Methods to evaluate the performance of segmentation algorithms for synthetic aperture radar (SAR) images are developed, based on known properties of coherent speckle and a scene model in which areas of constant backscatter coefficient are separated by abrupt edges. Local and global measures of segmentation homogeneity are derived and applied to the outputs of two segmentation algorithms developed for SAR data, one based on iterative edge detection and segment growing, the other based on global maximum a posteriori (MAP) estimation using simulated annealing. The quantitative statistically based measures appear consistent with visual impressions of the relative quality of the segmentations produced by the two algorithms. On simulated data meeting algorithm assumptions, both algorithms performed well but MAP methods appeared visually and measurably better. On real data, MAP estimation was markedly the better method and retained performance comparable to that on simulated data, while the performance of the other algorithm deteriorated sharply. Improvements in the performance measures will require a more realistic scene model and techniques to recognize oversegmentation.
Many emerging SAR applications require imagery which is multi-channel either in time, frequency or polarisation. If SAR segmentation algorithms are going to be of genuine utility they must be applicable to such datasets. Two approaches to multi-channel segmentation are considered: segmenting each channel separately and then recombining the results; and segmenting the multi-channel image as a single entity. In both cases segmentation is based on edge detection and segment growing. The utility of multi-channel segmentation for change detection, classification and analysing the information content of multi-channel data, is discussed. A multi-temporal ERS-1 image, and a multi-polarised, multi-frequency AIRSAR image of the same agricultural scene, are used for case studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.