检索结果-内蒙古大学图书馆

Chinese Control Conference (CCC)

作者： Yawen Yang Zhang Peng Peng Yu Qiao Jie Yang Sheng Zheng Wang The Key Laboratory of Ministry of Education for System Control and Information Processing Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai CN Merchant Marine College Shanghai Maritime University Shanghai CN

Point matching is an important component of image registration. Recent years, Coherent Point Drift (CPD) method becomes a very popular point matching approach. CPD treats point matching as a probability estimation problem and speeds up the process of matching a lot. In this method, one set of points are thought to be sampled from a Gaussian Mixture Model (GMM), which is centered by the other set of points. However, CPD is sensitive to outliers and noises, especially when the noise ratio increased or the number of outliers gets much high. To deal with this problem, we introduce shape context into the step of searching for matching points and then improve the form of prior probabilities of GMM in this paper. The main idea of our method is that if the most points in a data set are likely to be matched to a particular centroid, this Gaussian component should be have a more influence to GMM. Therefore, we set prior probability of GMM with the similarity between GMM components and the data set. And the computation of similarity is based on shape context. The experiments on 2D and 3D images show that when noise ratio is low, our method performs as well as CPD does, but as the ratio increased, our method is more robust and satisfactory than CPD.

关键词： Noise Shape Testing Context Robustness Three-dimensional displays Marine animals

来源：评论

学校读者我要写书评

暂无评论

Multiple model particle filter with correlated measurement and process noise

引用

Journal of Information and Computational Science 2013年第4期10卷 1179-1186页

作者： Hu, Zhentao Li, Song Liu, Xianxing Li, Jie Institute of Image Processing and Pattern Recognition Henan University Kaifeng 475004 China

Aiming at adverse influence of the correlation between measurement and process noise for filtering precision, a new multiple model particle filtering algorithm with correlated measurement noise and process noise is proposed. Firstly, multiple model particle filter is used as the basic framework realization of new algorithm, and the objective is to deal with the multi-mode problem in estimated system with less the calculated amount. Secondly, in order to avoid adverse influence from the correlation between measurement and process noise for filtering precision, the system model is modified by rearrange the state transition equation and measurement equation, and a novel decoupling method of correlated noise is given. Finally, experimental results show that the proposed method outperforms the general IMM-PF and MMPF when the measurement and process noise is with correlated characteristics. © 2013 by Binary Information Press.

关键词： Equations of state

来源：评论

学校读者我要写书评

暂无评论

Marginalized particle filtering algorithm in correlated noise

引用

Journal of Computational Information Systems 2013年第1期9卷 17-24页

作者： Hu, Zhentao Yang, Yiping Li, Jie Liu, Xianxing Institute of Image Processing and Pattern Recognition Henan University Kaifeng 475004 China

The particle filter offers a general numerical tool to approximate the posterior density function for the state in nonlinear and non-Gaussian filtering problems. While the particle filter is fairly easy to implement and tune, its main drawback is that its computational complexity increase quickly with the state dimension. By exploiting conditional dependencies between parts of the state to estimate, marginalized particle filter can improve the estimation quality while also reducing the overall computational load relative to standard PF. However, whether marginalized particle filter or other improving particle filters, process noise and observation noise are all supposed as the independent identical distribution. It will limit greatly the application field of sampling nonlinear filter. Aiming at the above problem, a decouple method of noise is structured by the rearrange and transformation of state transition equation and observation equation. Meanwhile, the decouple method is dynamically introduced into the framework of marginalized particle filter. Because the treatment for the computation-al complexity and correlation of noise are considered, the real-time and the filtering precision are obviously improved. Finally, the theoretical analysis and experimental results show the feasibility and efficiency of the proposed algorithm. © 2013 Binary Information Press.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

Real-Time Full Frame Video Stabilization

Real-Time Full Frame Video Stabilization

引用

2012 International Conference on Applied Informatics and Communication(ICAIC 2012)

作者： Dacheng Song Xiaogang Chen Jie Yang 800 Dongchuan RD.Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University

This paper proposes a three-layer model for full frame video *** is practical for real time full frame processing where the smoothness of intentional camera motion is *** undefined pixels in stabilized frame are filled by pixels in previous frames *** traditional methods that all neighboring frames are required to be stored and registered with current frame,the proposed algorithm only stores single updated mosaic image for video *** runs significantly faster than previous *** efficacy has been demonstrated by real experiments.

