检索结果-内蒙古大学图书馆

IEEE Intelligent vehicles Symposium

作者： Marc Tschentscher Ben Pruss Daniela Horn University of Bochum Institute for Neural Computation

ISBN: (纸本)9781509048052

Developing image-processing algorithms based on machine learning is a challenging problem concerning the huge amount of thoroughly annotated data needed. The internet provides many already tagged images for basic classification problems like vegetables or different cars, but not for more narrow problems. In order to extend and evaluate the previously presented parking guidance system from our previous work, in this paper, we propose a simulation system based on Unreal Engine 4. We developed an artificial camera which implements all features of a real camera, e.g., lens distortion, motion blur etc. to export video data from the simulated environment. This data is then compared to real-world video footage by using our classification module that distinguishes occupied and free parking lots. We reached a classification rate between 92.28% and 99.72% depending on the parking rows' distance using DoG-features and a support vector machine.

关键词： sort module Simulation systems videotapes Support vector Network Parking video data Internets Cameras image processing algorithm parking lots Simulated Environment motion blur

来源：评论

学校读者我要写书评

暂无评论

Low-cost dedicated hardware IP modules for background subtraction in embedded vision systems

引用

JOURNAL OF REAL-TIME image processing 2016年第4期12卷 681-695页

作者： Calvo-Gallego, Elisa Brox, Piedad Sanchez-Solano, Santiago CSIC Univ Seville Inst Microelect Sevilla IMSE CNM Seville Spain Univ Seville Dept Elect & Electromagnetism Seville Spain

This paper presents the design and implementation of dedicated hardware IP modules for background subtraction, which are suitable to be implemented in embedded vision systems and are efficient in terms of performance, resource consumption, and operational speed. To achieve this goal, a comprehensive experimental study of different algorithms has been carried out by evaluating a wide range of quality parameters. From the results of this analysis, five candidate algorithms were selected and implemented using a model-based design methodology supported by Matlab and Xilinx FPGA tools. Using only the internal block memory available in the FPGA, they provide adequate solutions for processing low-resolution images with CIF and QCIF formats.

关键词： Embedded vision systems Background subtraction Hardware implementation

来源：评论

学校读者我要写书评

暂无评论

visual Clustering based on Kernel Sparse Representation on Grassmann Manifolds

Visual Clustering based on Kernel Sparse Representation on G...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent systems

作者： Tianci Liu Zelin Shi Yunpeng Liu Key Laboratory of Opto-Electronic Information Processing CAS Shenyang 110016

ISBN: (纸本)9781538604915

image sets and videos can be modeled as subspaces which are actually points on Grassmann manifolds. Clustering of such visual data lying on Grassmann manifolds is a hard issue based on the fact that the state-of-the-art methods are only applied to vector space instead of non-Euclidean geometry. In this paper, we propose a novel algorithm termed as kernel sparse subspace clustering on the Grassmann manifold (GKSSC) which embeds the Grassmann manifold into a Reproducing Kernel Hilbert Space (RKHS) by an appropriate Gaussian projection kernel. This kernel is applied to obtain kernel sparse representations of data on Grassmann manifolds utilizing the self-expressive property and exploiting the intrinsic Riemannian geometry within data. Although the Grassmann manifold is compact, the geodesic distances between Grassmann points are well measured by kernel sparse representations based on linear reconstruction. With the kernel sparse representations, experimental results of clustering accuracy on the prevalent public dataset outperform state-of-the-art algorithms by more than 90 percent and the robustness of our algorithm is demonstrated as well.

关键词： Manifolds Kernel Clustering algorithms Sparse matrices Geometry Symmetric matrices Dictionaries Manifolds Kernel Symmetric matrix Seeds Dictionaries as Topic Sparse matrix Clustering algorithms geometry Non-Euclidean geometry Subspace

来源：评论

学校读者我要写书评

暂无评论

A fuzzy morphological hit-or-miss transform for grey-level images: A new approach

引用

FUZZY SETS AND systems 2016年 286卷 30-65页

作者： Gonzalez-Hidalgo, M. Massanet, S. Mir, A. Ruiz-Aguilera, D. Univ Balearic Isl Dept Math & Comp Sci Palma De Mallorca 07122 Illes Balears Spain

