Abstract: Sea ice floe segmentation is an import topic in remote sensing.Due to the large high-resolution remotely sensed sea ice image,the simple linear iterative clustering(SLIC) algorithm is used to construct superpixel blocks,which can capture image redundancy and greatly reduce the complexity of subsequent image processing tasks.Although SLIC can generate super-pixel blocks with regular and uniform shapes,but there are still some problems to be used in sea ice floe segmentation.For example,the initial seed points of the algorithm are sensitive to noise,the segmentation accuracy is not high and the running speed is not very quick.Therefore,an improved SLIC combining clustering algorithm is proposed to segment high-resolution remote sensing sea ice image.Aiming at the problem of noise sensitivity,anisotropic diffusion filtering is used to preprocess the image to ensure the integrity of the image while removing noise.Then the L-p norm is used to substitute and expand the traditional Euclidean distance in the SLIC algorithm.Finally,on the basis of SLIC superpixel block,DBSCAN and K-Means clustering algorithms are separately used to precisely segment the sea ice images,and the optimal result is obtained through performance comparison.Experiments show that the improved SLIC combined with K-Means segmentation method is better than Markov tandom field(MRF) algorithm and the improved SLIC combined with DBSCAN.It can obtain quite good segmentation results.

Key words: Image segmentation, Anisotropic diffusion filter, K-Means clustering, DBSCAN clustering, L-P norm, MRF algorithm