Multi-scale Segmentation of High-resolution Remote Sensing Image Based on Improved Watershed Transformation

  • School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China

Received date: 2013-04-02

  Revised date: 2013-05-02

  Online published: 2014-01-05


With the development of high resolution remote sensing images, imaging analysis technology of object-oriented method shows a distinct advantage in the field of information extraction and target recognition. Image segmentation, as a key technology of object-oriented image analysis method, has a vital role to play on the latter feature extraction and application analysis. Watershed transformation is usually adopted for image segmentation because of its unique advantages. However, because of the complexities of high spatial resolution remote sensing image itself, the traditional method of watershed segmentation is difficult to obtain satisfactory results. This paper presents a new multi-scale segmentation method for high resolution remote sensing image based on improved watershed transformation, in order to suppress over-segmentation of watershed transformation, as well as to provide arbitrary-scale segmentation of remote sensing image for object-oriented segmentation method. The algorithm fully considered multi-spectrum, multi-scale and multi-noises characteristics of high spatial resolution remote sensing image. The details are described as follows. Firstly, an anisotropic diffusion filter was used for image smoothing, because this technology can both remove the noises and maintain edges and other important details information of the input image. Secondly, in order to take into account the multi-scale characteristics of remote sensing images, multi-scale morphology gradient was extracted because of its good combination of the advantages of large structural element and small structural element, and then H-minima technology was used to extract tags of gradient image for the latter marker-based watershed algorithm. Finally, an improved fast region-merging algorithm was proposed to achieve the multi-scale segmentation. This paper elaborated the pre-processing filtering, multi-scale gradient, marking extraction and multi-scale region merging aspects, and the experiments showed that the proposed segmentation method effectively restrained over-segmentation of watershed transformation, and had a good performance for segmentation of high spatial resolution remote sensing images.

Cite this article

ZHANG Bo, HE Binbin . Multi-scale Segmentation of High-resolution Remote Sensing Image Based on Improved Watershed Transformation[J]. Journal of Geo-information Science, 2014 , 16(1) : 142 -150 . DOI: 10.3724/SP.J.1047.2014.00142


[1] Blaschke T. Object based image analysis for remote sensing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2010, 65(1):2-16.

[2] Chen J, Deng M, Xiao P, et al. Multi-scale watershed segmentation of high-resolution multi-spectral remote sensing image using wavelet transform[J]. Journal of Remote Sensing, 2011, 15(5):908-926.

[3] Tarabalka Y, Chanussot J, Benediktsson J A. Segmentation and classification of hyperspectral data using watershed transformation[J]. Pattern Recognition, 2010, 43(7):2367-2379.

[4] Angulo J, Velasco-Forero S, Chanussot J. Multiscale stochastic watershed for unsupervised hyperspectral image segmentation[C]. IEEE International Geoscience and Remote Sensing Symposium, 2009:93-96.

[5] Sun Y, He G. Segmentation of high-resolution remote sensing image based on marker-based watershed algorithm[C]. Fuzzy Systems and Knowledge Discovery, 2008. FSKD'08. Fifth International Conference on IEEE, 2008, 271-276.

[6] Feng M, Ze L, Wensheng Z, et al. Extracting of urban features from high resolution remote sensing data based on multiscale segmentation[C]. Urban Remote Sensing Event, 2009, 1-6.

[7] 刁智华, 赵春江, 郭新宇, 等.分水岭算法的改进方法研究[J].计算机工程, 2010, 36(17):4-6.

[8] 李珀任, 潘懋, 杜世宏.一种基于标记分水岭的高分辨率遥感影像分割方法[J].地理与地理信息科学, 2012, 28(5):10-15.

[9] Vincent L, Soille P. Watersheds in digital spaces: an efficient algorithm based on immersion simulations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(6):583-598.

[10] 罗玲, 解梅, 陈杉.基于多尺度形态滤波的分水岭图像分割方法[J].计算机辅助设计与图形学学报, 2004, 16(2):168-173.

[11] Lotufo R, Silva W. Minimal set of markers for the watershed transform[C]. Proceedings of ISMM, 2002:359-368.

[12] 王毅, 张良培, 李平湘.多光谱遥感图像的自适应各向异性扩散滤波[J].遥感学报, 2005, 9(6):659-666.

[13] Perona P, Malik J. Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7):629-639.

[14] González R C, Woods R E. Digital Image Processing[M]. Upper Saddle River, NJ, USA: Prentice Hall, 2008.

[15] O'Callaghan R J, Bull D R. Combined morphologicalspectral unsupervised image segmentation[J]. Image Processing, IEEE Transactions on, 2005, 14(1):49-62.

[16] 卢官明.一种计算图象形态梯度的多尺度算法[J].中国图象图形学报:A辑, 2001, 6(3):214-218.

[17] 孙颖, 何国金.基于标记分水岭算法的高分辨率遥感图像分割方法[J].科学技术与工程, 2008, 8(11):2776-2781.

[18] Gao L, Yang S Y, Li H Q. New unsupervised image segmentation via marker-based watershed[J]. Journal of Image and graphics, 2007, 6(12):1025-1032.

[19] 张桂峰.粒度理论下的多尺度遥感影像分割[D].武汉:武汉大学, 2010.

[20] 高丽, 杨树元, 李海强.一种基于标记的分水岭图像分割新算法[J].中国图象图形学报, 2007, 12(6):1025-1032.

[21] Soille P. Morphological image analysis: Principles and applications[M]. Springer-Verlag New York, Inc, 2003.

[22] Benz U C, Hofmann P, Willhauck G, et al. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2004, 58(3):239-258.

[23] Chen S, Luo J, Shen Z, et al. Segmentation of Multi-spectral Satellite Images Based on Watershed Algorithm[C]. KAM'08. International Symposium on Knowledge Acquisition and Modeling, 2008, 684-688.