The translation of the hit-or-miss transform (HMT) for grey-level images from the HMT for binary images is not simple. Initially established as a powerful tool for morphological binary image processing, some generalizations for grey-level images have been proposed in the literature. The difficulty lies in the definition of the complement of a given grey-level image. In this paper, after performing a detailed review of the different approaches proposed in the literature, including those based on fuzzy logic, we propose the definition of the hit-or-miss transform for grey-level images in the framework of the fuzzy mathematical morphology based on fuzzy conjunctions and implications under the duality with respect to a fuzzy negation approach. Some theoretical properties of this operator are studied when a general fuzzy conjunction is considered. In particular, we prove that this fuzzy morphological HMT reduces to the binary one when it is applied to binary images. After that, we focus on the fuzzy morphological HMT derived from t-norms and we introduce the concept of "part of an image" which will guide the study of the desirable properties of our operator and the interpretability of the obtained results. Some preliminary experimental results provide evidence of the potential of this tool to be feasible in design algorithms for detecting patterns. Moreover, some comparisons with other hit-or-miss transforms proposed in the literature are performed. (C) 2015 Elsevier B.v. All rights reserved.

关键词： Fuzzy conjunction Fuzzy implication t-Norm Hit-or-miss Fuzzy mathematical morphology image processing

来源：评论

学校读者我要写书评

暂无评论

Realistic human action recognition: When CNNS meet LDS

Realistic human action recognition: When CNNS meet LDS

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Lei Zhang Yangyang Feng Xuezhi Xiang Xiantong Zhen College of Information and Communication Engineering Harbin Engineering University China Department of Medical Biophysics University of Western Ontario London Canada

ISBN: (纸本)9781509041183

In this paper, we proposed new framework for human action representation, which leverages the strengths of convolutional neural networks (CNNs) and the linear dynamical system (LDS) to represent both spatial and temporal structures of actions in videos. We make two principal contributions: first, we incorporate image-trained CNNs to detect action clip concepts, which takes advantage of different levels of information by combining the two layers in CNNs trained from images;Second, we further propose adopting a linear dynamical system (LDS) to model the relationships between these clip concepts, which captures temporal structures of actions. We have applied the proposed method on two challenging realistic benchmark datasets, and our method achieves high performance up to 86.16% on the YouTube and 82.76% UCF50 datasets, which largely outperforms most of the state-of-the-art algorithms with more sophisticated techniques.

关键词： Deep learning image-trained CNNs Linear dynamical system Concept confidence Local Digital Switch temporal structure Action YouTube DYNAMICAL systems clipping Clip videotapes HIGH-PERFORMANCE Dataset

来源：评论

学校读者我要写书评

暂无评论

A nonconvex splitting method for symmetric nonnegative matrix factorization: Convergence analysis and optimality

A nonconvex splitting method for symmetric nonnegative matri...

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Songtao Lu Mingyi Hong Zhengdao Wang Department of Electrical and Computer Engineering Iowa State University Ames 50011 USA Industrial and Manufacturing Systems Engineering Iowa State University Ames 50011 USA

ISBN: (纸本)9781509041183

Symmetric non-negative matrix factorization (SymNMF) has important applications in data analytics problems such as document clustering, community detection and image segmentation. In this paper, we propose a novel nonconvex variable splitting method for solving SymNMF. Different from the existing works, we prove that the algorithm converges to the set of Karush-Kuhn-Tucker (KKT) points of the nonconvex SymNMF problem with a global sublinear convergence rate. We also show that the algorithm can be efficiently implemented in a distributed manner. Further, we provide sufficient conditions that guarantee the global and local optimality of the obtained solutions. Extensive numerical results performed on both synthetic and real data sets suggest that the proposed algorithm yields high quality of the solutions and converges quickly to the set of local minimum solutions compared with other algorithms.

关键词： Symmetric Nonnegative Matrix Factorization Karush-Kuhn-Tucker points variable splitting global and local optimality clustering optimality matrix decomposition Cluster Analysis Nonnegative CENTROSYMMETRIC Solutions image segmentation Converge Dataset Sufficient conditions

来源：评论

学校读者我要写书评

暂无评论

image scanning techniques for speeded-up color object detection 5th

Image scanning techniques for speeded-up color object detect...

引用

5th Eccomas Thematic Conference on Computational vision and Medical image processing, vipimage 2015

作者： Trifan, Alina Neves, António J. R. Cunha, Bernardo Department of Electronics and Telecommunications Engineering Intelligent Systems and Intelligent Robotics Laboratory Institute of Electronics and Informatics Engineering of Aveiro University of Aveiro Portugal

