首页 > 论文 > 激光与光电子学进展 > 57卷 > 4期(pp:41018--1)

结合卷积受限玻尔兹曼机的CV图像分割模型

CV Image Segmentation Model Combining Convolutional Restricted Boltzmann Machine

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

传统图像分割方法主要依赖图像光谱、纹理等底层特征,容易受到图像中遮挡和阴影等的干扰。为此,提出一种基于卷积受限玻尔兹曼机的CV(Chan-Vest)图像分割模型,采用生成式模型——卷积受限玻尔兹曼机对目标形状建模并生成目标形状,以此为先验信息对CV模型能量函数增加目标全局形状特征约束,指导图像分割。在训练数据有限、目标形态各异、目标尺度变化较大的遥感影像数据集Satellite-2000和Vaihigen的目标分割中取得了理想的结果。

Abstract

Traditional image segmentation methods mainly rely on the low-level features, such as image spectrum and texture, and are easily disturbed by occlusion and shadow. To address these problems, a CV (Chan-Vest) image segmentation model combining the convolutional restricted Boltzmann machine is proposed. The target shape a priori information is modeled and generated using the convolutional restricted Boltzmann machine. Then the energy function of the CV model is constrained by the added a priori shape term to guide image segmentation. Better segmentation results are obtained in remote sensing datasets Satellite-2000 and Vaihigen, whose training data are limited while target shapes and sizes are different.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:P315.69

DOI:10.3788/LOP57.041018

所属栏目:图像处理

基金项目:国家自然科学基金;

收稿日期:2019-07-29

修改稿日期:2019-09-27

网络出版日期:2020-02-01

作者单位    点击查看

李晓慧:陕西师范大学计算机科学学院, 陕西 西安 710119
汪西莉:陕西师范大学计算机科学学院, 陕西 西安 710119

联系人作者:汪西莉(wangxili@snnu.edu.cn)

备注:国家自然科学基金;

【1】Que H Y, Huang H X, Xu J M. Road edge detection based on dual-threshold SSDA template matching [J]. Remote Sensing for Land & Resources. 2014, 26(4): 29-33.
阙昊懿, 黄辉先, 徐建闽. 基于双阈值SSDA模板匹配的遥感图像道路边缘检测研究 [J]. 国土资源遥感. 2014, 26(4): 29-33.

【2】Xu Q Y, Li Y, Lin W J, et al. Remote sensing image segmentation based on information clustering [J]. Journal of China University of Mining & Technology. 2017, 46(1): 209-214.
徐秋晔, 李玉, 林文杰, 等. 基于信息聚类的遥感图像分割 [J]. 中国矿业大学学报. 2017, 46(1): 209-214.

【3】Li J F, Wen Z Q, Hu Y X, et al. Road extraction from remote sensing images based on improved regional growth [J]. Computer Engineering and Applications. 2016, 52(2): 209-213, 238.
李建飞, 文志强, 胡永祥, 等. 基于改进区域生长的遥感影像道路提取 [J]. 计算机工程与应用. 2016, 52(2): 209-213, 238.

【4】Lang W H, Shen Y, Ang A, et al. Segmentation of SAR sea ice image based on region splitting and adaptive refinement process [J]. Journal of Remote Sensing. 2015, 19(5): 864-872.
郎文辉, 沈杨, 昂安, 等. 带有区域分裂自适应细化过程的SAR海冰图像分割 [J]. 遥感学报. 2015, 19(5): 864-872.

【5】Guo J, Jiang J, Cao S X. Automatic building segmentation from remote sensing images using multi-layer level set framework [J]. Infrared and Laser Engineering. 2014, 43(4): 1332-1337.
郭靖, 江洁, 曹世翔. 水平集分层分割遥感图像中的建筑物 [J]. 红外与激光工程. 2014, 43(4): 1332-1337.

【6】Shi G M, Suo J D, Huang C, et al. Remote sensing image edge-detection based on improved Canny operator [J]. Journal of Dalian Jiaotong University. 2015, 36(3): 87-90, 108.
石桂名, 索继东, 黄超, 等. 基于改进Canny算子的遥感图像边缘检测 [J]. 大连交通大学学报. 2015, 36(3): 87-90, 108.

【7】Tan Y, Huang H X, Xu J M, et al. Road edge detection from remote sensing image based on improved Sobel operator [J]. Remote Sensing for Land & Resources. 2016, 28(3): 7-11.
谭媛, 黄辉先, 徐建闽, 等. 基于改进Sobel算子的遥感图像道路边缘检测方法 [J]. 国土资源遥感. 2016, 28(3): 7-11.

