检索结果-内蒙古大学图书馆

第一届亚洲模式识别会议

作者： Rongguo Zhang Xinyuan Cai Chunheng Wang Baihua Xiao State Key Laboratory of Intelligent Control and Management of Complex SystemsInstitute of Automation State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automatio

ISBN: (纸本)9781457701221

Histogram features, such as SIFT, HOG, LBP et al, are widely used in modern computer vision algorithms. According to [18], chi-square distance is an effective measure for comparing histogram features. In this paper, we propose a new method, named the Quadric-chi similarity metric learning (QCSML) for histogram features. The main contribution of this paper is that we propose a new metric learning method based on chi-square distance, in contrast with traditional Mahalanobis distance metric learning methods. The use of quadric-chi similarity in our method leads to an effective learning algorithm. Our method is tested on SIFT features for face identification, and compared with the state-of-art metric learning method (LDML) on the benchmark dataset, the Labeled Faces in the Wild (LFW). Experimental results show that our method can achieve clear performance gains over LDML.

关键词： histogram feature metric learning Quardic-chi similarity face identification

来源：评论

学校读者我要写书评

暂无评论

A Local Learning Based Image-To-Class Distance for Image Classification

A Local Learning Based Image-To-Class Distance for Image Cla...

引用

第一届亚洲模式识别会议

作者： Xinyuan Cai Rongguo Zhang Baihua Xiao Chunheng Wang State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automatio State Key Laboratory of Intelligent Control and Management of Complex SystemsInstitute of Automation

ISBN: (纸本)9781457701221

Image-To-Class distance is first proposed in Naive- Bayes Nearest-Neighbor. NBNN is a feature-based image classifier, and can achieve impressive classification accuracy. However, the performance of NBNN relies heavily on the large number of training samples. If using small number of training samples, the performance will degrade. The goal of this paper is to address this issue. The main contribution of this paper is that we propose a robust Image-to-Class distance by local learning. We define the patch-to-class distance as the distance between the input patch to its nearest neighbor in one class, which is reconstructed in the local manifold space;and then our image-toclass distance is the sum of patch-to-class distance. Furthermore, we take advantage of large-margin metric learning framework to obtain a proper Mahalanobis metric for each class. We evaluate the proposed method on four benchmark datasets: Caltech, Corel, Scene13, and Graz. The results show that our defined Image-To-Class Distance is more robust than NBNN and Optimal-NBNN, and by combining with the learned metric for each class, our method can achieve significant improvement over previous reported results on these datasets.

关键词： local learning image-to-class distance large margin metric learning Na(i)ve Bayes Nearest-Neighbor image classification

来源：评论

学校读者我要写书评

暂无评论

Contextual Constrained Independent Component Analysis Based Foreground Detection for Indoor Surveillance

Contextual Constrained Independent Component Analysis Based ...

引用

第一届亚洲模式识别会议

作者： Zhong Zhang Wen Zhou Baihua Xiao Shuang Liu Chunheng Wang State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automatio State Key Laboratory of Intelligent Control and Management of Complex SystemsInstitute of Automation

ISBN: (纸本)9781457701221

Recently, Independent Component Analysis based foreground detection has been proposed for indoor surveillance applications where the foreground tends to move slowly or remain still. Yet such a method often causes discrete segmented foreground objects. In this paper, we propose a novel foreground detection method named Contextual Constrained Independent Component Analysis (CCICA) to tackle this problem. In our method, the contextual constraints are explicitly added to the optimization objective function, which indicate the similarity relationship among neighboring pixels. In this way, the obtained de-mixing matrix can produce the complete foreground compared with the previous ICA model. In addition, our method performs robust to the indoor illumination changes and features a high processing speed. Two sets of image sequences involving room lights switching on/of and door opening/closing are tested. The experimental results clearly demonstrate an improvement over the basic ICA model and the image difference method.

