Journal of Remote Sensing & GIS

Urban change detection method of multi-temporal remote sensing images

World Congress on GIS & Remote Sensing

August 01-03, 2016 New Orleans, Louisiana, USA

V V Hnatushenko , V V Vasiliev, and M V Polyakov

Oles Honchar Dnipropetrovsk National University, Ukraine
EOS Data Analytics Ukraine
Noosphere, USA

Posters & Accepted Abstracts: J Remote Sensing & GIS

Abstract:

Change detection analyses, describes and quantifies differences between images of the same scene at different times. Change detection is a complex phenomenon which includes different procedures such as identifying the specific change detection problem, image preprocessing and variables and algorithm selection for the computations. The widely used methods for highresolution image change detection rely on textural/structural features. However, these spatial features always produce highdimensional data space since they are related to a series of parameters. Moreover, the current urban change detection methods are totally reliant on visual interpretation. This article presents a new automatic change detection method of multi-temporal remote sensing high-resolution images and visual interpretation of results. To detect changes, we apply a series of algorithms, which were independent of each other: Subpixel registration of multi-temporal images, spectral classification (building masks), singling-out of the most informative stripes and threshold segmenting, morphological filtering and object classification, vectorization and calculation of parameters and visualization of the changes on the map. The candidate changed areas were obtained based on spatial mask filtering, spectral differences, searching for spectral-temporal anomalies, morphological technique and a shadow detection method to identify the real changes. Experiments were conducted on the multi-temporal Pleiades images. Experimental results showed that the proposed method can effectively and quickly extract the changing urban area between the two temporal optical remote sensing images of high spatial resolution. Compared with other change detection methods, the proposed method reduces the effect of classification and segmentation on the change detection accuracy.

Biography :

In 1994 V.Hnatushenko graduated from the Dnipropetrovsk college of automation and telemechanics in Machine with CNC and robotic systems. In 1999, he received a M.S. degree in Technology and Telecommunications from Dnipropetrovsk National University, Ukraine. Volodymyr Hnatushenko has completed his PhD in 2003 and postdoctoral studies from Dnipropetrovsk National University. In 2006 - docent, 2009 - Doctor of Sciences, 2011 – Full Professor. He is the head of the automated data processing systems department at the Oles Honchar Dnepropetrovsk National University, Ukraine. He has supervised to completion 7 research PhD. He has published more than 200 papers in reputed journals.

Email: vvgnatush@gmail.com