|
Multi-temporal Change Detection for SAR Imagery
Presented at EUROPTO (Florence, Italy) 1999.
Cite this paper as:
Chris Oliver, Ian McConnell and Douglas Corr,
`Multi-temporal change detection for SAR imagery',
in SAR Image Analysis, Modelling and Techniques II,
edited by F. Posa,
Proc. SPIE 3869 (1999) pp55-66.
Abstract
This paper describes an optimised approach to identifying changes within a
sequence of ESR images of Heathrow airport.
We show that joint annealed segmentation avoids the false detections
encountered along the edges of structural features when detecting differences
between segmented scenes.
This leads to an optimised change detection process, which can be applied
in the detection of aircraft and vehicles around the airfield, even though
the resolution of ERS images is only 25m (range) by 6.25m (azimuth).
In addition, we show how joint segmentation of the coherence image between
pairs of 35-day repeats yields an appreciable improvement in a false colour
change representation based on two amplitude images and their coherence
image.
- (no PostScript available)
|
|
|
