Detecting Changes in Polarimetric SAR Data with Content-Based Image Retrieval Matthieu Molinier ∗† , Jorma Laaksonen † , Yrj¨ o Rauste ∗ and Tuomas H¨ ame ∗ ∗ VTT Technical Research Centre of Finland, Digital Information Systems, Earth Observation Team, P.O. Box 1000, FI-02044 VTT, Finland - Email: matthieu.molinier@vtt.fi † Helsinki University of Technology, Adaptive Informatics Research Centre, P.O. Box 5400, FI-02015 HUT, Finland Abstract—In this study, we extended the potential of a Content- Based Image Retrieval (CBIR) system based on Self-Organizing Maps (SOMs), for the analysis of remote sensing data. A database was artificially created by splitting each image to be analyzed into small images (or imagelets). Content-based image retrieval was applied to fully polarimetric airborne SAR data, using a selection of polarimetric features. After training the system on this imagelet database, automatic queries could detect changes. Results were encouraging on airborne SAR data and may be more useful for spaceborne polarimetric data. I. I NTRODUCTION Two novel polarimetric SAR satellites, TerraSAR-X and RADARSAT-2, will be launched in 2007. In addition, ALOS has been launched in 2006 and is being taken into operative use. The immense amount of data generated by these satellite missions demands new approaches to manage it efficiently. There is a growing interest in the remote sensing community for Content-Based Image Retrieval (CBIR), which allows management of large image archives, as well as satellite image annotation and interpretation. Our work extends the potential of PicSOM [1], a CBIR system based on Self-Organizing Maps (SOMs) [2], for polari- metric SAR image analysis. The key idea of our study [3] is to artificially generate a database of small images – or imagelets – from each full satellite image to be analyzed. Imagelets can be extracted from one scene for the detection of man- made structures or other targets, or from two (or more) scenes to detect changes. In this paper we present our experiments on change detection in fully polarimetric SAR data using PicSOM. II. PRE- PROCESSING AND DATABASE PREPARATION Due to unavailability of fully-polarimetric spaceborne datasets suitable for change detection, polarimetric airborne data was considered. The data consists of 2 EMISAR single- look complex (SLC in scattering matrix format) scenes ac- quired in March and July 1995. The March scene was then registered to the July scene – details on the data can be found in [4]. 3-by-3 coherent averaging was applied to form 9-look images of 1280 × 1616 pixels, using PolSARPro software [5]. A scene is typically divided into several thousands of imagelets, so that PicSOM produces relevant indexing. By this operation, the number of target classes within an imagelet is reduced compared to the original full scene. The extracts were cut into 16 × 16 pixels small images, forming a database of 8080 imagelets per scene. For the purpose of method evaluation, a ground truth was created by classifying each scene into 5 classes {mountain, forest, water, ice, shadow} [4]. Supervised Wishart classifica- tion was used in PolSARPro, after delineating training areas over the Pauli decomposition RGB image. Lack of optical data for creating the ground truth resulted in reduced number of classes and classification reliability. III. FEATURES Features were extracted from the polarimetric SAR image- lets to allow their indexing by the Self-Organizing Maps. The original PicSOM features were developed for RGB optical images. They are standard low-level measures of texture and color information, not suitable for polarimetric SAR images. Table I sums up the features included into PicSOM for polarimetric data analysis. Four Touzi polarimetric discrimi- nators [6] were considered : R 0 max the maximum scattered intensity, NDR 0 the normalized difference of the scattered intensity, p max the maximum degree of polarization and Δp the dynamic range of the degree of polarization. The polar azimuthal polarimetric signature [7] presents several advan- tages over the original polarimetric signature [8], mainly the continuity of range in orientation angle, and a less ambiguous mapping of horizontally and vertically polarized targets. In addition, a coordinate feature was carried along the whole analysis process, both to keep track of the position of any imagelet within the full image, and to complete the framework for change detection. Table II lists the feature groups extracted from the imagelets, and their dimensionality. For all features except the polarimetric signature and xy- coordinates, the imagelets were divided into 4 quadrants, from which the basic features were extracted after averaging the coherency matrix. For example, an imagelet of 16 × 16 pixels was divided into 4 quadrants of 8 × 8 pixels, over which the coherency matrix was averaged before extracting the LOGRATIOS features – thus generating a feature vector of dimension 4 × 3 = 12. The copolarized and crosspolarized signatures were calculated on the average coherency matrix over a whole imagelet, then aggregated into a single 1444- dimension vector. 1-4244-1212-9/07/$25.00 ©2007 IEEE. 2390