检索结果-内蒙古大学图书馆

International conference on High Performance Computing in the Asia-Pacific Region

作者： X. Shen G. Thiruvathukal W. Liao A. Choudhary A. Singh Center for Parallel and Distributed Computing Department of Electrical and Computer Engineering Northwestern University Evanston IL USA

Large-scale scientific applications present great challenges to computational scientists in terms of obtaining high performance and in managing large datasets. These applications (most of which are simulations) may employ multiple techniques and resources in a heterogeneously distributed environment. Effective working in such an environment is crucial for modern large-scale simulations. In this paper, we present an integrated Java graphical user interface (IJ-GUI) that provides a control platform for managing complex programs and their large datasets easily. As far as performance is concerned, we present and evaluate our initial implementation of two optimization schemes: data replication and data prediction. Data replication can take advantage of 'temporal locality' by caching the remote datasets on local disks; data prediction, on the other hand, provides prefetch hints based on the datasets' past activities that are kept in databases. We first introduce the data contiguity concept in such an environment that guides data prediction. The relationship between the two approaches is discussed.

关键词： Java Graphical user interfaces Large-scale systems Computer interfaces Distributed computing Computational modeling Visual databases Analytical models Data analysis Data visualization

来源：评论

学校读者我要写书评

暂无评论

Neural encoding of rigid object-shape perception from visually stimulated EEG signals

Neural encoding of rigid object-shape perception from visual...

引用

International conference on Control, Instrumentation, Energy and Communication (CIEC)

作者： Anwesha Khasnobish Shreyasi Datta Amit Konar D. N. Tibarewala School of Bioscience and Engineering Department of Electronics and Telecommunication Engineering Jadavpur University Kolkata India

Object shape recognition in the human brain in response to visual stimulus takes place by synchronous activities of the occipital and parietal regions. The same process due to tactile stimulus is related to the parietal region only. For complete perceptual understanding of objects both visual and tactile information is essential. Therefore, in case of damage of the parietal region object recognition by both vision as well as touch is hampered. The present work aims to predict the parietal EEG features from available occipital EEG in response to visual stimulus of different object shapes. Prediction is done by regression analysis using a back-propagation neural network with Levenberg-Marquardt optimization for weight adaptation and by means of least squares polynomial fitting as well. The parietal EEG features are predicted from occipital EEG features with Mean Squared Error (MSE) of 0.15 in 0.3 seconds and 0.0634 in 0.3 seconds using neural network and polynomial fitting respectively, on an average, over a number of subjects. Thus in the absence of parietal EEG signals, both the techniques can be implemented for efficient prediction of parietal features from occipital EEG in real time.

关键词： Electroencephalography Shape Polynomials visualization Fitting Biological neural networks Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Toward long-term, automated ship hull inspection with visual SLAM, explicit surface optimization, and generic graph-sparsification

Toward long-term, automated ship hull inspection with visual...

引用

IEEE International conference on Robotics and Automation (ICRA)

作者： Paul Ozog Ryan M. Eustice Department of Electrical Engineering & Computer Science University of Michigan Ann Arbor MI USA Department of Naval Architecture & Marine Engineering University of Michigan Ann Arbor MI USA

This paper reports on a method for an autonomous underwater vehicle to perform real-time visual simultaneous localization and mapping (SLAM) on large ship hulls over multiple sessions. Along with a monocular camera, our method uses a piecewise-planar model to explicitly optimize the ship hull surface in our factor-graph framework, and anchor nodes to co-register multiple surveys. To enable realtime performance for long-term SLAM, we use the recent Generic Linear Constraints (GLC) framework to sparsify our factor-graph. This paper analyzes how our single-session SLAM techniques can be used in the GLC framework, and describes a particle filter reacquisition algorithm so that an underwater session can be automatically re-localized to a previously built SLAM graph. We provide real-world experimental results involving automated ship hull inspection, and show that our localization filter out-performs Fast Appearance-Based Mapping (FAB-MAP), a popular place-recognition system. Using our approach, we can automatically align surveys that were taken days, months, and even years apart.

关键词： Simultaneous localization and mapping Marine vehicles visualization Cameras Sonar navigation

来源：评论

学校读者我要写书评

暂无评论

Assessing photograph aesthetic quality with color based descriptor

Assessing photograph aesthetic quality with color based desc...

引用

International conference on High Performance Computing & Simulation (HPCS)

作者： Xianghui Zhu Teng-Sheng Moh Department of Computer Science San Jose State University San Jose CA USA

Assessing photograph aesthetic quality is an interesting and important problem of computer vision. The understanding of how to classify photographs based on their aesthetic value not only provides us with important knowledge about effective methods and techniques of summarizing information embedded in digital images, but also has numerous practical applications in photo management systems, image search engines, photo library optimization processes, and smart cameras. Previous work has explored the method of using generic local descriptors extracted from gray-scale photographs to assess the aesthetic quality. In our work, we designed an aesthetic descriptor based on color information of local patches to asses the aesthetic quality of photographs. We employed the Bag of Words (BOW) model to describe our data. The BOW model is widely used in text analysis tasks due to its good performance. This model can also be adopted by computer vision tasks to classify and categorize images. With such a model, every photograph in our dataset was represented as a vector of visual words derived from the color descriptors. A Gaussian mixture model was used to cluster and verbalize photographs, which is proven to be highly effective in our classification task. The best performance we achieved in our experiments was 72.9% AUC.

