Lena Chang

Learn More
The advances of sensor technologies and the benefits of studying high dimensional spectral images make use of a growing number of spectral bands. High-dimensional remote sensing datasets obtained from multispectral, hyperspectral or even ultraspectral bands generally provide enormous spectral information for data analysis. It covers an abundance of(More)
Keywords: Oil spills SAR image Image segmentation Generalizes likelihood ratio test (GLRT) Constant false alarm ratio (CFAR) a b s t r a c t In the study, we propose a fast region-based method for the detection of oil spills in SAR images. The proposed method combines the image segmentation technique and conventional detection theory to improve the accuracy(More)
Recently, due to the advancement of remote sensors, optical remote sensing has been a significant increase in the number of spectral bands in acquired data, going from multispectral to hyperspectral. Hyperspectral imagery with hundreds of bands offers high spectral resolution and provides the potential accuracy in detection and classification of targets(More)
State-of-the-art sensor technology makes use of an increasing number of spectral bands. Although high volumes of remote sensing images are continuously being acquired and archived, existing methods have been proven inadequate for analyzing such large volumes of data. Besides, the demands for higher classification accuracy of remote sensing images have also(More)