检索结果-内蒙古大学图书馆

14th European Conference on Computer Vision (ECCV)

作者： Maninis, Kevis-Kokitsi Pont-Tuset, Jordi Arbelaez, Pablo Van Gool, Luc ETH Zurich Switzerland Univ Los Andes Bogota Colombia Katholieke Univ Leuven Leuven Belgium

ISBN: (纸本)9783319464480;9783319464473

We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computationally efficient, because it requires a single CNN forward pass for contour detection and it uses a novel sparse boundary representation for hierarchical segmentation;it gives a significant leap in performance over the state-of-the-art, and it generalizes very well to unseen categories and datasets. Particularly, we show that learning to estimate not only contour strength but also orientation provides more accurate results. We perform extensive experiments on BSDS, PASCAL Context, PASCAL segmentation, and MS-COCO, showing that COB provides state-of-the-art contours, region hierarchies, and object proposals in all datasets.

关键词： Contour detection Contour orientation estimation hierarchical image segmentation Object proposals

来源：评论

学校读者我要写书评

暂无评论

Multiscale Superpixels and Supervoxels Based on hierarchical Edge-Weighted Centroidal Voronoi Tessellation

引用

IEEE TRANSACTIONS ON image PROCESSING 2015年第11期24卷 3834-3845页

作者： Zhou, Youjie Ju, Lili Wang, Song Univ S Carolina Dept Comp Sci & Engn Columbia SC 29208 USA Univ S Carolina Dept Math Columbia SC 29208 USA

Superpixels and supervoxels play an important role in many computer vision applications, such as image segmentation, object recognition, and video analysis. In this paper, we propose a new hierarchical edge-weighted centroidal Voronoi tessellation (HEWCVT) method for generating superpixels/supervoxels in multiple scales. In this method, we model the problem as a multilevel clustering process: superpixels/supervoxels in one level are clustered to obtain larger size superpixels/supervoxels in the next level. In the finest scale, the initial clustering is directly conducted on pixels/voxels. The clustering energy involves both color similarities and boundary smoothness of superpixels/supervoxels. The resulting superpixels/supervoxels can be easily represented by a hierarchical tree which describes the nesting relation of superpixels/supervoxels across different scales. We first investigate the performance of obtained superpixels/supervoxels under different parameter settings, then we evaluate and compare the proposed method with several state-of-the-art superpixel/supervoxel methods on standard image and video data sets. Both quantitative and qualitative results show that the proposed HEWCVT method achieves superior or comparable performances with other methods.

关键词： Superpixel supervoxel image segmentation hierarchical image segmentation edge-weighted centroidal Voronoi tessellation

来源：评论

学校读者我要写书评

暂无评论

hierarchical image segmentation based on similarity of NDVI time series

引用

REMOTE SENSING OF ENVIRONMENT 2008年第2期112卷 506-521页

作者： Lhermitte, Stefaan Verbesselt, Jan Jonckheere, Inge Nackaerts, Kris van Aardt, Jan A. N. Verstraeten, Willem W. Coppin, Pol Katholieke Univ Leuven Biosyst Dept M3 BIORES Louvain Belgium Integraph Belgium BV Brussels Belgium CSIR Pretoria South Africa

Although a variety of hierarchical image segmentation procedures for remote sensing imagery have been published, none of them specifically integrates remote sensing time series in spatial or hierarchical segmentation concepts. However, this integration is important for the analysis of ecosystems which are hierarchical in nature, with different ecological processes occurring at different spatial and temporal scales. Therefore, the objective of this paper is to introduce a multi-temporal hierarchical image segmentation (MTHIS) methodology to generate a hierarchical set of segments based on spatial similarity of remote sensing time series. MTHIS employs the similarity of the fast Fourier transform (FFT) components of multi-seasonal time series to group pixels with similar temporal behavior into hierarchical segments at different scales. Use of the FFT allows the distinction between noise and vegetation related signals and increases the computational efficiency. The MTHIS methodology is demonstrated on the area of South Africa in an MTHIS protocol for Normalized Difference Vegetation Index (NDVI) time series. Firstly, the FFT components that express the major spatio-temporal variation in the NDVI time series, the average and annual term, are selected and the segmentation is performed based on these components. Secondly, the results are visualized by means of a boundary stability image that confirms the accuracy of the algorithm to spatially group pixels at different scale levels. Finally, the segmentation optimum is determined based on discrepancy measures which illustrate the correspondence of the applied MTHIS output with landcover-landuse maps describing the actual vegetation. In future research, MTHIS can be used to analyze the spatial and hierarchical structure of any type of remote sensing time series and their relation to ecosystem processes. (C) 2007 Elsevier Inc. All rights reserved.

