检索结果-内蒙古大学图书馆

3rd International Conference on Innovative Network Systems and Applications (iNetSApp) held in conjunction with Federated Conference on Computer Science and Information Systems (FedCSIS)

作者： Owczarek, Mateusz Baranski, Przemyslaw Strumillo, Pawel Lodz Univ Technol Inst Elect Lodz Poland

ISBN: (纸本)9788360810668

In this work we study the methods for pedestrian tracking in video sequences and indicate various applications of these methods ranging from surveillance systems to aiding the visually impaired persons. First, we define the general problem of object tracking that comprises the tasks of object detection, identifying the flow of object location in consecutive video images and finally analysis of the tracked trajectory data. We review the well known object tracking techniques i. e. the mean-shift and the CAMshift algorithm and discuss their properties. Then we introduce the computational technique known as particle filtering (PF) and explain how we have applied it to the tasks of pedestrian tracking. We compare the PF approach against the mean-shift and the CAMshift algorithms in terms of tracking robustness and the required computational demand. We conclude, that on the tested video sequences, the PF tracker outperforms the mean-shift and by a small margin the CAMshift algorithm. The PF tracker requires more computational power, however, its tracking performance can be flexibly adjusted to the application requirements.

关键词： image sequences object detection object tracking particle filtering (numerical methods) pedestrians video signal processing PF approach application requirements camshift algorithm computational demand computational power mean-shift algorithm object tracking techniques particle filtering approach pedestrian tracking surveillance systems trajectory data video sequences visually impaired persons Cameras Histograms Object detection Object tracking Target tracking Video sequences

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation Using Linked mean-shift Vectors and Its Implementation on GPU

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2014年第4期60卷 719-727页

作者： Cho, Hanjoo Kang, Suk-Ju Cho, Sung In Kim, Young Hwan Pohang Univ Sci & Technol POSTECH Dept Elect Engn Pohang 790784 South Korea Dong A Univ Dept Elect Engn Pusan 604714 South Korea POSTECH Dept Elect Engn Pohang 790784 South Korea POSTECH Dept Elect Engn & Creat IT Engn Pohang 790784 South Korea

This paper proposes a new approach to mean-shift-based image segmentation that uses a non-iterative process to determine the maxima of the underlying density, which are called modes. To identify the mode, the proposed approach performs a mean-shift process on each pixel only once, and uses the resulting mean-shift vectors to construct links for the pairs of pixels, instead of iteratively performing the mean-shift process. Then, it groups the pixels of the same mode, connected through the links, into the same cluster. Although the proposed approach performs the mean-shift process only once, it provides comparable segmentation quality to the conventional approaches. In experiments using benchmark images, the processing time was reduced to a quarter, while probabilistic rand index and segmentation covering were well maintained;they were degraded by only 0.38% and 1.87%, respectively. Furthermore, the proposed algorithm improves the locality of the required data and compute-intensity of the algorithm, which are important factors for utilizing the GPU effectively. The proposed algorithm, when implemented on a GPU, improved the processing speed by over 75 times compared to implementation on a CPU, while the conventional approach was accelerated by about 15 times(1).

关键词： mean-shift algorithm parallel processing image segmentation

来源：评论

学校读者我要写书评

暂无评论

Object Tracking using KLT aided mean-shift Object Tracker (ICCAS 2014) 14

Object Tracking using KLT aided Mean-shift Object Tracker (I...

引用

14th International Conference on Control, Automation and Systems (ICCAS)

作者： Kim, Sun-Ho Kim, Jungho Hwang, Youngbae Choi, Byoungho Yoon, Ju Hong Korea Elect Technol Inst Multimedia IP Ctr Pangyo 463400 South Korea

ISBN: (纸本)9788993215069

In this paper, we present a new object tracking algorithm which integrates color-based mean-shift and feature-based optical flow methods. To utilize two approaches in the complimentary manner, we iteratively compute the mean-shift vector based on color histograms and tracked features by KLT. In the experiments, we show the improved performance for partial occlusion and severe appearance changes in the representative benchmark sequences.

