Abstract

Synthetic Aperture Radar (SAR) images are useful for a wide variety of applications that involves environmental monitoring of vegetation, agriculture, forests, surface water and management of natural resources. Major issue faced by SAR images is speckle which complicates the interpretation of images. Existing speckle filtering algorithms are used to reduce the speckle without any loss of information. Quantitative analysis helps in the selection of effective speckle reduction filter. Mean, Standard deviation and Equivalent Number of Looks (ENL) are considered as a parameters for quantitative analysis. Evaluation of mean, standard deviation and ENL is primarily based on the selection of homogeneous area which is routinely done by manual method. In the process of manual selection, homogeneous region is selected manually and therefore some heterogeneous pixels may be introduced, which cannot be seen by human eyes. Therefore, in this paper, we are proposing a method for automated selection of homogeneous area using region growing approach for SAR image. Once homogeneous area is automatically selected, we have evaluated ENL for different speckle reducing filters. Results show that the use of the proposed method gives more accurate estimate of ENL than the values calculated by manual selection of homogeneous area. This region growing based novel approach is an automated procedure that gives precise homogeneous area and accurate value for ENL. Thus it helps in selecting best speckle reduction filter which ultimately helps in correct interpretation of the SAR image.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.