关键词： hierarchical image segmentation fast Fourier transform NDVI time series vegetation mapping

来源：评论

学校读者我要写书评

暂无评论

Interactive characterization of granulated materials

引用

COMPUTERS & GEOSCIENCES 2009年第10期35卷 1968-1974页

作者： Andrade, Marcos C. Pinto, Lucio C. M. CDTN Belo Horizonte MG Brazil

This paper illustrates an interactive approach to digital characterization of granulated materials, based on mathematical morphology, digital topology and non-linear differential equations. The digital characterization is achieved using a three-step sequential process, namely: denoising, interactive segmentation and quantification, with emphasis in the interactive segmentation step, since it has significant impact on the characterization results. Denoising is used to extract foreground and background markers. image segmentation results from an anisotropic region-growing and merging process based on immersion simulation. Region-growing evolves as a fully automated process, initiated at local image minima, while merging requires manual insertion of one single marker per region-of-interest. Non-significant regions are merged according to a hierarchy established by a set of markers and merging rules, which represent a robust solution to the over-segmentation problem inherent to immersion simulation algorithms. The sensitivity of the segmentation algorithm to local intensity variations allows the detection of the edges with high accuracy. Quantification is achieved using a suitable stereometric method, which computes the three-dimensional size distribution from the two-dimensional size distribution observed on the image. It is shown that this interactive approach represents a viable solution to digital characterization of granulated materials. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Denoising hierarchical image segmentation Partial occlusion Overlapping Material characterization Stereometry

来源：评论

学校读者我要写书评

暂无评论

HWT - Hybrid watershed transform: Optimal combination of hierarchical interactive and automated image segmentation

HWT - Hybrid watershed transform: Optimal combination of hie...

引用

Medical Imaging 2007 Conference

作者： Hahn, Horst K. Wenzel, Markus T. Drexl, Johann Zentis, Susanne Peitgen, Heinz-Otto MeVis Res Ctr Med Image Comp Univ Allee 29 D-28359 Bremen Germany

ISBN: (纸本)9780819466303

In quantitative medical imaging and therapy planning, the optimal combination of automated and interactively defined information is crucial for image segmentation methods to be both efficient and effective. We propose to combine an efficient hierarchical region merging scheme that collects per-region statistics across hierarchy levels with a trainable classification engine that facilitates automated region labeling based on an arbitrary number of reference segmentations. When applying the classification engine, we propose to use a corridor of non-classified regions resulting in a sparse labeling with extremely low false-classification rate, and to attribute labels to the remaining basins through successive merging with ready-labeled basins. The proposed hierarchical region merging scheme also permits to efficiently include interactively defined labels. We denominate this general approach as Hybrid hierarchical Interactive image segmentation Scheme (HIS2). More specifically, we present an extension of the Interactive Watershed Transform, which we combine with a trainable two-class Support Vector Machine based on Gaussian radial basis functions. Finally, we present a novel asymmetric marker scheme, which provides a powerful means of regionally correcting remaining inaccuracies while preserving full detail of the automatic labeling procedure. We denominate the complete algorithm as Hybrid Watershed Transform (HWT), which we apply to one challenging segmentation problem in clinical imaging, namely efficient bone removal in large computed tomography angiographic data sets. Efficiency and accuracy of the proposed methodology is evaluated on multi-slice images from nine different sites. As a result, its ability to rapidly and automatically generate robust and precise segmentation results in combination with a versatile manual correction mechanism could be proven without requiring specific anatomical or geometrical models.

关键词： medical image analysis hierarchical image segmentation watershed transform automation efficient human-computer interaction CT angiography bone removal

来源：评论

学校读者我要写书评

暂无评论

hierarchical MRF-based segmentation of remote-sensing images

Hierarchical MRF-based segmentation of remote-sensing images

引用

IEEE International Conference on image Processing (ICIP 2006)

作者： Gaetano, R. Poggi, G. Scarpa, G. Univ Naples Federico II Dipartimento Ingn Elettron & Telecommun Via Claudio 21 I-80125 Naples Italy

ISBN: (纸本)9781424404810

Remote-sensing images are often composed by a hierarchy of nested regions, with complex regions that are regarded as homogeneous at some observation scale, but can be further segmented at finer scales. Tree-structured Markov random fields (TS-MRF) allow one to model such images, and to develop efficient segmentation algorithms for them. TS-MRF are traditionally based on binary trees of classes, but the use of generic trees, with more degrees of freedom, can likely provide a better performance, as was shown in [1] with reference to synthetic images. Here we build upon the ideas proposed in [1] to devise a segmentation algorithm that works effectively, and with a limited computational burden, on real-world remote sensing images.

