MODIS image with an integral number of scale factors. The preprocessed image was
used to extract the land-cover classification map, which was used as the ground truth
in this MODIS experiment, by utilizing SVM.
17.4.2.2 Experiment Results
In this study, the scale factor S was set to 8; therefore, the subpixel resolution is
31.25 m. Since the original resolution of the soft classification images is
250 m  250 m and the average width of farmlands in our study area is around
100 m, this study sets the moving window factor w to 2 so that the moving window is
about 2 times the size of the original pixel and the current subpixel is always at the
center of the moving window. Soft classification images are used as inputs to the
SPM algorithms of ISAM, SPSAM, MSPSAM, and MSAM, which are developed
with ENVI IDL 8.3. Taking Landsat classification results as reference images, the
accuracies of SPM results are calculated. The SPM from different SAM algorithms
are displayed in Fig. 17.16, and the accuracy measures are shown in Table 17.5.
By making a visual assessment of SPM maps in Fig. 17.16, it can be found that
the SPM map from ISAM contains more details than those from other SAMs. For
instance, the details within the red rectangular areas in the SPM Map from ISAM
match the same areas in the reference map much better than those from other SAMs.
Table 17.5 shows that the OA of the SPM results from ISAM is 82.44%, which is
higher than those of other SAMs, and κ is 0.66, which is higher than that of SPSAM
and is equal to those of MSPSAM and MSAM. From both a visual assessment and
quantitative analysis, it can be concluded that ISAM is more effective than other
SAMs in SPM.
The comparison results of computational efficiency among ISAM, SPSAM,
MSPSAM, and MSAM are shown in Table 17.6. Among the four SAMs, SPSAM
is the most efficient SPM technique, while ISAM is the second most efficient one.
Comparing ISAM with SPAM, OA and κ increase by 12.22% and 0.2, respectively, in the experiment with MOIDS (though the accuracies of ISAM increase
slightly, compared with SPSAM, and MSPSAM and MSAM in the experiment with
Landsat). Therefore, ISAM can improve SPM accuracies more than SPSAM and is a
more efficient SPM technique than MSPSAM and MSAM.
17.5 Conclusion
Mapping and monitoring large-scale PML from satellite imagery is important both
scientifically and socio-economically. The decision-tree classifier, the threshold
model, and four types of spatial attraction models (SPSAM, MSPSAM, MSAM,
and ISAM) were analyzed and used to extract PML information. The experiment
results show that they are effective methods to map transparent PML over a large
geographic region with Landsat/MODIS images.
380
L. Lu
used to extract the land-cover classification map, which was used as the ground truth
in this MODIS experiment, by utilizing SVM.
17.4.2.2 Experiment Results
In this study, the scale factor S was set to 8; therefore, the subpixel resolution is
31.25 m. Since the original resolution of the soft classification images is
250 m  250 m and the average width of farmlands in our study area is around
100 m, this study sets the moving window factor w to 2 so that the moving window is
about 2 times the size of the original pixel and the current subpixel is always at the
center of the moving window. Soft classification images are used as inputs to the
SPM algorithms of ISAM, SPSAM, MSPSAM, and MSAM, which are developed
with ENVI IDL 8.3. Taking Landsat classification results as reference images, the
accuracies of SPM results are calculated. The SPM from different SAM algorithms
are displayed in Fig. 17.16, and the accuracy measures are shown in Table 17.5.
By making a visual assessment of SPM maps in Fig. 17.16, it can be found that
the SPM map from ISAM contains more details than those from other SAMs. For
instance, the details within the red rectangular areas in the SPM Map from ISAM
match the same areas in the reference map much better than those from other SAMs.
Table 17.5 shows that the OA of the SPM results from ISAM is 82.44%, which is
higher than those of other SAMs, and κ is 0.66, which is higher than that of SPSAM
and is equal to those of MSPSAM and MSAM. From both a visual assessment and
quantitative analysis, it can be concluded that ISAM is more effective than other
SAMs in SPM.
The comparison results of computational efficiency among ISAM, SPSAM,
MSPSAM, and MSAM are shown in Table 17.6. Among the four SAMs, SPSAM
is the most efficient SPM technique, while ISAM is the second most efficient one.
Comparing ISAM with SPAM, OA and κ increase by 12.22% and 0.2, respectively, in the experiment with MOIDS (though the accuracies of ISAM increase
slightly, compared with SPSAM, and MSPSAM and MSAM in the experiment with
Landsat). Therefore, ISAM can improve SPM accuracies more than SPSAM and is a
more efficient SPM technique than MSPSAM and MSAM.
17.5 Conclusion
Mapping and monitoring large-scale PML from satellite imagery is important both
scientifically and socio-economically. The decision-tree classifier, the threshold
model, and four types of spatial attraction models (SPSAM, MSPSAM, MSAM,
and ISAM) were analyzed and used to extract PML information. The experiment
results show that they are effective methods to map transparent PML over a large
geographic region with Landsat/MODIS images.
380
L. Lu