检索结果-内蒙古大学图书馆

9th International Symposium on Signal, image, Video and Communications (ISIVC)

作者： Es-salhi, Rachida Daoudi, Imane El Ouardi, Hamid Hassan II Univ Casablanca Natl High Sch Elect & Mech Engn Res Lab Casablanca Morocco EMSI Casablanca Pluridisciplinary Lab Res & Innovat Casablanca Morocco

ISBN: (纸本)9781538681732

image co-segmentation refers to the task of segmenting jointly a set of images sharing objects of a specific class. Recent methods can co-segment simple images well, however their performance may degrade significantly on more cluttered images. In this paper a novel method is presented to jointly segment out common objects from a set of images using image complexity analysis and dense correspondences. The images are first ranked based of their complexity scores. Then a set of simple images is selected and segmented. Finally the segmentation results of simple images are propagated to more cluttered images via multi-scale dense correspondences in order to guide their segmentation. The comparison experiments conducted on iCoseg dataset demonstrate the performance of the proposed method.

关键词： Co-segmentation image complexity analysis Segmentation propagation Dense correspondences

来源：评论

学校读者我要写书评

暂无评论

Feature Adaptive Co-Segmentation by complexity Awareness

引用

IEEE TRANSACTIONS ON image PROCESSING 2013年第12期22卷 4809-4824页

作者： Meng, Fanman Li, Hongliang Ngan, King Ngi Zeng, Liaoyuan Wu, Qingbo Univ Elect Sci & Technol China Sch Elect Engn Chengdu 611731 Peoples R China Chinese Univ Hong Kong Dept Elect Engn Hong Kong Hong Kong Peoples R China

In this paper, we propose a novel feature adaptive co-segmentation method that can learn adaptive features of different image groups for accurate common objects segmentation. We also propose image complexity awareness for adaptive feature learning. In the proposed method, the original images are first ranked according to the image complexities that are measured by superpixel changing cue and object detection cue. Then, the unsupervised segments of the simple images are used to learn the adaptive features, which are achieved using an expectation-minimization algorithm combining l1-regularized least squares optimization with the consideration of the confidence of the simple image segmentation accuracies and the fitness of the learned model. The error rate of the final co-segmentation is tested by the experiments on different image groups and verified to be lower than the existing state-of-the-art co-segmentation methods.

关键词： Cosegmentation distance metric learning image complexity analysis

来源：评论

学校读者我要写书评

暂无评论

complexity AWARENESS BASED FEATURE ADAPTIVE CO-SEGMENTATION

COMPLEXITY AWARENESS BASED FEATURE ADAPTIVE CO-SEGMENTATION

引用

20th IEEE International Conference on image Processing (ICIP)

作者： Meng, Fanman Li, Hongliang Univ Elect Sci & Technol China Sch Elect Engn Chengdu 610073 Peoples R China

ISBN: (纸本)9781479923410

In this paper, we achieve co-segmentation by learning adaptive feature model for each image group. A novel feature adaptive co-segmentation method and an image complexity awareness method are proposed. We also propose a linear feature model and an expectation-minimization (EM) based algorithm for adaptive feature learning. In the EM based algorithm, two aspects such as the accuracy confidence of the simple image segmentation and the fitness of the learned model to the simple image segmentation are considered. l1-regularized least squares optimization is also combined for the minimization. By testing on several well-known datasets, the error rates of the final co-segmentation are verified to be lower than the existing state-of-the-art co-segmentation methods.