关键词： Image color analysis Vocabulary Histograms Computational modeling visualization Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Speech-Based Visual Aid for the Blind Eye Using Deep Convolution Neural Network

Speech-Based Visual Aid for the Blind Eye Using Deep Convolu...

引用

International conference on Emerging Trends in Networks and Computer Communications (ETNCC)

作者： Prasidhi Nandwani Garima Jain Sanat Jain Ajay Kumar Phulre Suneet Joshi Rupayali Swaroop School of Computing Science Engineering and Artificial Intelligence VIT Bhopal University Kothri-Kalan Sehore India School of Computer Science and Engineering VIT Bhopal University Kothri-Kalan Sehore India Computer Science and Engineering JECRC University Jaipur Rajasthan India

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

To enhance the navigation experience for visually impaired individuals, this work proposes a novel assistive system for visually impaired individuals that leverages object detection, distance estimation, and voice feedback functionalities. The system utilizes a camera to capture real-time surroundings. Advanced object detection algorithms, like SSD or YOLO, will be employed to identify objects within the field of view. Subsequently, distance estimation techniques will be implemented to determine the approximate distance between the user and the detected object. Finally, a text-to-speech engine will convert this information into clear audio messages, providing the user with crucial environmental awareness. Voice commands will be integrated to allow users to interact with the system, initiating object detection or requesting specific information about their surroundings. This comprehensive approach aims to empower blind users by enhancing their spatial understanding and fostering independent navigation in everyday environments.

关键词： YOLO visualization Privacy Navigation Estimation Real-time systems Text to speech Safety Object recognition optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Capsule Networks for Accurate Microaneurysm Detection and Classification in Retinal Images

Deep Capsule Networks for Accurate Microaneurysm Detection a...

引用

International conference on Communications and Signal Processing

作者： Suroshe Akash Rao G. Sarvesh R. Bhargava Reddy B. Karthick Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh India

ISBN: (数字)9798350353068

ISBN: (纸本)9798350353075

Diabetic retinopathy (DR), is a leading cause of vision. Early detection and intervention are crucial for preventing irreversible vision impairment. Microaneurysms (MAs), small balloon-like dilatations in blood vessels, are often the earliest detectable signs of DR. This study explores an automated system using image processing and machine learning to identify microaneurysms (MAs) in five stages and early DR signs, in retinal images. Leveraging the Kaggle dataset, the system extracts key features from MAs using image processing techniques. These features are fed into a machine learning algorithm, specifically a Gaussian Naive Bayes classifier, trained to differentiate true MAs from non-MAs. The system achieves Enhanced accuracy, demonstrating its potential to assist ophthalmologists in early DR detection. Further optimization and validation on larger datasets are planned to refine the system for real-world implementation. This study highlights the promise of image processing and AI in automating DR screening, potentially improving accessibility and reducing vision loss from DR.

关键词： Diabetic retinopathy Technological innovation visualization Machine learning algorithms Visual impairment Collaboration Medical services

来源：评论

学校读者我要写书评

暂无评论

Image Encryption Design Based on Henon Mapping

Image Encryption Design Based on Henon Mapping

引用

Image Processing, Electronics and Computers (IPEC), Asia-Pacific conference on

作者： Wenyi Su Mingjie Zhou Jiaqing Bao Lanjing Yang Liping Zhu Guodong Li School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China School of Mathematics and Data Science Changji University Changji China

ISBN: (数字)9798350374407

ISBN: (纸本)9798350374414

Image data, compared to textual information, possesses visual characteristics that require novel encryption methods to ensure its security. Therefore, it is necessary to explore new encryption techniques tailored specifically for image data. By applying the Henon chaotic map, two random sequences are generated. These sequences, along with a given key, are used to produce four equally-sized random matrices through specific formulas. Two of these matrices are employed in the forward and backward diffusion modules, while the remaining two are utilized in the permutation module. Through two rounds of diffusion operations and one permutation operation, the four random matrices are utilized to encrypt the image, resulting in a secure, encrypted image. The security performance of this encryption algorithm is analyzed theoretically, considering encryption and decryption speeds, histogram statistical characteristics, correlations between adjacent pixels, and information entropy. Additionally, simulation experiments demonstrate the effectiveness of this digital image encryption scheme, showcasing excellent encryption results and security performance.

