Vegetation often exists as patch in arid and semi-arid region throughout the world. Vegetation patch can be effectively
monitored by remote sensing images. However, not all satellite platforms are suitable to study quasi-circular vegetation
patch. This study compares fine (GF-1) and coarse (CBERS-04) resolution platforms, specifically focusing on the quasicircular
vegetation patches in the Yellow River Delta (YRD), China. Vegetation patch features (area, shape) were
extracted from GF-1 and CBERS-04 imagery using unsupervised classifier (K-Means) and object-oriented approach
(Example-based feature extraction with SVM classifier) in order to analyze vegetation patterns. These features were then
compared using vector overlay and differencing, and the Root Mean Squared Error (RMSE) was used to determine if the
mapped vegetation patches were significantly different. Regardless of K-Means or Example-based feature extraction
with SVM classification, it was found that the area of quasi-circular vegetation patches from visual interpretation from
QuickBird image (ground truth data) was greater than that from both of GF-1 and CBERS-04, and the number of patches
detected from GF-1 data was more than that of CBERS-04 image. It was seen that without expert’s experience and
professional training on object-oriented approach, K-Means was better than example-based feature extraction with SVM
for detecting the patch. It indicated that CBERS-04 could be used to detect the patch with area of more than 300 m2, but
GF-1 data was a sufficient source for patch detection in the YRD. However, in the future, finer resolution platforms such
as Worldview are needed to gain more detailed insight on patch structures and components and formation mechanism.
|