关键词： Video stabilization,Video completion,Camera motion estimation.

来源：评论

学校读者我要写书评

暂无评论

Density-Aware Part-Based Object Detection with Positive Examples

Density-Aware Part-Based Object Detection with Positive Exam...

引用

International Conference on pattern recognition

作者： Ekaterina Riabchenko Joni-Kristian Kämäräinen Ke Chen Machine Vision and Pattern Recognition Laboratory Lappeenranta University of Technology Deparment of Signal Processing Tampere University of Technology

ISBN: (纸本)9781479952106

Part-based models have become the mainstream approach for visual object classification and detection. The key tools adopted by the most methods are interest point detectors and descriptors, shared codes for object parts (visual codebook) and discriminative learning using positive and negative class examples. Distinction of our method from the existing part-based methods for object detection is the use of sparse class-specific landmarks with semantic meaning. The landmarks are the additional distinguished information of object location in the proposed framework. Additionally, localising semantic and discriminative landmarks (object parts) is significant in other related applications of computer vision, such as facial expression recognition and pose/orientation estimation of objects. Therefore, we propose a model which deviates from the mainstream by the fact that the object parts' appearance and spatial variation, constellation, are explicitly modelled in a generative probabilistic manner. With using only positive examples our method can achieve object detection accuracy comparable to state-of-the-art discriminative method.

关键词： Training Probabilistic logic Estimation Face Feature extraction Object detection Detectors

来源：评论

学校读者我要写书评

暂无评论

Water Molecules Diffusion in Diffusion Weighted Imaging

Water Molecules Diffusion in Diffusion Weighted Imaging

引用

第三届健康信息学国际学术会议（HIS 2014）

作者： Fan Zhang Zhiwei Cao Xinhong Zhang Kui Cao Institute of Image Processing and Pattern Recognition Henan University School of Computer and Information Engineering Henan University Software School Henan University

In the studying of fibers microstructure of brain white matter,many reconstruction methods have been proposed to interpret the diffusion-weighted signalThose methods can be categorized into modelbased and model-free methodsIn this paper,the diffusion configuration of water molecules are discussed,and two questions are put forward to analyze the performance of the current algorithms about diffusion configuration.

关键词： diffusion weighted MRI,diffusion configuration,fibers microstructure

来源：评论

学校读者我要写书评

暂无评论

Learning Generative Models of Object Parts from a Few Positive Examples

Learning Generative Models of Object Parts from a Few Positi...

引用

International Conference on pattern recognition

作者： Ekaterina Riabchenko Joni-Kristian Kämäräinen Ke Chen Machine Vision and Pattern Recognition Laboratory Lappeenranta University of Technology Department of Signal Processing Tampere University of Technology

ISBN: (纸本)9781479952106

A number of computer vision problems such as object detection, pose estimation, and face recognition utilise local parts to represent objects, which include the distinguished information of objects. In this work, we introduce a novel probabilistic framework which automatically learns class-specific object parts (landmarks) in generative-learning manner. Encouraged by the success in learning and detecting facial landmarks, we employ bio-inspired multi-resolution Gabor features in the proposed framework. Specifically, complex-valued Gabor filter responses are first transformed to landmark specific likelihoods using Gaussian Mixture Models (GMM), and then efficient response matrix shift operations provide detection over orientations and scales. We avoid the undesirable characteristic of generative learning, a large number of training instances, with the novel concept of randomised Gaussian mixture model. Extensive experiments with public benchmarking Caltech-101 and BioID datasets demonstrate the effectiveness of our proposed method for localising object landmarks.

