高分辨率影像分割的分形网络演化改进方法
收稿日期: 2013-03-29
修回日期: 2013-04-28
网络出版日期: 2014-01-05
基金资助
高分辨率对地观测系统重大专项（02-Y30A04-9001-12/13）。
An Improved Method of FNEA for High Resolution Remote Sensing Image Segmentation
Received date: 2013-03-29
Revised date: 2013-04-28
Online published: 2014-01-05
分形网络演化是针对高分辨遥感影像的高精度分割方法。它是以像元自下而上进行地物域合并，直至满足区域对象间异质性值大于预设阈值，停止区域合并得到最终分割结果。当对大数据量遥感影像进行分割时，形成初始区域对象的速度较慢，并且数量较多，导致分割时间长，有待在整体分割效率上进一步提高。一种有效的改进措施是采用某种分割方法，快速生成初始区域对象，然后再以初始分割结果区域对象进行区域合并。本文提出一种自动种子点的并行区域生长分割方法，用于快速生成初始区域对象；提出均匀数据划分的并行区域生长策略及消除数据划分线两侧的区域对象方法；采用OpenMP并行技术实现并行区域生长过程。分割效果对比和效率分析结果表明，本文提出的初始分割方法效率较高，并且分割结果可重现，从可信度、通用性角度来看，具有较高的实用价值。
邓富亮, 杨崇俊, 曹春香, 范协裕 . 高分辨率影像分割的分形网络演化改进方法[J]. 地球信息科学学报, 2014 , 16(1) : 95 -101 . DOI: 10.3724/SP.J.1047.2013.00095
Fractal Net Evolution Approach (FNEA) is a high precision algorithm for high resolution remote sensing image segmentation. The segmentation algorithm starts with single image objects of one pixel and repeatedly merges them in several loops in pairs to larger units as long as an upper threshold of homogeneity is not exceeded locally. However, it's high computational cost for large images such as the currently high resolution remote sensing images includes two aspects, one is the time-consuming procedure of creation of initial image objects, and the other is the great amount of initial image objects. In order to boost the speed of the algorithm, generally, an effective improvement measure is to select a faster segmentation method to generate the initial image objects, and then carry out the region merging phase. Thus, the main focus of this paper is to tackle this problem by using a parallel process to segment the original image into subsets as the initial image objects firstly. For the original image data preprocessing, a regular data division way is used to divide the original image data into sub-rectangular data blocks, which will be used as the input data and assigned to different threads for the parallel computing. We introduced an improved method of fractal net evolution approach, the main work as follows: (i) Presenting an automatic seed selection method. The initial seeds are automatically selected from the original image data and the seeded image objects are produced where each image object corresponds to a seed. (ii) Proposing a parallel region growing strategy upon the data paralleled segmentation. Moreover, the strategy solves the problem of merging image objects on both sides of the dividing lines as well. (iii) Using the OpenMP parallel technology. Experimental results, including comparison of final segmentation and assessment of computing efficiency, show that the improved method is more effective and the final segmentation result is reproducible. Thus, the generality and reliability of the method proved the practical value of our work.
[1] 孙显, 付琨, 王宏琦.高分辨率遥感图像理解[M].北京:科学出版社, 2011, 1-28.
[2] Blaschke T. Object based image analysis for remote sensing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2010, 65(1):2-16.
[3] Baatz M, Schäpe A. Multiresolution segmentation: An optimization approach for high quality multi-scale image segmentation[C].//Angewandte Geographische Informationsverarbeitung XⅡ, Strobl J, Blaschke T, Griesebner G(Eds), Wichmann, Heidelberg, Germany, 2000.
[4] Schiewe J, Tufte L, Ehlers M. Potential and problems of multi-scale segmentation methods in remote sensing[J]. GeoBIT/GIS, 2001, 6(1):34-39.
[5] Blaschke T, Burnett C, Pekkarinen A. Image segmentation methods for object-based analysis and classification[C]. Remote sensing image analysis: Including the spatial domain.Springer Netherlands, 2006.
[6] Blaschke T, Lang S, Lorup E, et al. Object-oriented image processing in an integrated GIS/remote sensing environment and perspectives for environmental applications[J]. Environmental information for planning, politics and the public, 2000(2):555-570.
