Shadow regions detection algorithm by adaptive narrowband two-phase Chan-Vese model  

作　　者：WANG Xingmei YIN Guisheng LIU Guangyu LIU Zhipeng WANG Xiaowei 

机构地区：[1]College of Computer Science and Technology,Harbin Engineering University [2]College of Shipbuilding Engineering,Harbin Engineering University

出　　处：《Chinese Journal of Acoustics》2016年第3期292-308,共17页声学学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(41306086);Technology Innovation Talent Special Foundation of Harbin(2014RFQXJ105);the Fundamental Research Funds for the Central Universities(HEUCF100606)

摘　　要：An adaptive narrowband two-phase Chan-Vese （ANBCV） model is proposed for improving the shadow regions detection performance of sonar images. In the first noise smoothing step, the anisotropic second-order neighborhood MRF （Markov Random Field, MRF） is used to describe the image texture feature parameters. Then, initial two-class segmentation is processed with the block mode k-means clustering algorithm, to estimate the approximate position of the shadow regions. On this basis, the zero level set function is adaptively initialized by the approximate position of shadow regions. ANBCV model is provided to complete local optimization for eliminating the image global interference and obtaining more accurate results. Experimental results show that the new algorithm can efficiently remove partial noise, increase detection speed and accuracy, and with less human intervention.An adaptive narrowband two-phase Chan-Vese （ANBCV） model is proposed for improving the shadow regions detection performance of sonar images. In the first noise smoothing step, the anisotropic second-order neighborhood MRF （Markov Random Field, MRF） is used to describe the image texture feature parameters. Then, initial two-class segmentation is processed with the block mode k-means clustering algorithm, to estimate the approximate position of the shadow regions. On this basis, the zero level set function is adaptively initialized by the approximate position of shadow regions. ANBCV model is provided to complete local optimization for eliminating the image global interference and obtaining more accurate results. Experimental results show that the new algorithm can efficiently remove partial noise, increase detection speed and accuracy, and with less human intervention.

关 键 词：MRF Shadow regions detection algorithm by adaptive narrowband two-phase Chan-Vese model 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]