关键词： foreground detection contextual constraints indoor surveillance independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Background Modeling by Exploring Multi-scale Fusion of Texture and Intensity in complex Scenes

Background Modeling by Exploring Multi-scale Fusion of Textu...

引用

第一届亚洲模式识别会议

作者： Zhong Zhang Wen Zhou Chunheng Wang Baihua Xiao Shuang Liu State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automatio State Key Laboratory of Intelligent Control and Management of Complex SystemsInstitute of Automation

ISBN: (纸本)9781457701221

Background modeling is a fundamental yet challenging issue in video surveillance. Traditional methods usually adopt single feature type to solve the problem, while the performance is usually unsatisfactory when handling complex scenes. In this paper, we propose a multi-scale framework, which combines both texture and intensity feature, to achieve a robust and accurate solution. Our contributions are three folds: first, we provide a multi-scale analysis for the issue;second, for texture feature we propose a novel texture operator named Scale-invariant Centersymmetric Local Ternary Pattern, and a corresponding Pattern Adaptive Kernel Density Estimation technique for its probability estimation;third, we design a Simplified Gaussian Mixture Models for intensity feature. Our method is tested on several complex real world videos with illumination variation, soft shadows and dynamic backgrounds. The experimental results clearly demonstrate that our method is superior to the previous methods.

关键词： background modeling multi-scale fusion texture intensity

来源：评论

学校读者我要写书评

暂无评论

Polarity shifting: Corpus construction and analysis

Polarity shifting: Corpus construction and analysis

引用

2011 International Conference on Asian Language Processing, IALP 2011

作者： Zhang, Xiaoqian Li, Shoushan Zhou, Guodong Zhao, Hongxia Natural Language Processing Lab. Soochow University Suzhou China State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9780769545547

Polarity shifting has been a challenge to automatic sentiment classification. In this paper, we create a corpus which consists of polarity-shifted sentences in various kinds of product reviews. In the corpus, both the sentimental words and shifting trigger words are annotated. Furthermore, we analyze all the polarity shifted sentences and categorize them into five categories: opinion-itself, holder, target, time and hypothesis. Experimental study shows the agreement of annotation and the distribution of the five categories of polarity shifting. © 2011 IEEE.

关键词： corpus annotation polarity shifting sentiment classification

来源：评论

学校读者我要写书评

暂无评论

Evaluation indicator and models of time-varying traffic noise based on human feeling

Evaluation indicator and models of time-varying traffic nois...

引用

International Conference on Business Management and Electronic Information (BMEI)

作者： Zhang, Peng Shao, Chunfu Cai, Ming MOE Key Laboratory for Transportation Complex Systems Theory and Technology Beijing Jiaotong University Beijing China Research Center of Intelligent Transportation System Sun Yat-sen University Guangzhou China

ISBN: (纸本)9781612841069

Effects on human vary between uniform and time-varying traffic noise with the same equivalent sound level. Firstly, the subjective evaluation experiment of time-varying traffic noise is designed and implemented in this paper to get truthful data. Secondly, taking the gender, employment and mood factors into account, some conclusions about the effects of traffic noise with different time-varying characteristics on human are obtained based on the test results. Then the paper defines the disturbance degree of traffic noise on human as the subjective indicator of noise evaluation, represented by Lm. Finally, taking multiple existing noise indicators as inputs and Lm as output, three mathematical models are established using multiple regression, stepwise regression and artificial neural network analysis respectively. © 2011 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

An optimized modeling method based on BPEL4WS

An optimized modeling method based on BPEL4WS

引用

2011 IEEE International Conference on Service Operations, Logistics and Informatics, SOLI 2011

作者： Liu, Sheng Xiong, Gang Fan, Dong Yao, Jianshi State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Science Beijing 100190 China Chinese People's Liberation Army Beijing 100094 China

