Title :
Automatic detection of burned areas in wetlands by remote sensing multitemporal images
Author :
Capella Zanotta, Daniel ; Zani, Hiran ; Shimabukuro, Yosio E.
Author_Institution :
Nat. Inst. for Space Res., São José dos Campos, Brazil
Abstract :
In this paper, a methodology for automatic detection of burned areas is suggested. The classification criterion is performed using Bayesian statistical parameter (mean and covariance matrix) extracted automatically using the Expectation Maximization algorithm and taking into account the spectral similarity between burned and flooded areas. In this work the final process involves the application of morphological operators of erosion and dilation of images in order to insert information from the spatial context, refining the final map. Experiments were conducted to a TM-Landsat scene with areas affected by fires and seasonal flooding. The results show that the accuracy is increased with the consideration of flooding mask and the subsequent application of spatial context, reaching values up to 97% of accuracy when compared with a reference map.
Keywords :
Bayes methods; covariance matrices; erosion; expectation-maximisation algorithm; floods; geophysical image processing; image classification; statistical analysis; terrain mapping; wetlands; Bayesian statistical parameter; TM-Landsat scene; automatic detection; burned areas; classification criterion; covariance matrix; erosion; expectation maximization algorithm; flooded areas; flooding mask; image dilation; morphological operators; reference map; remote sensing multitemporal images; seasonal flooding; spatial context; spectral similarity; wetlands; Accuracy; Bayes methods; Classification algorithms; Context; Fires; Floods; Remote sensing; Land surface change; Optical imagery; Pattern recognition;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2013 IEEE International
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4799-1114-1
DOI :
10.1109/IGARSS.2013.6723191