[7] Schiewe J.Segmentation of high-resolution remotely sensed data-concepts, applications and problems[J]. International Archives of Photogrammetry Remote Sensing And Spatial Information Sciences, 2002, 34(4):380-385.
[8] Neubert M., Meinel G. Evaluation of segmentation programs for high resolution remote sensing applications[C].//International ISPRS Workshop "High Resolution Mapping from Space", 2003.
[9] 高伟, 刘修国, 彭攀, 等.一种改进的高分辨率遥感影像分割方法[J].地球科学:中国地质大学学报, 2010, 35(3):421-425.
[10] Trimble. eCognition Developer 8.7.2 Reference Book[M]. Trimble Germany GmbH: Trappentreustr, 2012, 34-40.
[11] Gonzalez R C, Woods R E. Digital image processing[M]. Upper Saddle River, NJ, USA: Prentice Hall, 2002, 394-402.
[12] 刘张桥, 王成良, 焦晓军.多核环境下的图像分割并行算法研究[J].计算机工程, 2011, 37(15):197-200.
[13] 梁隽源, 李海芳, 裴照君.基于小波变换的并行图像分割算法分析与优化[J].软件导刊, 2009, 8(6):65-67.
[14] 胡晓东, 骆剑承, 沈占峰, 等.高分辨率遥感影像并行分割结果缝合算法[J].遥感学报, 2010, 14(5):917-927.
[15] Downton A and Crookes D. Parallel architectures for image processing[J]. Electronics & Communication Engineering Journal, 1998, 10(3):139-151.
[16] 周海芳.遥感图像并行处理算法的研究与应用[D].长沙:国防科学技术大学, 2003.
[17] 黄国满, 郭建峰.分布式并行遥感图像处理中的数据划分[J].遥感信息, 2001(2):9-12.
[18] Wassenberg J, Middelmann W, Sanders P. An efficient parallel algorithm for graph-based image segmentation[C]. Computer Analysis of Images and Patterns, Springer Berlin Heidelberg, 2009.
[19] Korting T.S, Castejon E.F, Fonseca L.M.G. Divide and Segment-An alternative for parallel segmentation[C]. Proceedings XⅡ GEOINFO, 2011, 97-104.
[20] 沈占锋, 骆剑承, 陈秋晓, 等.高分辨率遥感影像并行处理数据分配策略研究[J].哈尔滨工业大学学报, 2007, 8(11):1968-1971.
[21] 卢丽君, 廖明生, 张路.分布式并行计算技术在遥感数据处理中的应用[J].测绘信息与工程, 2005, 30(3):1-2.
[22] 孙敏.图像处理并行算法研究与实现[D].绵阳:西南科技大学, 2011, 19-21.
[23] 胡英帅.基于MPI的分水岭与区域合并结合算法的并行化研究[D].银川:宁夏大学, 2011, 27-30.
[24] Cheng H D, Jiang X H, Sun Y, et al. Color image segmentation: Advances and prospects[J]. Pattern Recognition, 2001, 34(12):2259-2281.
[25] Ghule A, Deshmukh P. Image Segmentation Available Techniques, Open Issues and Region Growing Algorithm[J]. Journal of Signal and Image Processing, 2012, 3(1):20-30.
[26] 章毓晋.图像工程(中册)—图像分析[M].北京:清华大学出版社, 2012, 49-50.
[27] Shih F Y, Cheng S. Automatic seeded region growing for color image segmentation[J]. Image and Vision Computing, 2005, 23(10):877-886.
[28] Sima H, Liu L, Guo P. Color image segmentation based on blocks clustering and region growing[C]. 2011 International Conference on Neural Information Processing, 2011, 459-466.
[29] Liu J, Ma Y, Chen K, et al. A novel color image segmentation method based on improved region growing[C]. Artificial Intelligence and Computational Intelligence, 2012, 365-373.
[30] Baraldi A, Parmiggiani F. A neural network for unsupervised categorization of multivalued input patterns: an application to satellite image clustering[J]. Geoscience and Remote Sensing, 1995, 33(2):305-316.
[31] Baraldi A, Parmiggiani F. Single linkage region growing algorithms based on the vector degree of match[J]. Geoscience and Remote Sensing, 1996, 34(1):137-148.
/
| 〈 |
|
〉 |