Linear features for automatic registration and reliable change detection of multi-source imagery

摘要

Change detection analysis usually involves multi-spectral, multi-source and/or multi-resolution imagery that has been captured at different times. Accurate co-registration of these datasets is a prerequisite step for a reliable change detection procedure. This paper introduces a new approach for automatic image registration using the Modified Iterated Hough Transform (MIHT) and linear features, which have been chosen since they can be reliably extracted from imagery with varying geometric and radiometric properties. Finally, edge detection and subtraction of the registered images are used as the basis for the change-detection procedure. Experimental results from real data proved the feasibility of the suggested approach.View full textDownload full textKeywordschange detection, automatic registration, linear features, matching, multi-source imageryRelated var addthis_config = { ui_cobrand: "Taylor & Francis Online", services_compact: "citeulike,netvibes,twitter,technorati,delicious,linkedin,facebook,stumbleupon,digg,google,more", pubid: "ra-4dff56cd6bb1830b" }; Add to shortlist Link Permalink http://dx.doi.org/10.1080/14498596.2012.686430