关键词： hierarchical image segmentation tree structured markov random field mean shift remote sensing images

来源：评论

学校读者我要写书评

暂无评论

segmentation of textured polarimetric SAR scenes by likelihood approximation

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2004年第10期42卷 2063-2072页

作者： Beaulieu, JM Touzi, R Univ Laval Dept Comp Sci & Software Engn Dept Quebec City PQ G1K 7P4 Canada Nat Resources Canada Canada Ctr Remote Sensing Ottawa ON K1A 0Y7 Canada

A hierarchical stepwise optimization process is developed for polarimetric synthetic aperture radar image segmentation. We show that image segmentation can be viewed as a likelihood approximation problem. The likelihood segment merging criteria are derived using the multivariate complex Gaussian, the Wishart distribution, and the K-distribution. In the presence of spatial texture, the Gaussian-Wishart segmentation is not appropriate. The K-distribution segmentation is more effective in textured forested areas. The validity of the product model is also assessed, and a field-adaptable segmentation strategy combining different criteria is examined.

关键词： hierarchical image segmentation maximum-like-lihood estimation polarimetric synthetic aperture radar (SAR) image texture Wishart and K-distributions

来源：评论

学校读者我要写书评

暂无评论

segmentation of textured polarimetric SAR scenes by likelihood approximation

Segmentation of textured polarimetric SAR scenes by likeliho...

引用

23rd International Geoscience and Remote Sensing Symposium (IGARSS 2003)

作者： Beaulieu, JM Touzi, R Univ Laval Dept Comp Sci & Software Engn Dept Quebec City PQ G1K 7P4 Canada Nat Resources Canada Canada Ctr Remote Sensing Ottawa ON K1A 0Y7 Canada

关键词： hierarchical image segmentation maximum-like-lihood estimation polarimetric synthetic aperture radar (SAR) image texture Wishart and K-distributions

来源：评论

学校读者我要写书评

暂无评论

hierarchical spatiotemporal moving object segmentation based on a binary split algorithm

引用

OPTICAL ENGINEERING 2003年第1期42卷 245-254页

作者： Park, YS Chung, EY Kim, GS Ha, YH Kyongju Univ Sch Elect & Comp Engn Kyongju Kyung Buk South Korea nBlz Technol Co Ltd Seocho Gu Seoul 137070 South Korea Kyungpook Natl Univ Sch Elect Engn & Comp Sci Taegu 702701 South Korea

To segment moving objects in head-and-shoulder image sequences, a new morphological image segmentation algorithm is proposed using a hierarchical structure based on a binary split algorithm. The split method is performed using the combination of spatial and temporal similarities to reduce the residual errors between the original and segmented image. Spatial similarity is used to split those regions with the most different intensity values, while temporal similarity, based on the displacement vectors between two images, is used to split those regions with different motions. As a result, the proposed hierarchical segmentation method, based on a binary split algorithm, can increase the subjective image quality with only a small number of regions. Furthermore, a new contour simplification technique composed of three filtering steps is repeatedly applied to the segmented image, thereby eliminating any noisy contours of segmented regions. (C) 2003 Society of Photo-Optical Instrumentation Engineers.

关键词： morphological filter hierarchical image segmentation contour simplification watershed algorithm optical flow

来源：评论

学校读者我要写书评

暂无评论

hierarchical image segmentation BY MULTIDIMENSIONAL CLUSTERING AND ORIENTATION-ADAPTIVE BOUNDARY REFINEMENT

引用

PATTERN RECOGNITION 1995年第5期28卷 695-709页

作者： SCHROETER, P BIGUN, J SWISS FED INST TECHNOL DEPT ELECT ENGN CH-1015 LAUSANNE SWITZERLAND

In this paper we present a new multi-dimensional segmentation algorithm. We propose an orientation-adaptive boundary estimation process, embedded in a multiresolution pyramidal structure, that allows the use of different clustering procedures without spatial connectivity constraints. The presence of noise in the feature space, mainly produced by modeling errors, causes a class-overlap which can be reduced in a multiresolution pyramid. At the coarsest resolution level, the separation between the different classes is increased and the within-class variance reduced. Thus, at this level, the classes can be obtained with different multi-dimensional clustering algorithms without connectivity constraints. Small and scattered classes as well as isolated class labels are reassigned to their neighborhood by a process which guarantees the spatial connectivity. The resolution is then increased by projecting down the class labels. At each level, the borders are improved by reassigning the boundary pixels to their spatially closest class. However, the class-uncertainty astride the borders has first to be reduced, and we propose to do this by means of orientation-adaptive butterfly-shaped filters. This refinement process further eliminates spatially misclassified pixels produced by the unconstrained clustering. Experimental results show that similarly accurate boundaries are obtained with different clustering algorithms for various test images.

关键词： hierarchical image segmentation TEXTURE segmentation PYRAMIDS MULTIDIMENSIONAL CLUSTERING DETERMINISTIC RELAXATION ORIENTATION-ADAPTIVE FILTERS BOUNDARY REFINEMENT

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：