关键词： mean-shift algorithm Kanade-Lucas-Tomasi algorithm Object Tracking

来源：评论

学校读者我要写书评

暂无评论

Including the Size of Regions in Image Segmentation by Region-Based Graph

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2014年第2期23卷 635-644页

作者： Rezvanifar, Alireza Khosravifard, Mohammadali Isfahan Univ Technol Dept Elect & Comp Engn Esfahan *** Iran

Applying a fast over-segmentation algorithm to image and working on a region-based graph (instead of the pixel-based graph) is an efficient approach to reduce the computational complexity of graph-based image segmentation methods. Nevertheless, some undesirable effects may arise if the conventional cost functions, such as Ncut, AverageCut, and MinCut, are employed for partitioning the region-based graph. This is because these cost functions are generally tailored to pixel-based graphs. In order to resolve this problem, we first introduce a new class of cost functions (containing Ncut and AverageCut) for graph partitioning whose corresponding suboptimal solution can be efficiently computed by solving a generalized eigenvalue problem. Then, among these cost functions, we propose one that considers the size of regions in the partitioning procedure. By simulation, the performance of the proposed cost function is quantitatively compared with that of the Ncut and AverageCut.

关键词： Graph-based image segmentation Ncut AverageCut spectral clustering region-based graph mean-shift algorithm

来源：评论

学校读者我要写书评

暂无评论

Hardware Development and Implementation of an Object Tracking algorithm for UAV Applications

Hardware Development and Implementation of an Object Trackin...

引用

2015 International Conference on Image Processing, Production and Computer Science (ICIPCS’2015);2015 International Conference on Chemical, Metallurgy and Environmental Engineering (ICCMEE-15);International Conference on Innovations in Civil and Structural Engineering (ICICSE’15)

作者： Senthil Kumar K Mohamed Rasheed A Vairamanikandan K Department of Aerospace Engineering Division of AvionicsMadras Institute of TechnologyAnna University

The task of reliably detecting and tracking the moving objects in surveillance video forms a basis for higher level intelligence applications. This project aim is to develop the Hardware and to implement an object tracking algorithm. The tracking technique uses CAMshift algorithm to detect moving objects and generate reliable tracks from real-time surveillance video. In mean shift algorithm there are many limitations and one of the most important is that the window remains the same size when object is farther away or very close to camera, so it is necessary to adapt the window size with target size and rotation. The solution for this problem is Continuously Adaptive mean shift algorithm. It applies mean shift first, once mean shift converges it updates the size of the window. It also calculates the orientation of best fitting ellipse to it. Again it applies the mean shift with new scaled search window and previous window location. Window adaptation keeps continuing throughout of Tracking. This Tracking technique is implemented in arduino hardware with Pan-Tilt mechanism. Raspberry Pi is also used to implement CAMshift algorithm here. Raspberry Pi is widely used for video processing and it is fit for UAV related surveillance applications as it has less weight with more functionality for video processing. Pan-Tilt mechanism is made by using two servo motors. Here, Pan-Tilt mechanism is used for real-time tracking of the target. For UAV application, overall communication for real-time tracking is also taken care by Raspberry Pi.

关键词： Surveillance Hardware CAMshift algorithm mean-shift algorithm Raspberry Pi Pan-tilt UAV

来源：评论

学校读者我要写书评

暂无评论

Planar Clustering algorithm Based on RGB-D Data Fusion

Planar Clustering Algorithm Based on RGB-D Data Fusion

引用

Chinese Automation Congress (CAC)

作者： Huang Zhongyi Li Jiansheng Hao Xiangyang Wang Teng Yan Libo Informat Engn Univ Dept Nav & Aerosp Engn Zhengzhou Peoples R China

ISBN: (纸本)9781467371896

Plane detection is one of the frame works to the intelligent navigation of unmanned vehicles. In this article, a Kinect camera is used in the smart navigation field. We segment the RGB image first using a mean-shift algorithm and project three-dimensional point cloud, which is based on depth image, to segmented image. Then we cluster the whole plane area according the characteristics of the three-dimensional points set. The experiments show that the method can cluster plane from complex environments, and has a significant meaning to obstacle detection and intelligent avoidance of the next step.

