研究目的
To propose a novel superpixel segmentation method based on a new distance function and superpixel seed updating strategy for polarimetric synthetic aperture radar (PolSAR) images.
研究成果
The proposed method is effective and achieves a better tradeoff between boundary adherence and compactness. The main contribution includes a novel distance measure to control the superpixels in boundary adherence, homogeneity and compactness, and a new updating strategy of superpixel seeds based on Wishart distribution.
研究不足
The method may have high computational complexity and the generated superpixels may be irregular.
1：Experimental Design and Method Selection:
The proposed superpixel segmentation method is an adaption of k-means for superpixel generation, with a new distance measure and a new strategy to update the positions and intensities of superpixel seeds.
2：Sample Selection and Data Sources:
C-band RADARSAT-2 polarimetric SLC SAR images acquired over Fuzhou, China are used.
3：List of Experimental Equipment and Materials:
RADARSAT-2 data.
4：Experimental Procedures and Operational Workflow:
Initialize superpixel seeds with an expected number of superpixels, iteratively cluster the pixels based on the distance function, and update the superpixel seeds based on the updating strategy.
5：Data Analysis Methods:
The effectiveness of the proposed method is demonstrated by comparing with the SLIC algorithm and Ncut algorithm.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