关键词： Co-segmentation image complexity analysis Metric Learning

来源：评论

学校读者我要写书评

暂无评论

complexity AWARENESS BASED FEATURE ADAPTIVE CO-SEGMENTATION

COMPLEXITY AWARENESS BASED FEATURE ADAPTIVE CO-SEGMENTATION

引用

IEEE International Conference on image Processing

作者： Fanman Meng Hongliang Li School of Electronic Engineering University of Electronic Science and Technology of China Cheng Du China 610073

ISBN: (纸本)9781479923427

关键词： Co-segmentation image complexity analysis Metric Learning feature model image segmentation Error analysis complexity Self tuning health

来源：评论

学校读者我要写书评

暂无评论

Generation and Adaptation of Transferable Roadway Model for Anticipative Road Following on Satellite-Roadway-Vehicle Network

引用

SICE Journal of Control, Measurement, and System Integration 2011年第2期4卷 97-104页

作者： Kohji Kamejima Faculty of Information Science and Technology Osaka Institute of Technology

By matching roadway images in an encountered scene with bird's eye views, the scope of humans' perception is expanded to a satellite-roadway-vehicle network. Based on the geometric consistency of the satellite images with as-is local terrain, in this paper, a computational mechanism is introduced for generation and adaptation of a roadway model transferable through the network. First, the chromatic complexity of the roadway area is represented as a palette of saliency colors via fractal sampling of the scene image. Next, the palette is adapted to the associated area in the bird's eye view. Finally, the palette is transferred to the bird's eye view for anticipatively following the roadway pattern. Experimental results demonstrate that the transferable model can be applied to the extension of the roadway pattern prior to physical access.

关键词： transferable roadway model satellite-roadway-vehicle network image complexity analysis

来源：评论

学校读者我要写书评

暂无评论

Generation and Adaptation of Transferable Roadway Model in Naturally Complex Scene

Generation and Adaptation of Transferable Roadway Model in N...

引用

Annual Conference of the SICE

作者： Kamejima, Kohji Osaka Inst Technol Fac Informat Sci & Technol Osaka 535 Japan

ISBN: (纸本)9784907764302

To expand the scope of humans' perception on satellite-roadway-vehicle network, roadway images in encountered scene are matched with bird's eye view. Based on the geometric consistency of the satellite images with as-is local terrain, in this paper, a computational mechanism is presented for generation and adaptation of roadway model transferable through the network. Laplacian-Gaussian filter is applied to the distribution of random texture in the scene image for generating a fractal model of the perspective of the roadway area. The structure of chromatic complexity is extracted via fractal sampling of the scene image and adapted to the associated area of the bird's eye view. By transferring the chromatic complexity the roadway pattern is segmented and extended in the bird's eye. view. Through experimental studies, roadway patterns were demonstrated to be extended beyond the perspective in the scene images prior to physical arrival.

关键词： Transferable Roadway Model Satellite-Roadway-Vehicle Network image complexity analysis

来源：评论

学校读者我要写书评

暂无评论

Comparative study of state of the art algorithms for hyperspectral image analysis

Comparative study of state of the art algorithms for hypersp...

引用

Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral imagery XIII

作者： Rivera-Borrero, Carlos Hunt, Shawn D. Univ Puerto Rico Dept Elect & Comp Engn Lab Appl Remote Sensing & Image Proc Mayaguez Campus San Juan PR 00936 USA

ISBN: (纸本)9780819466877

This work studies the end-to-end performance of hyperspectral classification and unmixing systems. Specifically, it compares widely used current state of the art algorithms with those developed at the University of Puerto Rico. These include algorithms for image enhancement, band subset selection, feature extraction, supervised and unsupervised classification, and constrained and unconstrained abundance estimation. The end to end perfortriance for different combinations of algorithms is evaluated. The classification algorithms are compared in terms of percent correct classification. This method, however, cannot be applied to abundance estimation, as the binary evaluation used for supervised and unsupervised classification is not directly applicable to unmixing performance analysis. A procedure to evaluate unmixing performance is described in this paper and tested using coregistered data acquired by various sensors at different spatial resolutions. Performance results are generally specific to the image used. In an effort to try and generalize the results, a formal description of the complexity of the images used for the evaluations is required. Techniques for image complexity analysis currently available for automatic target recognizers are included and adapted to quantify the performance of the classifiers for different image classes.

关键词： hyperspectral imagery end-to-end performance image complexity analysis

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：