检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Tao Zhou Xiangjian He Kai Xie Keren Fu Junhao Zhang Jie Yang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Faculty of Engineering and Information Technology University of Technology Sydney Australia

In this paper, a novel and robust tracking method based on efficient manifold ranking is proposed. For tracking, tracked results are taken as labeled nodes while candidate samples are taken as unlabeled nodes, and the goal of tracking is to search the unlabeled sample that is the most relevant with existing labeled nodes by manifold ranking algorithm. Meanwhile, we adopt non-adaptive random projections to preserve the structure of original image space, and a very sparse measurement matrix is used to efficiently extract low-dimensional compressive features for object representation. Furthermore, spatial context is used to improve the robustness to appearance variations. Experimental results on some challenging video sequences show the proposed algorithm outperforms six state-of-the-art methods in terms of accuracy and robustness.

关键词： Target tracking Manifolds Context Computational modeling Robustness Clutter

来源：评论

学校读者我要写书评

暂无评论

Visual tracking based on weighted subspace reconstruction error

Visual tracking based on weighted subspace reconstruction er...

引用

IEEE International Conference on image processing

作者： Tao Zhou Junhao Zhang Kai Xie Jie Yang Xiangjian He Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Faculty of Engineering and Information Technology University of Technology Sydney Australia

ISBN: (纸本)9781479957521

It is a challenging task to develop an effective and robust visual tracking method due to factors such as pose variation, illumination change, occlusion, and motion blur. In this paper, a novel tracking algorithm based on weighted subspace reconstruction error is proposed. We first compute the discriminative weights by sparse construction error with template dictionary consisted of positive and negative samples, and then confidence map for candidates is computed through subspace reconstruction error. Finally, the location of the target object is estimated by maximizing the decision map which is combined discriminative weights and subspace reconstruction error. Furthermore, we use the new evaluation criterion to verify the robustness of the current tracking result, which can reduce the accumulated error effectively. Experimental results on some challenging video sequences show that the proposed algorithm performs favorably against seven state-of-the-art methods in terms of accuracy and robustness.

关键词： Target tracking Dictionaries Robustness image reconstruction Visualization Computer vision

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

EFFECTIVE SMALL DIM TARGET DETECTION BY LOCAL CONNECTEDNESS CONSTRAINT

EFFECTIVE SMALL DIM TARGET DETECTION BY LOCAL CONNECTEDNESS ...

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Keren Fu Kai Xie Chen Gong Irene Y.H. Gu Jie Yang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Department of Signals and Systems Chalmers University of Technology Gothenburg Sweden

ISBN: (纸本)9781479928941

The main drawback of conventional filtering based methods for small dim target (SDT) detection is they could not guarantee sufficient suppression ability towards trivial high frequency component which belongs to background, such as strong corners and edges. To overcome this bottleneck, this paper proposes an effective SDT detection algorithm by using local connectedness constraint. Our method provides direct control for target size, ensure high accuracy and could be easily embedded into the classical sliding-window based framework. The effectiveness of the proposed method is validated using images with cluttered background.

关键词： Object detection Direct control clutter background images sliding windows Detection algorithms BACKGROUND

来源：评论

学校读者我要写书评

暂无评论

Estimation of distribution algorithm for the Max-Cut problem

Estimation of distribution algorithm for the Max-Cut problem

引用

9th IAPR-TC-15 International Workshop on Graph-Based Representations in pattern recognition, GbRPR 2013

作者： De Sousa, Samuel Haxhimusa, Yll Kropatsch, Walter G. Vienna University of Technology Pattern Recognition and Image Processing Group Vienna Austria

ISBN: (纸本)9783642382208

In this paper, we investigate the Max-Cut problem and propose a probabilistic heuristic to address its classic and weighted version. Our approach is based on the Estimation of Distribution Algorithm (EDA) that creates a population of individuals capable of evolving at each generation towards the global solution. We have applied the Max-Cut problem for image segmentation and defined the edges' weights as a modified function of the L2 norm between the RGB values of nodes. The main goal of this paper is to introduce a heuristic for Max-Cut and additionally to investigate how it can be applied in the segmentation context. © 2013 Springer-Verlag.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Structural cues in 2D tracking: Edge lengths vs. barycentric coordinates 1

引用

18th Iberoamerican Congress on pattern recognition, CIARP 2013

作者： Artner, Nicole M. Kropatsch, Walter G. Vienna University of Technology Pattern Recognition and Image Processing Group Vienna Austria

