Multi-Threshold Technique for Segmentation of Satellite Imagery for Feature Extraction

Pair Features Overlapping Analysis
The pair features overlapping analysis algorithm can be described in figure 3. In this analysis, 12 logical expressions are used to do the overlapping analysis of the range of Min to Max grey value for a pair of features in one band. The algorithm shown that expression 1 to 8 can be used to extract threshold values and 9 to 12 are no threshold values can be extracted. This algorithm works by overlapping analysis to the one feature ( i, k ) with another feature ( j, k ) in one band k, where, ( i ) ¹ ( j ). After completed analysis in band k, the analysis repeat again for another band k + 1 until running through all bands k = m.

>

Figure 3. Pair features overlapping analysis algorithm

Threshold Values Selection Program
The threshold values selection program is used for optimal threshold values selection after pair features overlapping analysis. The algorithm is shown in figure 4.





This algorithm can be used to automatic selected the optimal threshold values for each features and the results are shows in table 2. The result shows that threshold values for urban feature (i=1) can be extracted from band 1, 2, and 3 excepted bands 4, 5 and 6. But for water feature (i=4) is opposite condition with urban feature band 4, 5 and 6 provided threshold values and band 1, 2 and 3 no threshold values can be selected. Clear land feature (i=2) threshold value can be extracted from band 1 to 6. Finally, band 1, 2, 3, 5 and 6 can be used to select the optimal threshold value for forest feature (i=3).

Page 2 of 3
| Previous | Next |