skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Superpixel segmentation using multiple SAR image products.

Abstract

Abstract not provided.

Authors:
; ; ;
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1141305
Report Number(s):
SAND2014-2731C
507022
DOE Contract Number:
AC04-94AL85000
Resource Type:
Conference
Resource Relation:
Conference: Proposed for presentation at the Radar Sensor Technology XVIII (DS 108), SPIE Defense, Security, and Sensing Symposium held May 5-9, 2014 in Baltimore, MD.
Country of Publication:
United States
Language:
English

Citation Formats

Moya, Mary M, Koch, Mark William, Perkins, David Nikolaus, and West, Roger Derek. Superpixel segmentation using multiple SAR image products.. United States: N. p., 2014. Web.
Moya, Mary M, Koch, Mark William, Perkins, David Nikolaus, & West, Roger Derek. Superpixel segmentation using multiple SAR image products.. United States.
Moya, Mary M, Koch, Mark William, Perkins, David Nikolaus, and West, Roger Derek. Tue . "Superpixel segmentation using multiple SAR image products.". United States. doi:. https://www.osti.gov/servlets/purl/1141305.
@article{osti_1141305,
title = {Superpixel segmentation using multiple SAR image products.},
author = {Moya, Mary M and Koch, Mark William and Perkins, David Nikolaus and West, Roger Derek},
abstractNote = {Abstract not provided.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Apr 01 00:00:00 EDT 2014},
month = {Tue Apr 01 00:00:00 EDT 2014}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • It is useful in a variety of military and commercial application to accurately register the position of synthetic aperture radar (SAR) imagery in absolute coordinates. The two basic SAR measurements, range and doppler, can be used to solve for the position of the SAR image. Imprecise knowledge of the SAR collection platform`s position and velocity vectors introduce errors in the range and doppler measurements and can cause the apparent location of the SAR image on the ground to be in error by tens of meters. Recent advances in carrier phase GPS techniques can provide an accurate description of the collectionmore » vehicle`s trajectory during the image formation process. In this paper, highly accurate carrier phase GPS trajectory information is used in conjunction with SAR imagery to demonstrate a technique for accurate registration of SAR images in WGS-84 coordinates. Flight test data will be presented that demonstrates SAR image registration errors of less than 4 meters.« less
  • Purpose: To propose a new variational method which couples image restoration with tumor segmentation for PET images using multiple regularizations. Methods: Partial volume effect (PVE) is a major degrading factor impacting tumor segmentation accuracy in PET imaging. The existing segmentation methods usually need to take prior calibrations to compensate PVE and they are highly system-dependent. Taking into account that image restoration and segmentation can promote each other and they are tightly coupled, we proposed a variational method to solve the two problems together. Our method integrated total variation (TV) semi-blind deconvolution and Mumford-Shah (MS) segmentation. The TV norm was usedmore » on edges to protect the edge information, and the L{sub 2} norm was used to avoid staircase effect in the no-edge area. The blur kernel was constrained to the Gaussian model parameterized by its variance and we assumed that the variances in the X-Y and Z directions are different. The energy functional was iteratively optimized by an alternate minimization algorithm. Segmentation performance was tested on eleven patients with non-Hodgkin’s lymphoma, and evaluated by Dice similarity index (DSI) and classification error (CE). For comparison, seven other widely used methods were also tested and evaluated. Results: The combination of TV and L{sub 2} regularizations effectively improved the segmentation accuracy. The average DSI increased by around 0.1 than using either the TV or the L{sub 2} norm. The proposed method was obviously superior to other tested methods. It has an average DSI and CE of 0.80 and 0.41, while the FCM method — the second best one — has only an average DSI and CE of 0.66 and 0.64. Conclusion: Coupling image restoration and segmentation can handle PVE and thus improves tumor segmentation accuracy in PET. Alternate use of TV and L2 regularizations can further improve the performance of the algorithm. This work was supported in part by National Natural Science Foundation of China (NNSFC), under Grant No.61375018, and Fundamental Research Funds for the Central Universities, under Grant No. 2012QN086. Wei Lu was supported in part by the National Institutes of Health (NIH) Grant No. R01 CA172638.« less
  • A method for post-reconstruction nuclear medicine image segmentation based on an analogy to the Ising model of a two-dimensional square lattice of N particles (pixel values) is presented. A reconstructed 2-D slice image is analyzed as a multi-pixel system where pixel values correspond to a 2-D lattice of points with non-zero interaction energy with their nearest neighbors. The model assumes that pixel intensities belonging to the same homogeneous image region are relatively constant, where region intensity means (or labels) are determined by both statistical parameter estimation and deterministic image analysis. The change in value of each pixel during the segmentationmore » process depends on (1) the statistical properties in the reconstructed image and (2) the values (or states) of its nearest neighbors. These changes are either in the direction of statistically estimated intensity means or other previously analyzed regions of significance. The segmentation technique uses a new innovative relaxation labeling connective network. The global relaxation dynamics of the network are controlled by the interaction of local synergetic and logistic functions assigned to each pixel. This result may improve the localization of hot and cold regions of interest as compared to the original image.« less
  • We present a method for hierarchical image segmentation and feature extraction. This method builds upon the combination of the detection of image spectral discontinuities using Canny edge detection and the image Laplacian, followed by the construction of a hierarchy of segmented images of successively reduced levels of details. These images are represented as sets of polygonized pixel patches (polygons) attributed with spectral and structural characteristics. This hierarchy forms the basis for object-oriented image analysis. To build fine level-of-detail representation of the original image, seed partitions (polygons) are built upon a triangular mesh composed of irregular sized triangles, whose spatial arrangementmore » is adapted to the image content. This is achieved by building the triangular mesh on the top of the detected spectral discontinuities that form a network of constraints for the Delaunay triangulation. A polygonized image is represented as a spatial network in the form of a graph with vertices which correspond to the polygonal partitions and graph edges reflecting pairwise partitions relations. Image graph partitioning is based on the iterative graph oontraction using Boruvka's Minimum Spanning Tree algorithm. An important characteristic of the approach is that the agglomeration of partitions is constrained by the detected spectral discontinuities; thus the shapes of agglomerated partitions are more likely to correspond to the outlines of real-world objects.« less