关键词： Plane clustering panel Kinect Camera mean-shift algorithm 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

γ-SUP: A CLUSTERING algorithm FOR CRYO-ELECTRON MICROSCOPY IMAGES OF ASYMMETRIC PARTICLES

引用

ANNALS OF APPLIED STATISTICS 2014年第1期8卷 259-285页

作者： Chen, Ting-Li Hsieh, Dai-Ni Hung, Hung Tu, I-Ping Wu, Pei-Shien Wu, Yi-Ming Chang, Wei-Hau Huang, Su-Yun Acad Sinica Inst Stat Sci Taipei 11529 Taiwan Natl Taiwan Univ Inst Epidemiol & Prevent Med Taipei 10055 Taiwan Duke Univ Dept Biostat & Bioinformat Durham NC 27710 USA

Cryo-electron microscopy (cryo-EM) has recently emerged as a powerful tool for obtaining three-dimensional (3D) structures of biological macromolecules in native states. A minimum cryo-EM image data set for deriving a meaningful reconstruction is comprised of thousands of randomly orientated projections of identical particles photographed with a small number of electrons. The computation of 3D structure from 2D projections requires clustering, which aims to enhance the signal to noise ratio in each view by grouping similarly oriented images. Nevertheless, the prevailing clustering techniques are often compromised by three characteristics of cryo-EM data: high noise content, high dimensionality and large number of clusters. Moreover, since clustering requires registering images of similar orientation into the same pixel coordinates by 2D alignment, it is desired that the clustering algorithm can label misaligned images as outliers. Herein, we introduce a clustering algorithm gamma-SUP to model the data with a q-Gaussian mixture and adopt the minimum gamma-divergence for estimation, and then use a self-updating procedure to obtain the numerical solution. We apply gamma-SUP to the cryo-EM images of two benchmark macromolecules, RNA polymerase II and ribosome. In the former case, simulated images were chosen to decouple clustering from alignment to demonstrate gamma-SUP is more robust to misalignment outliers than the existing clustering methods used in the cryo-EM community. In the latter case, the clustering of real cryo-EM data by our gamma-SUP method eliminates noise in many views to reveal true structure features of ribosome at the projection level.

关键词： Clustering algorithm cryo-EM images gamma-divergence k-means mean-shift algorithm multilinear principal component analysis q-Gaussian distribution robust statistics self-updating process

来源：评论

学校读者我要写书评

暂无评论

Human Recognition Based on Head-shoulder Contour Extraction and BP Neural Network

Human Recognition Based on Head-shoulder Contour Extraction ...

引用

International Symposium on Optoelectronic Technology and Application (IPTA) - Image Processing and Pattern Recognition

作者： Kong Xiao-fang Wang Xiu-qin Gu Guo-hua Chen Qian Qian Wei-xian Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing 210094 Jiangsu Peoples R China Xian North Photoelect Co Ltd Xian 710043 Peoples R China