ISBN: (纸本)9781138029262

Nowadays there are many computer vision algorithms dedicated to solve the problem of object detection, from many different perspectives. Many of these algorithms take a considerable processing time even for low resolution images. Research areas that are more concerned about real-time capabilities of a system, such as the case of robotics for example, are focusing on adapting the existing algorithms or developing new ones that cope with time constraints. Color object detection algorithms are often used in time-constrained application since the color of an object is an important clue for its detection. In addition, color segmentation algorithms have a smaller computational cost than generic object detection algorithms. Most of the color object detection algorithms include a step of image scanning in search of pixels of the color of interest. In this paper we present a study on the influence of an image scanning pattern while searching for pixels of a certain color versus the image resolution in the results of three color object detection algorithms. We present results comparing different scanning approaches versus different resolution images for color object detection algorithms based on blob formation, contours detection and region growing clustering. Our experiments show that using search lines for color segmentation, followed by blob formation provides faster and more accurate results. © 2016 Taylor & Francis Group, London.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

CAS-CNN: A Deep Convolutional Neural Network for image Compression Artifact Suppression

CAS-CNN: A Deep Convolutional Neural Network for Image Compr...

引用

International Joint Conference on Neural Networks

作者： Lukas Cavigelli Pascal Hager Luca Benini Integrated Systems Laboratory ETH Zurich Zurich Switzerland

ISBN: (纸本)9781509061839

Lossy image compression algorithms are pervasively used to reduce the size of images transmitted over the web and recorded on data storage media. However, we pay for their high compression rate with visual artifacts degrading the user experience. Deep convolutional neural networks have become a widespread tool to address high-level computer vision tasks very successfully. Recently, they have found their way into the areas of low-level computer vision and image processing to solve regression problems mostly with relatively shallow networks. We present a novel 12-layer deep convolutional network for image compression artifact suppression with hierarchical skip connections and a multi-scale loss function. We achieve a boost of up to 1.79 dB in PSNR over ordinary JPEG and an improvement of up to 0.36 dB over the best previous ConvNet result. We show that a network trained for a specific quality factor (QF) is resilient to the QF used to compress the input image - a single network trained for QF 60 provides a PSNR gain of more than 1.5 dB over the wide QF range from 40 to 76.

关键词： image coding Training Neural networks Transform coding image resolution Convolution visualization

来源：评论

学校读者我要写书评

暂无评论

Automatic Morphologic Analysis of Quasi-Periodic Masonry Walls from LiDAR

引用

COMPUTER-AIDED CIvIL AND INFRASTRUCTURE ENGINEERING 2016年第4期31卷 305-319页

作者： Riveiro, Belen Lourenco, Paulo B. Oliveira, Daniel v. Gonzalez-Jorge, Higinio Arias, Pedro Univ Vigo Dept Mat Engn Appl Mech & Construct Appl Geotechnol Grp Vigo 36208 Spain Univ Minho ISISE Dept Civil Engn P-4800058 Azurem Guimaraes Portugal Univ Vigo Dept Nat Resources & Environm Engn Appl Geotechnol Grp Vigo 36310 Spain

This article presents a novel segmentation algorithm that allows the automatic segmentation of masonry blocks from a 3D point cloud acquired with LiDAR technology, for both stationary and mobile devices. The point cloud segmentation algorithm is based on a 2.5D approach that creates images based on the intensity attribute of LiDAR systems. image processing algorithms based on an improvement of the marked-controlled watershed was successfully used to produce the automatic segmentation of the point cloud in the 3D space isolating each individual stone block. Finally, morphologic analysis in two case studies has been carried out. The morphologic analysis provides information about the assemblage of masonry pieces, which is valuable for the structural evaluation of masonry buildings.

关键词： MASONRY LIDAR (Optics) SEGMENTATION (image processing) AUTOMATIC control CLOUD computing

来源：评论

学校读者我要写书评

暂无评论

vehicle routing algorithms based on a route reservation approach

引用

Journal of Physics: Conference Series 2018年第1期1096卷

作者： A A Agafonov v v Myasnikov Samara National Research University Moskovskoye shosse 34 Samara Russia 443086 Image Processing Systems Institute – Branch of the Federal Scientific Research Centre 'Crystallography and Photonics' of RAS Molodogvardeyskaya st. 151 Samara Russia 443001

Traffic congestion remains a serious problem in transportation networks. Widely used navigation systems can only react to the presence of traffic jams but not to prevent their creation. One of the possibilities to prevent congestion is to manage road traffic within the urban area. This work considers a route reservation approach with possibility to reroute a vehicle during a journey. This approach decomposes road segments into time-spatial slots and for every vehicle it makes the slots reservation for the corresponding route. Since the travel time in real networks cannot be determined precisely and can be considered as stochastic, we propose to use a rerouting procedure to minimize the traveling time. The experiments are carried out in microscopic simulation of a real-world traffic environment in the transportation network of Samara, Russia, using multi-agent transport simulation MATSim.

关键词：

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：