Search

The increasing amount and resolution of satellite sensors demand new techniques for browsing remote sensing image archives. Content-based querying allows an efficient retrieval of images based on the information they contain, rather than their acquisition date or geographical extent. Self-organizing maps (SOMs) have been successfully applied in the PicSOM system to content-based image retrieval in databases of conventional images. In this paper, we investigate and extend the potential of PicSOM for the analysis of remote sensing data. We propose methods for detecting man-made structures, as well as supervised and unsupervised change detection, based on the same framework. In this paper, a database was artificially created by splitting each satellite image to be analyzed into small images. After training the PicSOM on this imagelet database, both interactive and off-line queries were made to detect man-made structures, as well as changes between two very high resolution images from different years. Experimental results were both evaluated quantitatively and discussed qualitatively, and suggest that this new approach is suitable for analyzing very high resolution optical satellite imagery. Possible applications of this work include interactive detection of man-made structures or supervised monitoring of sensitive sites. Index Terms--Change detection, content-based information retrieval, high-resolution optical satellite images, man-made structure detection, self-organizing maps (SOMs).

Landslides in Malaysia, and other tropical countries where heavy monsoon rains are common, form a risk to people, buildings, and roads. In particular, steep slopes that have been cut to accommodate road lines are prone to landslides. The objective of the study was to develop algorithms and methods that can be used to alert on increased risk of landslides through detecting small signs of slope instability with synthetic aperture radar (SAR) image analysis. A time series of 19 scenes from the TerraSAR-X satellite was analyzed in study site Gunung Pass. Amplitude image analysis and interferometric techniques were applied to study soil movements. Two terrace fragments were measured to have slid 2.5 and 4.9 m in two amplitude images. The phase of topography-flattened coherence images was used to map small movements in a slope-failure area. The highest movement that was detected with interferometric techniques was 1.71 cm while the corresponding movement in ground data was 2.65 cm. High soil movements (over 16 cm) in the slope failure area prevented the use of phase data because fringes disappeared. [ABSTRACT FROM PUBLISHER]

The paper presents a method based on two phase sampling and applicable to forest inventories. The first phase estimates are obtained from satellite imagery and, if required, from extra material such as maps. Second phase estimates are measured in the field. The method is flexible and also applicable to compartmentwise forest inventories. The experiments were based on six study areas with 439 relascope plots. The correlation coefficients between first and second stage estimates varied largely according to the study area. The PDF includes a summary in Finnish.