Edge-Guided Multiscale Segmentation of Satellite Multispectral Imagery

This paper presents a new approach to multiscale segmentation of satellite multispectral imagery using edge information. The Canny edge detector is applied to perform multispectral edge detection. The detected edge features are then utilized in a multiscale segmentation loop, and the merge procedure for adjacent image objects is controlled by a separability criterion that combines edge information with segmentation scale. The significance of the edge is measured by adjacent partitioned regions to perform edge assessment. The present method is based on a half-partition structure, which is composed of three steps: single edge detection, separated pixel grouping, and significant feature calculation. The spectral distance of the half-partitions separated by the edge is calculated, compared, and integrated into the edge information. The results show that the proposed approach works well on satellite multispectral images of a coastal area.

[1]  Martial Hebert,et al.  Toward Objective Evaluation of Image Segmentation Algorithms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  C. Drewniok,et al.  Multi-spectral edge detection. Some experiments on data from Landsat-TM , 1994 .

[3]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .

[4]  Jungho Im,et al.  Synergistic use of QuickBird multispectral imagery and LIDAR data for object-based forest species classification , 2010 .

[5]  Rae-Hong Park,et al.  Multiresolution edge detection techniques , 1995, Pattern Recognit..

[6]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[7]  Daniel F. García,et al.  Objective comparison of edge detection assessment methods based on genetic optimization , 2009, J. Electronic Imaging.

[8]  J. L. Moigne,et al.  Refining image segmentation by integration of edge and region data , 1992, IEEE Trans. Geosci. Remote. Sens..

[9]  Gunilla Borgefors,et al.  Integrated method for boundary delineation of agricultural fields in multispectral satellite images , 2000, IEEE Trans. Geosci. Remote. Sens..

[10]  G. J. Hay,et al.  A multiscale framework for landscape analysis: Object-specific analysis and upscaling , 2001, Landscape Ecology.

[11]  P. Gong,et al.  Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery , 2006 .

[12]  Kacem Chehdi,et al.  Automatic image segmentation system through iterative edge - region co-operation , 2002, Image Vis. Comput..

[13]  G. Hay,et al.  An automated object-based approach for the multiscale image segmentation of forest scenes , 2005 .

[14]  Marina Mueller,et al.  Edge- and region-based segmentation technique for the extraction of large, man-made objects in high-resolution satellite imagery , 2004, Pattern Recognit..

[15]  C. Burnett,et al.  A multi-scale segmentation/object relationship modelling methodology for landscape analysis , 2003 .

[16]  J. Strobl,et al.  Object-Oriented Image Processing in an Integrated GIS/Remote Sensing Environment and Perspectives for Environmental Applications , 2000 .

[17]  Narendra Ahuja,et al.  Multiscale image segmentation by integrated edge and region detection , 1997, IEEE Trans. Image Process..

[18]  Chen Jian-Yu,et al.  Optimum segmentation of simple objects in high-resolution remote sensing imagery in coastal areas , 2006 .

[19]  Wenzhong Shi,et al.  A Fuzzy-Topology-Based Area Object Extraction Method , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[20]  S. M. Jong,et al.  The Importance of Scale in Object-based Mapping of Vegetation Parameters with Hyperspectral Imagery , 2007 .

[21]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  M. Baatz,et al.  Object-oriented and Multi-scale Image Analysis in Semantic Networks Introduction: the Necessity for Integration of Remote Sensing and Gis , 2022 .

[23]  Jake K. Aggarwal,et al.  The Integration of Image Segmentation Maps using Region and Edge Information , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  U. Benz,et al.  Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information , 2004 .

[26]  Jianguo Wu,et al.  A spatially explicit hierarchical approach to modeling complex ecological systems: theory and applications , 2002 .

[27]  Jaime S. Cardoso,et al.  Toward a generic evaluation of image segmentation , 2005, IEEE Transactions on Image Processing.

[28]  Jocelyn Chanussot,et al.  New hyperspectral data representation using binary partition tree , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[29]  X. Zhang,et al.  Quantification of Extensional Uncertainty of Segmented Image Objects by Random Sets , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Alfred Stein,et al.  Existential uncertainty of spatial objects segmented from satellite sensor imagery , 2002, IEEE Trans. Geosci. Remote. Sens..

[31]  Jianyu Chen,et al.  Image‐object detectable in multiscale analysis on high‐resolution remotely sensed imagery , 2009 .

[32]  Stefan Lang,et al.  Object-based mapping and object-relationship modeling for land use classes and habitats , 2006 .