【8】Dai J D, Liu Y D, Mao X Y, et al. Registration based on NSCT-domain FAST corner detection for infrared and visible images of electrical equipment [J]. Electrical Measurement & Instrumentation. 2019, 56(1): 108-114.
戴进墩, 刘亚东, 毛先胤, 等. 基于NSCT域FAST角点检测的电气设备红外与可见光图像配准 [J]. 电测与仪表. 2019, 56(1): 108-114.

【9】Yao H B, Bian J W, Cong J W, et al. Medical image segmentation model based on local sparse shape representation [J]. Laser & Optoelectronics Progress. 2018, 55(5): 051011.
姚红兵, 卞锦文, 丛嘉伟, 等. 基于局部稀疏形状表示的医学图像分割模型 [J]. 激光与光电子学进展. 2018, 55(5): 051011.

【10】Wang B, Gao X B, Li J, et al. A level set method with shape priors by using locality preserving projections [J]. Neurocomputing. 2015, 170: 188-200.

【11】Amberg B, Vetter T. Optimal landmark detection using shape models and branch and bound . [C]∥2011 International Conference on Computer Vision, November 6-13, 2011, Barcelona, Spain. New York: IEEE. 2011, 455-462.

【12】Tan G H, Hou J, Han Y P, et al. Low-parameter real-time image segmentation algorithm based on convolutional neural network [J]. Laser & Optoelectronics Progress. 2019, 56(9): 091003.
谭光鸿, 侯进, 韩雁鹏, 等. 基于卷积神经网络的低参数量实时图像分割算法 [J]. 激光与光电子学进展. 2019, 56(9): 091003.

【13】Pei L, Liu Y, Tan H, et al. Cloud detection of ZY-3 satellite remote sensing images based on improved fully convolutional neural networks [J]. Laser & Optoelectronics Progress. 2019, 56(5): 052801.
裴亮, 刘阳, 谭海, 等. 基于改进的全卷积神经网络的资源三号遥感影像云检测 [J]. 激光与光电子学进展. 2019, 56(5): 052801.

【14】Zhou M F, Wang X L, Wang L, et al. Convolutional neural network models for high spatial resolution satellite imagery classification [J]. Journal of Image and Graphics. 2017, 22(7): 996-1007.
周明非, 汪西莉, 王磊, 等. 高分辨卫星图像卷积神经网络分类模型 [J]. 中国图象图形学报. 2017, 22(7): 996-1007.

【15】Gerke M. Use of the stair vision library within the ISPRS 2D semantic labeling benchmark (Vaihingen)[R] . Netherlands: University of Twente. 2014.

【16】Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets [J]. Neural Computation. 2006, 18(7): 1527-1554.

【17】Salakhutdinov R, Hinton G E. Deep Boltzmann machines[C]∥Proceedings of the 12th International Conference on Artificial Intelligence and Statistics, April 16-18, 2009, Clearwater Beach, Florida, USA. USA: , 2009, 448-455.

【18】Norouzi M, Ranjbar M, Mori G. Stacks of convolutional Restricted Boltzmann Machines for shift-invariant feature learning . [C]∥2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami, FL, USA. New York: IEEE. 2009, 2735-2742.

【19】Salakhutdinov R. Learning deep generative models [J]. Annual Review of Statistics and Its Application. 2015, 2(1): 361-385.

【20】Hinton G E. Training products of experts by minimizing contrastive divergence [J]. Neural Computation. 2002, 14(8): 1771-1800.

【21】Gibbs sampling[J/OL]. -01-01) https:∥www.researchgate.net/publication/259088117_Markov_Chain_Monte_Carlo_and_Gibbs_ [2019-07-28]. Sampling. 2004.

【22】Li C M, Xu C Y, Gui C F, et al. Distance regularized level set evolution and its application to image segmentation [J]. IEEE Transactions on Image Processing. 2010, 19(12): 3243-3254.

【23】Chan T F, Sandberg B Y, Vese L A. Active contours without edges for vector-valued images [J]. Journal of Visual Communication and Image Representation. 2000, 11(2): 130-141.

【24】Li X, Zhao F, Guo Y. Conditional restricted Boltzmann machines for multi-label learning with incomplete labels[C]∥Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS)2015, May 9-12, 2015, San Diego, CA, USA. USA: , 2015, 635-643.

【25】Zhang J, Wang X L, Yang J G. Shape modeling method based on deep learning [J]. Chinese Journal of Computers. 2018, 41(1): 132-144.
张娟, 汪西莉, 杨建功. 基于深度学习的形状建模方法 [J]. 计算机学报. 2018, 41(1): 132-144.

引用该论文

Li Xiaohui,Wang Xili. CV Image Segmentation Model Combining Convolutional Restricted Boltzmann Machine[J]. Laser & Optoelectronics Progress, 2020, 57(4): 041018

李晓慧,汪西莉. 结合卷积受限玻尔兹曼机的CV图像分割模型[J]. 激光与光电子学进展, 2020, 57(4): 041018

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF