检索结果-内蒙古大学图书馆

Fusion of visible and thermal images for facial expression recognition

Frontiers of computer Science 2014年第2期8卷 232-242页

作者： Shangfei WANG Shan HE Yue WU Menghua HE Qiang JI School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China Key Lab of Computing and Communicating Software of Anhui Province Hefei 230027 China Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY12180-3590 USA

Most present research into facial expression recognition focuses on the visible spectrum, which is sen- sitive to illumination change. In this paper, we focus on in- tegrating thermal infrared data with visible spectrum images for spontaneous facial expression recognition. First, the ac- tive appearance model AAM parameters and three defined head motion features are extracted from visible spectrum im- ages, and several thermal statistical features are extracted from infrared （IR） images. Second, feature selection is per- formed using the F-test statistic. Third, Bayesian networks BNs and support vector machines SVMs are proposed for both decision-level and feature-level fusion. Experiments on the natural visible and infrared facial expression （NVIE） spontaneous database show the effectiveness of the proposed methods, and demonstrate thermal 1R images＇ supplementary role for visible facial expression recognition.

关键词： facial expression recognition feature-level fu-sion decision-level fusion support vector machine Bayesiannetwork thermal infrared images visible spectrum images

来源：评论

学校读者我要写书评

暂无评论

DPT‐tracker:Dual pooling transformer for efficient visual tracking

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 948-959页

作者： Yang Fang Bailian Xie Uswah Khairuddin Zijian Min Bingbing Jiang Weisheng Li Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Mechanical Precision Engineering Malaysia‐Japan International Institute of TechnologyUniversity of Technology MalaysiaKuala LumpurMalaysia Department of Electrical and Computer Engineering Inha UniversityIncheonRepublic of Korea School of Information Science and Technology Hangzhou Normal UniversityHangzhouChina

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations,thus the model complexity will grow quadratically with the number of input *** alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers,we propose a dual pooling transformer tracking framework,dubbed as DPT,which consists of three components:a simple yet efficient spatiotemporal attention model(SAM),a mutual correlation pooling Trans-former(MCPT)and a multiscale aggregation pooling Transformer(MAPT).SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time *** aims to capture multi‐scale pooled and correlated contextual features,which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking *** tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on Track-ingNet while maintaining a shorter sequence length of attention tokens,fewer parameters and FLOPs compared to existing state‐of‐the‐art(SOTA)Transformer tracking *** experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

关键词： human‐computer interfacing image motion analysis pattern recognition signal processing tracking

来源：评论

学校读者我要写书评

暂无评论

Condition Monitoring and Maintenance Management with Grid-Connected Renewable Energy Systems

引用

computers, Materials & Continua 2022年第8期72卷 3999-4017页

作者： Md.Mottahir Alam Ahteshamul Haque Mohammed Ali Khan Nebras M.Sobahi Ibrahim Mustafa Mehedi Asif Irshad Khan Department of Electrical and Computer Engineering(ECE) King Abdulaziz UniversityJeddah 21589Saudi Arabia Advance Power Electronics Research Lab Department of Electrical EngineeringJamia Millia IslamiaNew Delhi 110025India Department of Electrical Power Engineering Faculty of Electrical Engineering and CommunicationBrno University of TechnologyBrno 61600Czech Republic Center of Excellence in Intelligent Engineering Systems(CEIES) King Abdulaziz UniversityJeddah 21589Saudi Arabia Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah 21589Saudi Arabia

The shift towards the renewable energy market for carbon-neutral power generation has encouraged different governments to come up with a plan of *** with the endorsement of renewable energy for harsh environmental conditions like sand dust and snow,monitoring and maintenance are a few of the prime *** problems were addressed widely in the literature,but most of the research has drawbacks due to long detection time,and high misclassification *** to overcome these drawbacks,and to develop an accurate monitoring approach,this paper is motivated toward the understanding of primary failure concerning a grid-connected photovoltaic(PV)system and highlighted along with a brief overview on existing fault detection *** on the drawback a data-driven machine learning approach has been used for the identification of fault and indicating the maintenance unit regarding the operation and maintenance ***,the system was tested with a 4 kWp grid-connected PV system,and a decision tree-based algorithm was developed for the identification of a *** results identified 94.7%training accuracy and 14000 observations/sec prediction speed for the trained classifier and improved the reliability of fault detection nature of the grid-connected PV operation.

关键词： Fault detection machine learning fault ride through

来源：评论

学校读者我要写书评

暂无评论

Non-uniform camera shake removal using a spatially-adaptive sparse penalty

Non-uniform camera shake removal using a spatially-adaptive ...

引用

27th Annual Conference on Neural Information Processing Systems, NIPS 2013

作者： Zhang, Haichao Wipf, David School of Computer Science Northwestern Polytechnical University Xi'an China Department of Electrical and Computer Engineering Duke University United States Visual Computing Group Microsoft Research Asia Beijing China

Typical blur from camera shake often deviates from the standard uniform convolutional assumption, in part because of problematic rotations which create greater blurring away from some unknown center point. Consequently, successful blind deconvolution for removing shake artifacts requires the estimation of a spatially varying or non-uniform blur operator. Using ideas from Bayesian inference and convex analysis, this paper derives a simple non-uniform blind deblurring algorithm with a spatially-adaptive image penalty. Through an implicit normalization process, this penalty automatically adjust its shape based on the estimated degree of local blur and image structure such that regions with large blur or few prominent edges are discounted. Remaining regions with modest blur and revealing edges therefore dominate on average without explicitly incorporating structure selection heuristics. The algorithm can be implemented using an optimization strategy that is virtually tuning-parameter free and simpler than existing methods, and likely can be applied in other settings such as dictionary learning. Detailed theoretical analysis and empirical comparisons on real images serve as validation.

关键词： Inference engines

来源：评论

学校读者我要写书评

暂无评论

Distinction between handwritten and machine-printed text based on the bag of visual words model

Distinction between handwritten and machine-printed text bas...

引用

作者： Zagoris, Konstantinos Pratikakis, Ioannis Antonacopoulos, Apostolos Gatos, Basilis Papamarkos, Nikos Visual Computing Group Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi Greece Research Lab School of Computing Science and Engineering University of Salford Greater Manchester United Kingdom Institute of Informatics and Telecommunications National Center for Scientific Research Demokritos Athens Greece

In a variety of documents, ranging from forms to archive documents and books with annotations, machine printed and handwritten text may coexist in the same document image, raising significant issues within the recognition pipeline. It is, therefore, necessary to separate the two types of text so that it becomes feasible to apply different recognition methodologies to each modality. In this paper, a new approach is proposed which strives towards identifying and separating handwritten from machine printed text using the Bag of visual Words model (BoVW). Initially, blocks of interest are detected in the document image. For each block, a descriptor is calculated based on the BoVW. The final characterization of the blocks as Handwritten, Machine Printed or Noise is made by a decision scheme which relies upon the combination of binary SVM classifiers. The promising performance of the proposed approach is shown by using a consistent evaluation methodology which couples meaningful measures along with new datasets dedicated to the problem upon consideration. © 2013 Elsevier Ltd. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

The Design and Development of a GPU-accelerated Radar Simulator for Space Debris Monitoring 21

The Design and Development of a GPU-accelerated Radar Simula...

引用

5th High Performance computing and Cluster Technologies Conference, HPCCT 2021

作者： Martin, Mogamat Yaaseen Winberg, Simon Lucas Gaffar, Mohammed Yunus Abdul Macleod, David Department of Electrical Engineering University of Cape Town South Africa Advanced Computer Engineering Lab Centre for High Performance Computing South Africa

ISBN: (纸本)9781450390132

The problem of space debris represents a major topic of concern in astronomy as the threat of space junk continues to grow, and the accuracy of its tracking is greatly restricted by the insufficiency and limitations of current surveillance sensors. This article presents the development of an open-source, high-performance, signal-level radar simulator to assist in modelling the detection and tracking of space debris from terrestrial radar stations, including multistatic installations where the transmitter and receiver may be separated by many kilometers. This tool is expected to aid astronomers and researchers in space situational awareness, supporting the modelling of radar interactions in this context and simulation-based exploration of radar designs for space surveillance. It makes use of an accelerated orbit propagation technique with measured two-line element datasets being used to define space debris objects. The software has been named the Space Object Astrodynamics and Radar Simulator - or SOARS - and both the transmitted and received signals generated by the application have been shown to agree with theoretical expectations. Additionally, SOARS is presently undergoing continued development, extension and optimization for heterogeneous computing platforms, enabling the use of the NVIDIA® Compute Unified Device Architecture (CUDA) interface. Results have demonstrated promising speed-ups in simulation runtimes when using the CUDA version of the application over the original sequential version, even on lower-end graphics processors. It is anticipated that the developed application will be used for the design and testing of radar sensors for space situational awareness applications, as well as for use in research, teaching and training environments. © 2021 ACM.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Eyebrow shape-based features for biometric recognition and gender classification: A feasibility study

Eyebrow shape-based features for biometric recognition and g...

