A Likelihood-Based SLIC Superpixel Algorithm for SAR Images Using Generalized Gamma Distribution

Huanxin Zou; Xianxiang Qin; Shilin Zhou; Kefeng Ji
July 2016
Sensors (14248220);Jul2016, Vol. 16 Issue 7, p1107
Academic Journal
The simple linear iterative clustering (SLIC) method is a recently proposed popular superpixel algorithm. However, this method may generate bad superpixels for synthetic aperture radar (SAR) images due to effects of speckle and the large dynamic range of pixel intensity. In this paper, an improved SLIC algorithm for SAR images is proposed. This algorithm exploits the likelihood information of SAR image pixel clusters. Specifically, a local clustering scheme combining intensity similarity with spatial proximity is proposed. Additionally, for post-processing, a local edge-evolving scheme that combines spatial context and likelihood information is introduced as an alternative to the connected components algorithm. To estimate the likelihood information of SAR image clusters, we incorporated a generalized gamma distribution (GÃD). Finally, the superiority of the proposed algorithm was validated using both simulated and real-world SAR images.


Related Articles

  • Research on Image Saliency Detection Model Based on Calculating the Probability of Objectness Likelihood. Chao Ji; Huiying Liu; Jingfeng Sun; Sheng He // Applied Mechanics & Materials;2014, Issue 536-537, p141 

    This paper introduces a novel plausible model on the probability of saliency objectness likelihood based on superpixels to dectect image saliency. Firstly, analysing factors which affect the size of visual attention; And then use the SLIC algorithm to divide image into N superpixels; Next,...

  • 基于 SLIC 与条件随机场的图像分割算法. 孙巍; 郭敏 // Application Research of Computers / Jisuanji Yingyong Yanjiu;Dec2015, Vol. 32 Issue 12, p3817 

    The stage of estimating parameter and inferencing model in conditional random field (CRF) has a high time complexity. To improve this problem, this paper introduced the conception of simple linear interactive clustering (SLIC) method into the CRF model, and proposed a SLIC-based CRF image...

  • 整合超像元分割和峰值密度的高光谱图像聚类. 于文博; 王忠勇; 李山山; 孙旭 // Journal of Image & Graphics;Oct2016, Vol. 21 Issue 10, p1402 

    Objective Traditional clustering algorithm usually utilizes more spectrum than spatial information, which is susceptible to noise interference. In this study, we propose a hyperspectral image clustering algorithm based on simple linear iterative clustering (SLIC) and density peaks (DP) to solve...

  • Color Constancy using Superpixel. Xingsheng Yuan; Zhengzhi Wang // World Academy of Science, Engineering & Technology;2012, Issue 64, p499 

    Color constancy algorithms are generally based on the simplified assumption about the spectral distribution or the reflection attributes of the scene surface. However, in reality, these assumptions are too restrictive. The methodology is proposed to extend existing algorithm to applying color...

  • Shadow-based Building Detection and Segmentation in High-resolution Remote Sensing Image. Dongyue Chen; Shibo Shang; Chengdong Wu // Journal of Multimedia;Jan2014, Vol. 9 Issue 1, p181 

    This paper proposes an effective method to extract buildings in high-resolution remote sensing images based on shadow detection. Firstly, a superpixel segmentation algorithm called SLIC is introduced to split the input image into homogeneous patches. LDA-based color features of the patches are...

  • AN APPROACH FOR SUPERPIXELS USING UNIFORM SEGMENTATION AND RECIPROCAL NEAREST NEIGHBORS CLUSTERING. JUNRUI LV // Journal of Theoretical & Applied Information Technology;1/31/2013, Vol. 47 Issue 3, p1032 

    An approach using uniform segmentation and reciprocal nearest neighbours (RNN) clustering is presented to generate superpixels. The method is made of two steps. First, image is segmented to a large number of regular homogeneous small regions which are similar to cell. Second, instead of the...

  • 基于SLIC区域分割的三维地形重建算法. 常方媛; 冯志勇; 徐超 // Computer Engineering & Science / Jisuanji Gongcheng yu Kexue;Sep2015, Vol. 37 Issue 9, p1718 

    Most traditional 3D terrain reconstruction algorithms cannot represent the accurate structure of the terrain and are time consuming as well,thus the technological development is seriously hindered. In order to realize the 3D terrain reconstruction accurately by using pictures taken by...

  • 基于图像分割的三维点云深度值合成. 黄訸; 黄山 // Application Research of Computers / Jisuanji Yingyong Yanjiu;Oct2015, Vol. 32 Issue 10, p3168 

    Aiming at the poor performance of using traditional computer vision based methods to reconstruct complicated objects,this paper proposed a depth synthesis algorithm based on segmentation of input images. The algorithm over-segmented input images into a set of superpixels in nearly the same shape...

  • A Fast Superpixel Segmentation Algorithm for PolSAR Images Based on Edge Refinement and Revised Wishart Distance. Yue Zhang; Huanxin Zou; Tiancheng Luo; Xianxiang Qin; Shilin Zhou; Kefeng Ji // Sensors (14248220);Oct2016, Vol. 16 Issue 10, p1687 

    The superpixel segmentation algorithm, as a preprocessing technique, should show good performance in fast segmentation speed, accurate boundary adherence and homogeneous regularity. A fast superpixel segmentation algorithm by iterative edge refinement (IER) works well on optical images. However,...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics