检索结果-内蒙古大学图书馆

Advances in Intelligent Systems and Computing 2013年 212卷 929-937页

作者： Tu, Zhengzheng Sun, Dengdi Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China School of Computer Science and Technology Anhui University Hefei 230601 China Key Lab of Industrial Image Processing and Analysis of Anhui Province Hefei 230039 China

ISBN: (纸本)9783642375019

Video summarization provides condensed and succinct representations of the content of a video stream. A static storyboard summarization approach based on robust low-rank subspace segmentation is proposed in this paper. Firstly, video frames are represented as multi-dimensional vectors, and then embedded into a group of affine subspaces using low-rank representation according to the content similarity of the frames in the same subspace. Secondly, a series of subspaces are segmented based on the Normalized Cuts algorithm. The video summary is finally generated by choosing key frames from the significant subspaces and ranking these key frames in temporal order. The experimental results demonstrate that the proposed summarization algorithm can produce crucial key frames and effectively reduce the visual content redundancy in summary comparing with the conventional approaches. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

An efficient algorithm for feature selection with feature correlation

An efficient algorithm for feature selection with feature co...

引用

3rd Sino-Foreign-Interchange Workshop on Intelligent science and Intelligent Data Engineering, IScIDE 2012

作者： Huang, Li-Li Tang, Jin Chen, Si-Bao Ding, Chris Luo, Bin School of Computer Science and Technology Anhui University 230601 China Key Lab of Industrial Image Processing and Analysis of Anhui Province Hefei 230039 Anhui China

ISBN: (纸本)9783642366680

Feature selection is an important component of many machine learning applications. In this paper, we propose a new robust feature selection method for multi-class multi-label learning. In particular, feature correlation is added into the sparse learning of feature selection so that we can learn the feature correlation and do feature selection simultaneously. An efficient algorithm is introduced with rapid convergence. Our regression based objective makes the feature selection process more efficient. Experiments on benchmark data sets illustrate that the proposed method outperforms many state-of-the-art feature selection methods. © Springer-Verlag 2013.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Robust dense endoscopic stereo reconstruction for minimally invasive surgery

Robust dense endoscopic stereo reconstruction for minimally ...

引用

15th International Conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2012

作者： Bernhardt, Sylvain Abi-Nahed, Julien Abugharbieh, Rafeef Biomedical Signal and Image Computing Lab. University of British Columbia Vancouver BC Canada Qatar Robotic Surgery Centre Qatar Science and Technology Park Qatar

ISBN: (纸本)9783642366192

Robotic assistance in minimally invasive surgical interventions has gained substantial popularity over the past decade. Surgeons perform such operations by remotely manipulating laparoscopic tools whose motion is executed by the surgical robot. One of the main tools deployed is an endoscopic binocular camera that provides stereoscopic vision of the operated scene. Such surgeries have notably garnered wide interest in renal surgeries such as partial nephrectomy, which is the focus of our work. This operation consists of the localization and removal of tumorous tissue in the kidney. During this procedure, the surgeon would greatly benefit from an augmented reality view that would display additional information from the different imaging modalities available, such as pre-operational CT and intra-operational ultrasound. In order to fuse and visualize these complementary data inputs in a pertinent way, they need to be accurately registered to a 3D reconstruction of the imaged surgical scene topology captured by the binocular camera. In this paper we propose a simple yet powerful approach for dense matching between the two stereoscopic camera views and for reconstruction of the 3D scene. Our method adaptively and accurately finds the optimal correspondence between each pair of images according to three strict confidence criteria that efficiently discard the majority of outliers. Using experiments on clinical in-vivo stereo data, including comparisons to two state-of-the-art 3D reconstruction techniques in minimally invasive surgery, our results illustrate superior robustness and better suitability of our approach to realistic surgical applications. © 2013 Springer-Verlag.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

image representation and recognition based on directed complex network model

Image representation and recognition based on directed compl...

引用

8th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2013

作者： Chen, Ying Tang, Jin Luo, Bin School of Computer Science and Technology Anhui University Hefei230601 China Key Lab of Industrial Image Processing and Analysis of Anhui Province Hefei230039 China

ISBN: (纸本)9783642375019

image structure representation is a vital technique in the image recognition. A novel image representation and recognition method based on directed complex network is proposed in this paper. Firstly, the key points are extracted from an image as the nodes to construct an initial complete undirected complex network. Then, the k-nearest neighbor evolution method is designed to form a series of directed networks. At last, the feature descriptor of the image is constructed by concatenating the structure features of each directed network to finally achieve image recognition. Experimental results demonstrate that the proposed method outperforms the traditional methods in image recognition and can describe the structure of images more effectively. © Springer-Verlag Berlin Heidelberg 2013.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

VISCERAL: Towards large data in medical imaging - Challenges and directions

VISCERAL: Towards large data in medical imaging - Challenges...

引用

3rd MICCAI International Workshop on Medical Content-Based Retrieval for Clinical Decision Support, MCBR-CDS 2012

作者： Langs, Georg Hanbury, Allan Menze, Bjoern Müller, Henning Computational Image Analysis and Radiology Lab. Department of Radiology Medical University of Vienna Austria Institute for Software Technology and Interactive Systems Faculty of Computer Science Vienna University of Technology Austria Computer Vision Lab. ETH Zurich Switzerland Switzerland

ISBN: (纸本)9783642366772

The increasing amount of medical imaging data acquired in clinical practice holds a tremendous body of diagnostically relevant information. Only a small portion of these data are accessible during clinical routine or research due to the complexity, richness, high dimensionality and size of the data. There is consensus in the community that leaps in this regard are hampered by the lack of large bodies of data shared across research groups and an associated definition of joint challenges on which development can focus. In this paper we describe the objectives of the project Visceral. It will provide the means to jump-start this process by providing access to unprecedented amounts of real world imaging data annotated through experts and by using a community effort to generate a large corpus of automatically generated standard annotations. To this end, Visceral will conduct two competitions that tackle large scale medical image data analysis in the fields of anatomy detection, and content-based image retrieval, in this case the retrieval of similar medical cases using visual data and textual radiology reports. © 2013 Springer-Verlag.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

A probability-based object tracking method

A probability-based object tracking method

引用

4th International Conference on Intelligence science and Big Data Engineering, IScIDE 2013

作者： Song, Xu Li, Guoqiang Li, Ying Zhang, Yanning Shaanxi Province Key Lab. of Speech and Image Information Processing Northwestern Polytechnical University Xi'an 710129 China Science and Technology on Electro-optic Control Laboratory Louyang 471009 China

ISBN: (纸本)9783642420566

Here we take advantage of the signal recovery power of Compressive Sensing (CS) to significantly reduce the computational complexity brought by the high-dimension image data, then an effective and efficient low-dimensional subspace representation of the object is computing by applying Principal Component Analysis (PCA) to a collection of object observations which are low-dimensional vectors derived from CS. An incremental PCA algorithm is used to update this subspace model for characterizing the object appearance changes. Meanwhile, two distances derived from Probabilistic Principal Component Analysis (PPCA): distance from feature space (DFFS) and distance in feature space (DIFS), are used to describe visual similarity between the learned subspace representation model and candidate targets. Comparing with the traditional used reconstruction error, the sum of two distances: DFFS + DIFS, is more accurate and more robust to noises and partial occlusions. Numerous experiment demonstrate that subspace representation model can handle the situation that target objects experience pose changes, scale changes, significant illumination variation, partial occlusions and so on. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional cardiac motion estimation based on non-rigid image registration using a novel transformation model adapted to the heart

Three-dimensional cardiac motion estimation based on non-rig...