ISBN: (纸本)9781628413878

In practical application scenarios like video surveillance and human-computer interaction, human body movements are uncertain because the human body is a non-rigid object. Based on the fact that the head-shoulder part of human body can be less affected by the movement, and will seldom be obscured by other objects, in human detection and recognition, a head-shoulder model with its stable characteristics can be applied as a detection feature to describe the human body. In order to extract the head-shoulder contour accurately, a head-shoulder model establish method with combination of edge detection and the mean-shift algorithm in image clustering has been proposed in this paper. First, an adaptive method of mixture Gaussian background update has been used to extract targets from the video sequence. Second, edge detection has been used to extract the contour of moving objects, and the mean-shift algorithm has been combined to cluster parts of target's contour. Third, the head-shoulder model can be established, according to the width and height ratio of human head-shoulder combined with the projection histogram of the binary image, and the eigenvectors of the head-shoulder contour can be acquired. Finally, the relationship between head-shoulder contour eigenvectors and the moving objects will be formed by the training of back-propagation (BP) neural network classifier, and the human head-shoulder model can be clustered for human detection and recognition. Experiments have shown that the method combined with edge detection and mean-shift algorithm proposed in this paper can extract the complete head-shoulder contour, with low calculating complexity and high efficiency.

关键词： Head-shoulder contour extraction Edge detection mean-shift algorithm BP neural network

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Tracking Based on Improved Level Set algorithm

Hand Gesture Tracking Based on Improved Level Set Algorithm

引用

2015 International Conference on Artificial Intelligence and Industrial Engineering(AIIE 2015)

作者： N.G.Yu F.F.Mo M.Guo X.G.Ruan Department of Electronic information and Control Engineering Beijing University of Technology

ISBN: (纸本)9781510806450

The tracking and extraction the hand pose is the previous work of gesture analysis. I n this paper, a mixed Gauss model based level set contour extraction algorithm is presented. The algorithm combined with the mean shift algorithm to achieve the extraction of hand contour dynamically in a video sequence. This method first get the initial contour by color information, and build Gaussian model of the inside and outside of the outline of the image features by using Gaussian mixture model. Depending on the characteristics of the Gaussian distribution and combining with active contour algorithm for image segmentation,then obtaining hand movement position by mean shift algorithm, we achieved gesture tracking. The test results show that compared to pixel-based active contour algorithm, this method has greater stability, which can get more accurate extraction region and achieve accurate contour extraction and gesture tracking.

关键词： active contour mean-shift algorithm edge detection hand tracking

来源：评论

学校读者我要写书评

暂无评论

Nonparametric Change Detection in Multitemporal SAR Images Based on mean-shift Clustering

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2013年第4期51卷 2022-2031页

作者： Aiazzi, Bruno Alparone, Luciano Baronti, Stefano Garzelli, Andrea Zoppetti, Claudia Natl Res Council IFAC CNR N Carrara Inst Appl Phys I-50019 Sesto Fiorentino Italy Univ Florence Dept Informat Engn DINFO I-50139 Florence Italy Univ Siena Dept Informat Engn & Math Sci I-53100 Siena Italy

A nonparametric method for unsupervised change detection in multipass synthetic aperture radar (SAR) imagery is described. The method relies on a novel feature capturing the structural change between two SAR images and is robust to the statistical change that may be originated by speckle and coregistration inaccuracies. The proposed method starts from the scatterplot of the amplitude levels in the two images and applies the mean-shift (MS) algorithm to find the modes of the underlying bivariate distribution. If we assume that the two images have been preliminarily coregistered and calibrated on one another, then all the modes lying outside the main diagonal correspond to the structural changes across the two observations. The value of the probability density function (PDF) in any of the off-diagonal modes found by the MS algorithm is translated into a value of conditional information. This value is assigned to all image pixels generating the corresponding cluster in the scatterplot. Thus, a feature is obtained on a per-pixel basis. Experimental results on simulated changes and true SAR images acquired by the COSMO-SkyMed satellite constellation show that the proposed feature exhibits significantly better discrimination capability than the classical log-ratio (LR). Advantages over a preliminary version of the method without MS regularization and over another nonparametric method based on Kullback-Leibler divergence are also demonstrated. The method is robust when it is applied to SAR images with different acquisition angles, whose effects are deemphasized compared to the actual scene changes.

关键词： Change detection information-theoretic features mean-shift algorithm multitemporal images nonparametric methods synthetic aperture radar (SAR)

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：