, the following variables (Table 
1) were chosen as input to SVM model. 
Table 1. Spectral and textural input variables selected for SVM 
  
  
  
modelling 
Variable name and formula References 
Textural parameters 
Grey level co-occurrence matrix (GLCM) (Trimble, 
Entropy 2010) 
N-1 
GLCM Entropy - 5 Pij(-In Pi, j) 
i,j=0 
i is the row number of the image 
j is the column number 
Pi,j is the normalised value in the cell i,j 
  
Vi jis the value in the cell i, j of the matrix 
N is the number or rows or columns 
  
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 
  
Vegetation indices 
Normalised Difference Index 4-7 
  
  
  
NDI47 = m — 5) 
B4+B7 
Normalized Difference Index 4-5 
NDI45 (S = = 
B4+B5 
Enhanced Vegetation Index (Huete et al., 
Ma a 2002) 
B4+CIxB3-C2xB1+L 
G-22.5, C126, C2=7.5 and L=1 
Modified Chlorophyll Absorption and (Daughtry et 
Reflectance Index al., 2000) 
MCARI - [(B4 - B3) - 0.2(B4 - 203 
Green Normalised Difference Vegetation (Gitelson and 
Index Merzlyak, 
GNDVI (E = 5) 1996) 
B4+B2 
  
Temporal spectral variables 
EVI-range (winter/summer crop season) 
EVI-minimum (winter/summer crop 
season) 
Other spectral variables 
Reflectance in Blue-Green (B1) 
Reflectance in Red (B3) 
Reflectance in Near Infrared (B4) 
Reflectance in Mid Infrared (B5) 
B indicates the band of Landsat data converted to exo- 
atmospheric reflectance. eg. B4 means band 4 as shown in 
Landsat hand book (NASA, 2011). 
3. RESULTS AND DISCUSSION 
Ground reference data collected (Section 2.6) for crop seasons 
summer 2010 and winter 2011 were analysed in conjunction 
with the spatial data variables described in Section 2.7. 
Random forest variable importance analysis showed that the 
range of EVI was the most influential variable. Temporal 
signatures of average EVI values derived for different classes 
during the crop season of summer 2011 are illustrated in Figure 
4. Areas of cropping consistently shows higher range of EVI 
values compared with bare soil or pasture, due to the spectral 
variations associated with the crop phenological changes during 
the crop season. 
| — Fallow 
0.8 eu 
7 || Cotton E 
9 ~~ Pasture £ 
06 - ——Sorghum | ^ i 
| LE es = 
|^ 05] ys ete 
G 04. 
0.3 1 
0.2 | 
0.1 1 
  
0+— Ed RO em ser dE AE 1 
Sep2010  Jan2011  Feb2011  Apr2011 
Figure 4. Temporal changes in mean EVI values for different 
classes during summer 2010 crop season derived 
from Landsat time series data 
Accuracy assessment clearly demonstrated the potential of 
SVM techniques for classification of the major classes (fallow, 
crop, pasture and woody). Overall classification accuracy for 
summer 2010 was 87% (k = 0.73)(Table 2) while that of winter 
2011 was 93% (k = 0.9) (0.