引用

3rd International Workshop on Statistical Atlases and Computational Models of the Heart: Imaging and Modelling Challenges, STACOM 2012

作者： Heyde, Brecht Barbosa, Daniel Claus, Piet Maes, Frederik D'Hooge, Jan Cardiovascular Imaging and Dynamics University of Leuven Leuven Belgium Medical Image Computing University of Leuven Leuven Belgium Medical Imaging Lab. Norwegian Institute for Science and Technology Trondheim Norway

ISBN: (纸本)9783642369605

We present a novel method for tracking myocardial motion from volumetric ultrasound data based on non-rigid image registration using an anatomical free-form deformation model. Traditionally, the B-spline control points of such a model are defined on a rectangular grid in Cartesian space. This arrangement may be suboptimal as it treats the blood pool and myocardium similarly and as it enforces spatial smoothness in non-physiological directions. In this work, the basis functions are locally oriented along the radial, longitudinal and circumferential direction of the endocardium. This formulation allows us to model the left ventricular motion more naturally. We obtained encouraging accuracy results for the simulated models, with average errors of 0.8±0.6mm (10% relatively) and 0.5±0.4mm (15% relatively) compared to the ground truth in high and low contractility models respectively. © 2013 Springer-Verlag.

关键词： Echocardiography

来源：评论

学校读者我要写书评

暂无评论

An improved method in change detection of multitemporal remote sensing image

An improved method in change detection of multitemporal remo...

引用

4th International Conference on Intelligence science and Big Data Engineering, IScIDE 2013

作者： Liao, Fangshun Yu, Sufen Li, Ying Zhang, Yanning Shaanxi Provincial Key Lab. of Speech and Image Information Processing Northwestern Polytechnical University Xi'an Shaanxi 710072 China Science and Technology on Electro-optic Control Laboratory Louyang 471009 China

ISBN: (纸本)9783642420566

Traditional Markov random Field (MRF) methods assume that neighboring pixels tend to have the same label. However, this assumption is always inconsistent with the actual situation and affects the resultant accuracy of the algorithm. To overcome this, we propose an object-based Markov Random Field (OMRF) model and a change detection method based on OMRF model. The OMRF model assumes that pixels within same object are in the same class. First, we generate the difference image from multi-temporal remote sensing images. Second, Mean Shift is applied to extract objects from difference image. Finally, change detection map is generated by iterative algorithm. The experimental results show that the algorithm can effectively improve the detection accuracy of the algorithm on real remote sensing datasets. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

A local elitism based membrane evolutionary algorithm for point pattern matching

A local elitism based membrane evolutionary algorithm for po...

引用

8th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2013

作者： Ding, Zhuanlian Tang, Jin Zhang, Xingyi Luo, Bin School of Computer Science and Technology Anhui University HefeiAnhui230601 China Key Lab of Industrial Image Processing and Analysis of Anhui Province HefeiAnhui230039 China

ISBN: (纸本)9783642375019

Point pattern matching is a fundamental problem in computer vision and pattern recognition. Membrane computing is an emergent branch of bio-inspired computing, which provides a novel idea to solve computationally hard problems. In this paper, a new point pattern matching algorithm with local elitism strategy is proposed based on membrane computing models. Local elitism strategy is used to keep good correspondences of point pattern matching found during the search, so the matching rate and the convergence speed are improved. Five heuristic mutation rules are introduced to avoid the local optimum. Experiment results on both synthetic data and real world data illustrate that the proposed algorithm is of higher matching rate and better stability. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Membranes

来源：评论

学校读者我要写书评

暂无评论

Sparse Representation-Based Human Action Recognition Using an Action Region-Aware Dictionary

Sparse Representation-Based Human Action Recognition Using a...

引用

IEEE International Symposium on Multimedia

作者： Hyun-Seok Min Wesley De Neve Yong Man Ro Image and Video Systems Lab Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea

Automatic human action recognition is a core functionality of systems for video surveillance and human-object interaction. Conventional vision-based systems for human action recognition require the use of segmentation in order to achieve an acceptable level of recognition effectiveness. However, generic techniques for automatic segmentation are currently not available yet. Therefore, in this paper, we propose a novel sparse representation-based method for human action recognition, taking advantage of the observation that, although the location and size of the action region in a test video clip is unknown, the construction of a dictionary can leverage information about the location and size of action regions in training video clips. That way, we are able to segment, implicitly, action and context information in a test video clip, thus improving the effectiveness of classification. That way, we are also able to develop a context-adaptive classification strategy. As shown by comparative experimental results obtained for the UCF Sports Action data set, the proposed method facilitates effective human action recognition, even when testing does not rely on explicit segmentation.

关键词： Dictionaries Multimedia communication Abstracts Context

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：