论文信息 - Building Extraction of SAR Images Using Morphological Attribute Profiles

Building Extraction of SAR Images Using Morphological Attribute Profiles

A building extraction method is proposed in this chapter used to deal with the special situation of SAR images processing. Morphological attribute profiles (APs) are the generalization of the recently proposed method morphological profiles (MPs). APs extract a multilevel characterization of an image by sequential application of morphological attribute filters. According to the type of the attributes considered in the morphological attribute transformation, different parametric features can be modeled. Here, the method proposed above is used for building extraction of SAR images. SVMs (Support vector machines) are used for classifications at last. The experimental analysis proved the usefulness of Aps in modeling the spatial information present in the image.

[1] Pierre Soille,et al. Morphological Image Analysis: Principles and Applications , 2003 .

[2] Jon Atli Benediktsson,et al. Morphological Attribute Profiles for the Analysis of Very High Resolution Images , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[3] Jon Atli Benediktsson,et al. Morphological attribute filters for the analysis of very high resolution remote sensing images , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[4] Pierre Soille,et al. Advances in mathematical morphology applied to geoscience and remote sensing , 2002, IEEE Trans. Geosci. Remote. Sens..

[5] Jon Atli Benediktsson,et al. A new approach for the morphological segmentation of high-resolution satellite imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[6] Johannes R. Sveinsson,et al. Classification of hyperspectral data from urban areas based on extended morphological profiles , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[7] Paul Wintz,et al. Digital image processing (2nd ed.) , 1987 .

[8] Jon Atli Benediktsson,et al. Classification and feature extraction for remote sensing images from urban areas based on morphological transformations , 2003, IEEE Trans. Geosci. Remote. Sens..