关键词： Military communication visualization Chaotic communication Military computing Digital images Encryption Performance analysis Information entropy optimization Random sequences

来源：评论

学校读者我要写书评

暂无评论

International conference on Applied Sciences ICAS2022

引用

Journal of Physics: conference Series 2023年第1期2540卷 011001页

作者： Dan, Ludovic LEMLE United States

Banja Luka, Bosnia and Herzegovina, May 25-28, 2022International conference on Applied Sciences ICAS2022 took place in Banja Luka, Bosnia and Herzegovina, in the period May 25–28, 2022, at the University of Banja Luka, with the aims to serve as a platform for exchange of information between various areas of applied sciences, and to promote the communication between the scientists of different nations, countries and *** conference has been focused on several fields of application, operation and influence of the applied sciences and technologies on *** of the conference covers a comprehensive spectrum of issues from:1. Fundamental Sciences: Numerical approximation and analysis, Numerical simulation, Numerical optimization, General statistical methods, Stochastic analysis methods, Analytical and numerical techniques, Finite element methods, Dynamical systems methods, Chemical composition analysis, Energy analysis, Heat transfer, Interdisciplinary applications of physics, Environmental aspects, Effects of pollution, Fuzzy logic, and others…2. Computers Engineering: Computer modeling and simulation, Algorithms, Software engineering, Artificial intelligence, Neural networks, Image processing, Data acquisition: hardware and software, Data presentation and visualization, Data analysis: algorithms and implementation, Data management, Big Data, Internet and network applications, and others…3. Electrical Engineering: Electrical and electronic instruments and components, Circuits and circuit components, Signal processing electronics, Power electronics, Electric motors, Electric vehicles, Biomass energy, Wind energy, Solar energy, Solar cells (photovoltaics), Conventional hydropower, Hydroturbines, and others…4. Mechanical Engineering: General theory of classical mechanics, Computational methods in classical mechanics, Control of mechanical systems, Dynamics and kinematics of rigid bodies, Mechanical properties of solids, Applied mechanics and design, Defo

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visual-Inertial SLAM Technology Based on Monocular Infrared Camera

Visual-Inertial SLAM Technology Based on Monocular Infrared ...

引用

Chinese Control and Decision conference, CCDC

作者： Chunming Lv Leilei Li Ranfeng Wei Xia Wang Tao Zuo School of Automation Beijing Institute of Technology Beijing China School of Optios and Photonios Beijing Institute of Technology Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Traditional visual-inertial odometry based on visible light cameras experiences significant visual degradation in complex lighting environments, posing significant challenges for the practical application of SLAM systems. Thermal infrared cameras are less affected by changes in lighting conditions and can operate around the clock. However, due to issues such as weak textures, low contrast, and low signal-to-noise ratio in infrared images, existing SLAM methods are not directly compatible with thermal infrared cameras. Edge features exhibit minimal performance degradation in infrared images. To address these challenges, we propose an infrared visual-inertial SLAM method based on point and line features. This method employs techniques such as bilateral filtering, stripe noise filtering, and adaptive histogram equalization to enhance image contrast and filter noise, overcoming the issues associated with poor-quality infrared images. Subsequently, an improved feature extraction method is employed to extract point and line features and track them. Finally, real-time state estimation is achieved by nonlinear optimization that minimizes reprojection errors over a sliding window.

关键词： Degradation visualization Simultaneous localization and mapping Accuracy Lighting Cameras Feature extraction

来源：评论

学校读者我要写书评

暂无评论

HumanReg: Self-supervised Non-rigid Registration of Human Point Cloud

HumanReg: Self-supervised Non-rigid Registration of Human Po...

引用

International conference on 3D Imaging, Modeling, Processing, visualization and Transmission (3DIMPVT)

作者： Yifan Chen Zhiyu Pan Zhicheng Zhong Wenxuan Guo Jianjiang Feng Jie Zhou Department of Automation Tsinghua University Beijing China

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

In this paper, we present a novel registration framework, HumanReg, that learns a non-rigid transformation between two human point clouds end-to-end. We introduce body prior into the registration process to efficiently handle this type of point cloud. Unlike most exsisting supervised registration techniques that require expensive point-wise flow annotations, HumanReg can be trained in a self-supervised manner benefiting from a set of novel loss functions. To make our model better converge on real-world data, we also propose a pretraining strategy, and a synthetic dataset (HumanSyn4D) consists of dynamic, sparse human point clouds and their auto-generated ground truth annotations. Our experiments shows that HumanReg achieves state-of-the-art performance on CAPE-512 dataset and gains a qualitative result on another more challenging real-world dataset. Furthermore, our ablation studies demonstrate the effectiveness of our synthetic dataset and novel loss functions. Our code and synthetic dataset is available at https://***/chenyifanthu/HumanReg.

关键词： Point cloud compression Three-dimensional displays Annotations Noise optimization methods Estimation Feature extraction

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：