引用

2011 International Joint Conference on Biometrics, IJCB 2011

作者： Dong, Yujie Woodard, Damon L. Department of Electrical and Computer Engineering School of Computing Clemson University United States Biometrics and Pattern Recognition Lab School of Computing Clemson University United States

ISBN: (纸本)9781457713583

A wide variety of applications in forensic, government, and commercial fields require reliable personal identification. However, the recognition performance is severely affected when encountering non-ideal images caused by motion blur, poor contrast, various expressions, or illumination artifacts. In this paper, we investigated the use of shape-based eyebrow features under non-ideal imaging conditions for biometric recognition and gender classification. We extracted various shape-based features from the eyebrow images and compared three different classification methods: Minimum Distance Classifier (MD), Linear Discriminant Analysis Classifier (LDA) and Support Vector Machine Classifier (SVM). The methods were tested on images from two publicly available facial image databases: The Multiple Biometric Grand Challenge (MBGC) database and the Face Recognition Grand Challenge (FRGC) database. Obtained recognition rates of 90% using the MBGC database and 75% using the FRGC database as well as gender classification recognition rates of 96% and 97% for each database respectively, suggests the shape-based eyebrow features maybe be used for biometric recognition and soft biometric classification. © 2011 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Investigating resilient high performance reconfigurable computing with minimally-invasive system monitoring

Investigating resilient high performance reconfigurable comp...

引用

2010 4th International Workshop on High-Performance Reconfigurable computing Technology and Applications, HPRCTA'10, Held in Conjunction with SC10

作者： Huang, Bin Schmidt, Andrew G. Mendon, Ashwin A. Sass, Ron Reconfigurable Computing Systems Lab. Department of Electrical and Computer Engineering University of North Carolina Charlotte NC United States

ISBN: (纸本)9781424495177

As researchers push for Exascale computing, one of the emerging challenges is system resilience. Unlike fault-tolerance which corrects errors, recent reports suggest that resilient systems will need to continue to make progress on an application despite faults. A first step in developing a resilient system is to have robust, scalable system monitoring. The work described here presents a novel, minimally-invasive system monitor that operates over a separate network. We analytically characterize the performance for an arbitrary set of nodes and demonstrate a working implementation of the design. We argue that the hardware approach is inherently superior to the ad hoc, software techniques currently employed in practice. © 2010 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

IoT based Smart Fan Dimmer with suppressed Humming Sound and Nonlinear Effect of Inverter 15

IoT based Smart Fan Dimmer with suppressed Humming Sound and...

引用

15th International Conference on Open Source Systems and Technologies, ICOSST 2021

作者： Ikram, Ataul Aziz Imran, Hamza Ali Ikram, Ahmed Jamal Hamza, Kiran Sehgal, Khawaja Usman Riaz FAST-National University of Computer Emerging Sciences EPIC Lab Islamabad Pakistan School of Electrical Engineering Computer Science National University of Science and Technology Department of Computing Islamabad Pakistan School of Electrical Engineering Computer Science National University of Science and Technology Department of Electrical Engineering Islamabad Pakistan

ISBN: (纸本)9781665413053

To address power shortages in third-world countries, other energy sources such as uninterrupted power supplies that charge batteries while line voltage is available are employed. Inverters on the market contain output voltage waveforms that do not provide pure sine waves, and these modified sine waves are non-linear and high-frequency components that impair connected appliances such as fan dimmers. With the rising smart home and IoT industries in mind, this article presents a revised fan dimmer that does not generate humming noises, is resilient, and can be connected to the internet via WiFi using the ESP8266 board. This allows the user to control the speed of the fan from a smartphone via voice command or user-interface © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Random beamforming in MIMO systems exploiting efficient multiuser diversity

Random beamforming in MIMO systems exploiting efficient mult...

引用

2005 IEEE 61st Vehicular Technology Conference -VTC 2005 - Spring Stockholm: Paving the Path for a Wireless Future

作者： Kim, Eun Yong Chun, Joohwan Scientific Computing Lab. Department of Electrical Engineering and Computer Science Korea Advanced Institute of Science and Technology Daejeon Korea Republic of

We propose a new random beamforming technique in forward link multiuser MIMO systems that exploits efficient multiuser diversity and spatial multiplexing gain. The common channels are allocated to more than one user simultaneously and multiple antennas at the receivers are used for interference nulling, resulting in higher throughput and reduced average waiting time. We show that the throughput of the proposed scheme outperforms the upper bound of the conventional scheme. © 2005 IEEE.

关键词： Communication channels (information theory)

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：