Marjan Teheri; MahmodReza Sahebi; Mehrnoosh Omati
Abstract
Synthetic aperture radar (SAR) sensors with various properties offer potential in various remote sensing applications, such as land cover and land use segmentation. Despite the two independent approaches of region-based segmentation and boundary-based segmentation, it isn't easy to obtain satisfactory ...
Read More
Synthetic aperture radar (SAR) sensors with various properties offer potential in various remote sensing applications, such as land cover and land use segmentation. Despite the two independent approaches of region-based segmentation and boundary-based segmentation, it isn't easy to obtain satisfactory results if either process is used in SAR images. In contrast, complementary information can be obtained using both region-based and boundary-based segmentation methods, removing existing limitations and improving results.In this research, with the help of polarimetric SAR images, a new segmentation method is presented, aiming to improve segmentation results by combining the two region-based and boundary-based approaches. From the set of superpixel methods, the Felzenszwalb method as a proposed region-based algorithm is compared with Quickshift and SLIC methods. The proposed method was able to prevent over-segmentation of the image and significantly increased the efficiency of segmentation analysis. Also, as the proposed method of boundary-based segmentation, Shannon entropy has considerably preserved the boundaries of the image segmentation compared to the two gradient-based methods, Canny and Laplacian. Comparison of the results of this method with reference data shows the total error of 10.39% and 11.25% for the first and second-time images, respectively. Compared to the performance of the other two methods, the absolute error has been decreased to 5.81% and 9.73% in the first image, and 11.16% and 13.86% in the second image, respectively. Finally, as a significant achievement of this research, integrating the two proposed segmentation algorithms improves the accuracy of polarimetric image segmentation.