关键词： Feature extraction Gaussian mixture model Face Training Motorcycles Estimation

来源：评论

学校读者我要写书评

暂无评论

VIOLENT VIDEO DETECTION BASED ON MoSIFT FEATURE AND SPARSE CODING

VIOLENT VIDEO DETECTION BASED ON MoSIFT FEATURE AND SPARSE C...

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Long Xu Chen Gong Jie Yang Qiang Wu Lixiu Yao Institution of Image Processing and Pattern Recognition Shanghai Jiao Tong University China School of Computing and Communications University of Technology Sydney Australia

ISBN: (纸本)9781479928941

To detect violence in a video, a common video description method is to apply local spatio-temporal description on the query video. Then, the low-level description is further summarized onto the high-level feature based on Bag-of-Words (BoW) model. However, traditional spatio-temporal descriptors are not discriminative enough. Moreover, BoW model roughly assigns each feature vector to only one visual word, therefore inevitably causing quantization error. To tackle the constrains, this paper employs Motion SIFT (MoSIFT) algorithm to extract the low-level description of a query video. To eliminate the feature noise, Kernel Density Estimation (KDE) is exploited for feature selection on the MoSIFT descriptor. In order to obtain the highly discriminative video feature, this paper adopts sparse coding scheme to further process the selected MoSIFTs. Encouraging experimental results are obtained based on two challenging datasets which record both crowded scenes and non-crowded scenes.

关键词： Videotapes Eigenvector Quantization Feature extraction Violence BOW labeling scheme High-level features LOW LEVEL

来源：评论

学校读者我要写书评

暂无评论

Shadow detection using regression tree fields with paired regions

引用

Journal of Computational Information Systems 2013年第11期9卷 4309-4317页

作者： Tao, Wei Zhou, Yue Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai 200240 China

In this paper, we try to deal with the problem of shadow detection from static images and video sequences. In instead to considering individual regions separately, we use relative illumination conditions between segmented regions and perform pair-wise classification based on such information. We use Regression Tree Fields to solve the labeling of shadow and non-shadow regions. And we use continuous value to describe the possibility of the shadow of the region. We evaluate our method on static images and a series of video sequences. © 2013 by Binary Information Press.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Text-independent writer identification by feature fusion

Text-independent writer identification by feature fusion

引用

International Conference on Intelligent Control and Information processing (ICICIP)

作者： Yongjie Hu Wenming Yang Youbin Chen Department of Electronic Engineering of Tsinghua University Zhejiang University Research interests include digital image processing and computer vision Department of Electronic Engineering of Tsinghua University Research interests include digital image processing and pattern recognition

ISBN: (纸本)9781479936519

This paper explores text-independent writer identification by combining Bag of Features (BoF), contour-hinge and SIFT scales feature. The BoF method adopted differs from the common BoF approach for writer identification in that it extracts SIFT descriptors and uses Locality-constrained Linear Coding to get feature vector of each document. The Locality-constrained Linear Coding (LLC) tries to reconstruct each feature through locality constraint and has much more discriminative power than the common used Vector Quantization (VQ). Contour-hinge feature can capture orientation and curvature of the ink trace. Modification is made to the original contour-hinge to improve the identification rate. Besides, we also use SIFT scale information and integrate these three kinds of features together. Experiments are conducted the challenging ICDAR2013 writer identification contest dataset and dataset for "ICFHR2012 Writer Identification Contest, Challenge 1: Latin Documents". The experiment results show that the proposed BoF approach outperforms the common ones that adopt VQ, and after the integration, our method achieves the best result on the entire ICDAR2013 and ICFHR2012 dataset under soft evaluation.

关键词： Feature extraction Vectors Encoding image reconstruction Text analysis Educational institutions

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：