ISBN: (数字)9783642418273

ISBN: (纸本)9783642418266

Graph models offer high representational power and useful structural cues. Unfortunately, tracking objects by matching graphs over time is in general NP-hard. Simple appearance-based trackers are able to find temporal correspondences fast and efficient, but often fail to overcome challenging situations like occlusions, distractors and noise. This paper proposes an approach, where an attributed graph is used to represent the structure of the target object and multiple, simple trackers in combination with structural cues replace the costly graph matching. Thus, the strengths of both methodologies are combined to overcome their weaknesses. Experiments based on synthetic videos are used to evaluate two possible structural cues. Results show the superiority of the cue based on barycentric coordinates and the potential of the proposed tracking approach in challenging situations. © Springer-Verlag 2013.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the evaluation of graph centrality for shape matching

On the evaluation of graph centrality for shape matching

引用

9th IAPR-TC-15 International Workshop on Graph-Based Representations in pattern recognition, GbRPR 2013

作者： De Sousa, Samuel Artner, Nicole M. Kropatsch, Walter G. Vienna University of Technology Pattern Recognition and Image Processing Group Vienna Austria

ISBN: (纸本)9783642382208

Graph centrality has been extensively applied in Social Network Analysis to model the interaction of actors and the information flow inside a graph. In this paper, we investigate the usage of graph centralities in the Shape Matching task. We create a graph-based representation of a shape and describe this graph by using different centrality measures. We build a Naive Bayes classifier whose input feature vector consists of the measurements obtained by the centralities and evaluate the different performances for each centrality. © 2013 Springer-Verlag.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Spectral salient object detection

Spectral salient object detection

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Keren Fu Chen Gong Irene Y. H. Gu Jie Yang Xiangjian He Department of Signals and Systems Chalmers University of Technology Gothenburg Sweden Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Faculty of Engineering University of Technology Sydney Australia

Many existing methods for salient object detection are performed by over-segmenting images into non-overlapping regions, which facilitate local/global color statistics for saliency computation. In this paper, we propose a new approach: spectral salient object detection, which is benefited from selected attributes of normalized cut, enabling better retaining of holistic salient objects as comparing to conventionally employed pre-segmentation techniques. The proposed saliency detection method recursively bi-partitions regions that render the lowest cut cost in each iteration, resulting in binary spanning tree structure. Each segmented region is then evaluated under criterion that fit Gestalt laws and statistical prior. Final result is obtained by integrating multiple intermediate saliency maps. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method against 13 state-of-the-art approaches to salient object detection.

关键词： image segmentation image color analysis Principal component analysis Object detection Visualization Educational institutions image edge detection

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Pencil of Conics with Double Complex Contact and Its Application to Camera Calibration

引用

Journal of Shanghai Jiaotong university(Science) 2013年第1期18卷 1-6页

作者：蔡琴王宸昊阎炎刘允才 Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Information and Communication Technology Department University of Trento

In this paper, we introduce a novel class of coplanar conics, the pencil of which can doubly contact to calibrate camera and estimate pose. We first analyze the properties of con-axes and con-eccentricity ellipses, which consist of a naturM extending pattern of concentric circles. Then the general case that two ellipses have two repeated complex intersection points is presented. This degenerate configuration results in a one-parameter family of homographies which map the planar pattern to its image. Although it is unable to compute the complete homography, an indirect 3-degree polynomial or 5-degree polynomial constraint on intrinsic parameters from one image can also be used for camera calibration and pose estimation under the minimal conditions. Furthermore, this nonlinear problem can be treated as a polynomial optimization problem （POP） and the global optimization solution can be also obtained by using SparsePOP （a sparse semidefinite programming relaxation of POPs）, Finally, the experiments with simulated data and real images are shown to verify the correctness and robustness of the proposed technique.

关键词： camera calibration homography con-axes and con-eccentricity ellipse concentric circle polynomial optimization problem （POP）

来源：评论

学校读者我要写书评

暂无评论

Graph Construction for Salient Object Detection in Videos

Graph Construction for Salient Object Detection in Videos

引用

International Conference on pattern recognition

作者： Keren Fu Irene Y.H. Gu Yixiao Yun Chen Gong Jie Yang Shanghai Jiao Tong University Shanghai CN Department of Signals and Systems Chalmers University of Technology Gothenburg Sweden Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)9781479952106

Recently many graph-based salient region/object detection methods have been developed. They are rather effective for still images. However, little attention has been paid to salient region detection in videos. This paper addresses salient region detection in videos. A unified approach towards graph construction for salient object detection in videos is proposed. The proposed method combines static appearance and motion cues to construct graph, enabling a direct extension of original graph-based salient region detection to video processing. To maintain coherence in both intra- and inter-frames, a spatial-temporal smoothing operation is proposed on a structured graph derived from consecutive frames. The effectiveness of the proposed method is tested and validated using seven videos from two video datasets.

关键词： Videos Smoothing methods Optical imaging Object detection Histograms Integrated optics Manifolds

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：