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
Step 5: Eliminate the pixel with the distance larger than a predefined threshold to update D.
Some adaptive thresholding approach can be used. For simplicity, a percentage of the number of
the samples is used. For example, the largest 1% samples can be excluded.
Step 6: Iterate Step 2. to Step 4. until the dataset D doesn't change.
Step 7: After all the clustered classes are performed, the pixels excluded in each clustered class
are labeled as the anomaly targets.
Experiments and anslysis
Experiments on real-world hyperspectral images have been done to evaluate our proposed
method, including air-born hyperspectral remote sensing images and near scene hyperspectral
images. Five rows of panels distribute in the scene and considered as anomalies, shown in Fig.2 .
Several state of art methods are used as comparison ones. Our method iterates 5 times until the
results keep stable. Preliminary experiments results with AVIRIS hyperspectral images are shown
in Fig. 3. It is obvious that our proposed method did best among all the methods. Considering the
mixed boundary anomaly pixels, the performances of different methods for different kinds of
anomalies are also presented in Table I, which further reveal that the improvement of our method
is partly due to the superior performance on the transition boundary pixels.
1.04
$ oe
He
$
= 0.8. ras
a Serene
% 07 io
=
2 083 — eec Dov€-RX
2 mm | EON
E 05 | —S-— Proposed method
oa i ; :
0 2 4 6 8 10
Number of False Alarms
Fig. 2. Target panels in the AVIRIS image. Fig. 3. Performances of different methods.
Table.1 Number of detected anomalies under minimized false alarms
Methods Proposed RX K-RX BACON
Method
Number of Boundary
13 4 6 7
anomaly pixels detected