ISBN: (纸本)9781457705731

As an efficient business process execution language which supports web services, BPEL4WS is widely supported by the academic and the industrial circles. According to the shortcomings such as number of computer terms, abstract model definition and the complex description of people activity, this paper presents easy-to-use BPEL4WS modeling method and tool which encapsulates computer terms and convert business models to BPEL4WS models directly. In comparison to the other modeling methods, our method cut down the number of modeling elements by more than 85 percent and save the modeling time by 80 percent and accelerate model running by more than 40 percent. Thus it is more appropriate for popularization. © 2011 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

New method for recognition of circular traffic sign based on radial symmetry and pseudo-zernike moments

引用

Journal of Beijing Institute of Technology (English Edition) 2011年第4期20卷 520-526页

作者： Fu, Meng-Yin Huang, Yuan-Shui Ma, Hong-Bin Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing 100081 China

Recognizing various traffic signs, especially the popular circular traffic signs, is an essential task for implementing advanced driver assistance system. To recognize circular traffic signs with high accuracy and robustness, a novel approach which uses the so-called improved constrained binary fast radial symmetry (ICBFRS) detector and pseudo-zernike moments based support vector machine (PZM-SVM) classifier is proposed. In the detection stage, the scene image containing the traffic signs will be converted into Lab color space for color segmentation. Then the ICBFRS detector can efficiently capture the position and scale of sign candidates within the scene by detecting the centers of circles. In the classification stage, once the candidates are cropped out of the image, pseudo-zernike moments are adopted to represent the features of extracted pictogram, which are then fed into a support vector machine to classify different traffic signs. Experimental results under different lighting conditions indicate that the proposed method has robust detection effect and high classification accuracy. © Copyright.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Rank-SIFT: Learning to rank repeatable local interest points

Rank-SIFT: Learning to rank repeatable local interest points

引用

作者： Li, Bing Xiao, Rong Li, Zhiwei Cai, Rui Lu, Bao-Liang Zhang, Lei Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China Microsoft Research Asia Beijing 100190 China MOE Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9781457703942

Scale-invariant feature transform (SIFT) has been well studied in recent years. Most related research efforts focused on designing and learning effective descriptors to characterize a local interest point. However, how to identify stable local interest points is still a very challenging problem. In this paper, we propose a set of differential features, and based on them we adopt a data-driven approach to learn a ranking function to sort local interest points according to their stabilities across images containing the same visual objects. Compared with the handcrafted rule-based method used by the standard SIFT algorithm, our algorithm substantially improves the stability of detected local interest point on a very challenging benchmark dataset, in which images were generated under very different imaging conditions. Experimental results on the Oxford and PASCAL databases further demonstrate the superior performance of the proposed algorithm on both object image retrieval and category recognition. © 2011 IEEE.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Thrust analysis of the undulating ribbon-fin for biomimetic underwater robots

Thrust analysis of the undulating ribbon-fin for biomimetic ...

引用

International Conference on intelligent Control and Information Processing

作者： Wang, Shuo Dong, Xiang Shang, Liu-Ji State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Institute of Intelligent Machines Chinese Academy of Sciences P.O. Box 1130 Hefei City 230031 Anhui Province China

ISBN: (纸本)9781457708145

Biomimetic underwater robots have been paid more and more attention because of high efficiency, high maneuverability and low-noise. The undulating ribbon-fins used by rajiformes and gymnotiformes show better maneuverability than those of other fishes in turbulent water. So the undulating ribbon-fin propulsion is analyzed for biomimetic underwater robot design and optimization in the paper. The geometric model of the ribbon-fin is set up in Cartesian space. The undulating motion of the ribbon-fin is expressed in trigonometric functions. And the ribbon-fin has been divided into many small elements to compute the force acted on the small element. All the forces acted on the elements in one undulating period are summed, and the average thrust for one undulating period of the ribbon-fin is obtained. The simulation results show the influence of several important parameters on the ribbon-fin thrust. And an experimental platform is built and several experiments are carried out. And the difference between the results of simulation and experiment are discussed further. © 2011 IEEE.

关键词： Fins (heat exchange)

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：