Synthetic aperture radar river image segmentation using improved localizing region-based active contour model

Pattern Analysis and Applications - Tập 22 - Trang 731-746 - 2018
Kang Ni1, Yiquan Wu1,2
1School of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
2Key Laboratory of Port, Waterway and Sedimentation Engineering of the Ministry of Transport, Nanjing Hydraulic Research Institute, Nanjing, China

Tóm tắt

Adaptive localizing region-based active contour model driven by Laplacian kernel-based fitting energy is proposed for improving the efficiency and accuracy of synthetic aperture radar (SAR) river image segmentation in the paper. Defining regional energy functional that depends on the Laplacian kernel distance which is robust and non-Euclidean, Laplacian kernel distance is nonlinear transformation, whose transformed space can be linear classification. Additionally, providing the novel calculation for fitting center which relies on the local and global gray value, furthermore, the adaptive selection function of local radius is made. By using both of them, the proposed model can improve the accuracy of the fitting center and local region; afterward, the evolution of the curve can achieve the global optimal and be controlled better. Finally, in order to speed up the computation of proposed model, the localized region surrounded by adjacent four pixel points on the evolution curve can be replaced by the localized region of the intermediate pixel. The proposed model has been successfully applied to river channel extraction from synthetic aperture radar (SAR) images with desirable results. Comparisons with other state-of-the-art approaches demonstrate the great performances of the model.

Tài liệu tham khảo

Yu XS, Wu CD, Chen DY et al (2012) River detection in remote sensing image based on multi-feature fusion. J Nottheastern Univ Nat Sci 33(11):1547–1550 Wang C, Huang FC, Tang XB et al (2012) A river extraction algorithm for high-resolution SAR images with complex backgrounds. Remote Sense Technol Appl 27(4):516–522 Bharathi PT, Subashini P (2013) Texture based color segmentation for infrared river ice images using K-means clustering. In: 2013 International conference on signal processing, image processing and pattern recognition, 298–302 Zhao JJ, Yu H, Gu XG et al (2010) The edge detection of river model based on self-adaptive Canny Algorithm and connected domain segmentation. In: 2010 8th World congress on intelligent control and automation, 1333–1336 Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10(2):266–277 Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vision 1:321–331 Kim W, Kim C (2013) Active contours driven by the salient edge energy model. IEEE Trans Image Process 22(4):1667–1673 Dzyubachyk O, van Cappellen WA, Essers J et al (2010) Advanced level-set-based cell tracking in time-lapse fluorescence microscopy. IEEE Trans Med Imaging 29:852–867 Vasilevskiy A, Siddiqi K (2002) Flux maximizing geometric flows. IEEE Trans Pattern Anal Mach Intell 24(12):1565–1578 Li C, Kao C, Gore JC, Ding Z (2007) Implicit active contours driven by local binary fitting energy. In: IEEE conference on computer vision and pattern recognition, 1–7 Zhang K, Song H, Zhang L (2010) Active contours driven by local image fitting energy. Pattern Recogn 43(4):1199–1206 Li C, Kao CY, John G et al (2106) Minimization of region-scalable fitting energy for image Segmeatation. In: SAI computing conference, 255–263 Zheng Q, Dong E, Cao Z (2014) Active contour model driven by linear speed function for local segmentation with robust initialization and applications in MR brain images. Sig Process 97(4):117–133 Lankton S, Tannnenbaum A (2008) Localizing region-based active contours. IEEE Trans Image Process 17(11):2029–2039 Song Y, Wu YQ, Dai YM (2016) A new active contour remote sensing river image segmentation algorithm inspired from the cross entropy. Digit Signal Proc 48:322–332 Elisee IM, Juan GA, Arturo GP et al (2017) Localized active contour model with background intensity compensation applied on automatic MR brain tumor segmentation. Neurocomputing 220(S1):84–97 Huang C, Zeng L (2016) Level set evolution model for image segmentation based on variable exponent p-Laplace equation. Appl Math Model 40(S1):7739–7750 Niu S, Chen Q, Sisternes LD, Ji Z, Zhou Z (2017) Robust noise region-based active contour model via local similarity factor for image segmentation. Pattern Recogn 61(S1):104–119 Li XM, Wei WH, Fan YF (2016) Segmentation of brain tumor based on gaussian probability localizing local region active contour model. J Med Image Health Inf 6(7):1741–1745 Wang Y, Xiang S, Pan C, Wang L, Meng G (2013) Level set evolution with locally linear classification for image segmentation. Pattern Recogn 46(6):1734–1746 Zhang CC, Song ST, Wen XT et al (2015) Improved sparse decomposition based on a smoothed L0 norm using a Laplacian kernel to select features form fMRI data. J Neurosci Methods 245:15–24 Gao GG, Wen CL, Wang HB (2017) Fast and robust image segmentation with active contours and student’s-t mixture model. Pattern Recogn 63(S1):71–86 Li C, Huang R, Ding Z, Gatenby JC et al (2011) A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI. IEEE Trans Image Process 20(7):2007–2016 Li C, Xu C, Gui C, Fox MD (2010) Distance regularized level set evolution and its application to image segmentation. IEEE Trans Image Process 19(12):3243–3255 Dietenbeck T, Alessandrini M, Friboulet D et al (2010) A free software for the evaluation of image segmentation algorithms based on level-set. In: Proceedings of the IEEE international conference on image processing. 665–668