Multiscale and Multifeature Segmentation of High-Spatial Resolution Remote Sensing Images Using Superpixels with Mutual Optimal Strategy

被引:26
作者
Fu, Zhongliang [1 ,2 ]
Sun, Yangjie [1 ]
Fan, Liang [1 ]
Han, Yutao [3 ]
机构
[1] Wuhan Univ, Sch Remote Sensing & Informat Engn, Wuhan 430079, Hubei, Peoples R China
[2] Wuhan Univ, Collaborat Innovat Ctr Geospatial Technol, Wuhan 430079, Hubei, Peoples R China
[3] Sichuan Inst Aerosp Syst Engn, Chengdu 610100, Sichuan, Peoples R China
基金
中国国家自然科学基金;
关键词
image segmentation; high spatial resolution (HSR); multifeature; multiscale; superpixel; adjacency graph; MEAN-SHIFT; SCALE; MULTIRESOLUTION; CLASSIFICATION; OPTIMIZATION; ALGORITHM; PARAMETER; ATTENTION;
D O I
10.3390/rs10081289
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
High spatial resolution (HSR) image segmentation is considered to be a major challenge for object-oriented remote sensing applications that have been extensively studied in the past. In this paper, we propose a fast and efficient framework for multiscale and multifeatured hierarchical image segmentation (MMHS). First, the HSR image pixels were clustered into a small number of superpixels using a simple linear iterative clustering algorithm (SLIC) on modern graphic processing units (GPUs), and then a region adjacency graph (RAG) and nearest neighbors graph (NNG) were constructed based on adjacent superpixels. At the same time, the RAG and NNG successfully integrated spectral information, texture information, and structural information from a small number of superpixels to enhance its expressiveness. Finally, a multiscale hierarchical grouping algorithm was implemented to merge these superpixels using local-mutual best region merging (LMM). We compared the experiments with three state-of-the-art segmentation algorithms, i.e., the watershed transform segmentation (WTS) method, the mean shift (MS) method, the multiresolution segmentation (MRS) method integrated in commercial software, eCognition9, on New York HSR image datasets, and the ISPRS Potsdam dataset. Computationally, our algorithm was dozens of times faster than the others, and it also had the best segmentation effect through visual assessment. The supervised and unsupervised evaluation results further proved the superiority of the MMHS algorithm.
引用
收藏
页数:30
相关论文
共 51 条
  • [1] SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
    Achanta, Radhakrishna
    Shaji, Appu
    Smith, Kevin
    Lucchi, Aurelien
    Fua, Pascal
    Suesstrunk, Sabine
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (11) : 2274 - 2281
  • [2] [Anonymous], 2000, P AGIS
  • [3] [Anonymous], 2015, ARXIV150904232
  • [4] Unsupervised Multi-Spectral Satellite Image Segmentation Combining Modified Mean-Shift and a New Minimum Spanning Tree Based Clustering Technique
    Banerjee, Biplab
    Varma, Surender
    Buddhiraju, Krishna Mohan
    Eeti, Laxmi Narayana
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2014, 7 (03) : 888 - 894
  • [5] HIERARCHY IN PICTURE SEGMENTATION - A STEPWISE OPTIMIZATION APPROACH
    BEAULIEU, JM
    GOLDBERG, M
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (02) : 150 - 163
  • [6] Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information
    Benz, UC
    Hofmann, P
    Willhauck, G
    Lingenfelder, I
    Heynen, M
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2004, 58 (3-4) : 239 - 258
  • [7] Object based image analysis for remote sensing
    Blaschke, T.
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2010, 65 (01) : 2 - 16
  • [8] Geographic Object-Based Image Analysis - Towards a new paradigm
    Blaschke, Thomas
    Hay, Geoffrey J.
    Kelly, Maggi
    Lang, Stefan
    Hofmann, Peter
    Addink, Elisabeth
    Feitosa, Raul Queiroz
    van der Meer, Freek
    van der Werff, Harald
    van Coillie, Frieke
    Tiede, Dirk
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2014, 87 : 180 - 191
  • [9] A multilevel context-based system for classification of very high spatial resolution images
    Bruzzone, Lorenzo
    Carlin, Lorenzo
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2006, 44 (09): : 2587 - 2600
  • [10] A multi-scale segmentation/object relationship modelling methodology for landscape analysis
    Burnett, C
    Blaschke, T
    [J]. ECOLOGICAL MODELLING, 2003, 168 (03) : 233 - 249