检索结果-内蒙古大学图书馆

IEEE International conference on high performance computing and Communications (HPCC)

作者： Xin Zhang Rabab Abdelfattah Yuqi Song Samuel A. Dauchert Xiaofeng Wang University of South Carolina Columbia United States

Depth information is the foundation of perception, essential for autonomous driving, robotics, and other source- constrained applications. Promptly obtaining accurate and effi-cient depth information allows for a rapid response in dynamic environments. Sensor-based methods using LIDAR and RADAR obtain high precision at the cost of high power consumption, price, and volume. While due to advances in deep learning, vision-based approaches have recently received much attention and can overcome these drawbacks. In this work, we explore an extreme scenario in vision-based settings: estimate a depth map from one monocular image severely plagued by grid artifacts and blurry edges. To address this scenario, We first design a convolutional attention mechanism block (CAMB) which consists of channel attention and spatial attention sequentially and insert these CAMBs into skip connections. As a result, our novel approach can find the focus of current image with minimal overhead and avoid losses of depth features. Next, by combining the depth value, the gradients of X axis, Y axis and diagonal directions, and the structural similarity index measure (SSIM), we propose our novel loss function. Moreover, we utilize pixel blocks to accelerate the computation of the loss function. Finally, we show, through comprehensive experiments on two large- scale image datasets, i.e. KITTI and NYU - v2, that our method outperforms several representative baselines.

关键词： Deep learning Power demand Laser radar Image edge detection Current measurement Estimation Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Extensibility of U-Net Neural Network Model for Hydrographic Feature Extraction and Implications for Hydrologic Modeling

引用

remote sensing 2021年第12期13卷

作者： Stanislawski, Lawrence, v Shavers, Ethan J. Wang, Shaowen Jiang, Zhe Usery, E. Lynn Moak, Evan Duffy, Alexander Schott, Joel US Geol Survey Ctr Excellence Geospatial Informat Sci Rolla MO 65401 USA Univ Illinois Dept Geog & Geog Informat Sci Urbana IL 61801 USA Univ Florida Dept Comp & Informat Sci & Engn Gainesville FL 32611 USA Univ Missouri Sci & Technol Coll Engn & Comp Rolla MO 65401 USA

Accurate maps of regional surface water features are integral for advancing ecologic, atmospheric and land development studies. The only comprehensive surface water feature map of Alaska is the National Hydrography Dataset (NHD). NHD features are often digitized representations of historic topographic map blue lines and may be outdated. Here we test deep learning methods to automatically extract surface water features from airborne interferometric synthetic aperture radar (IfSAR) data to update and validate Alaska hydrographic databases. U-net artificial neural networks (ANN) and high-performance computing (HPC) are used for supervised hydrographic feature extraction within a study area comprised of 50 contiguous watersheds in Alaska. Surface water features derived from elevation through automated flow-routing and manual editing are used as training data. Model extensibility is tested with a series of 16 U-net models trained with increasing percentages of the study area, from about 3 to 35 percent. Hydrography is predicted by each of the models for all watersheds not used in training. Input raster layers are derived from digital terrain models, digital surface models, and intensity images from the IfSAR data. Results indicate about 15 percent of the study area is required to optimally train the ANN to extract hydrography when F1-scores for tested watersheds average between 66 and 68. Little benefit is gained by training beyond 15 percent of the study area. Fully connected hydrographic networks are generated for the U-net predictions using a novel approach that constrains a D-8 flow-routing approach to follow U-net predictions. This work demonstrates the ability of deep learning to derive surface water feature maps from complex terrain over a broad area.

关键词： machine learning neural network U-net feature extraction hydrography

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Convolution Accelerator and Memristor IP Core for Cooperative Acceleration of the YOLO Network

FPGA-Based Convolution Accelerator and Memristor IP Core for...

引用

Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), IEEE International conference on

作者： Aolong Tan Yucheng Yang Shukai Duan Lidan Wang College of Artificial Intelligence Southwest University Chongqing China State Key Laboratory of Intelligent Vehicle Safety Technology National & Local Joint Engineering Research Center of Intelligent Transmission and Control Technology China Chongqing Key Laboratory of Brain-inspired Computing and Intelligent Chips Chongqing China Laboratory of Luminescence Analysis and Molecular Sensing (Southwest University) Ministry of Education Southwest University Chongqing PR China

ISBN: (数字)9798350378542

ISBN: (纸本)9798350378559

Object detection technology is widely used in areas such as autonomous driving, drone reconnaissance, smart surveillance and industrial automation, especially in remote or hazardous scenarios where it can improve efficiency and safety. Therefore, the development of a high-precision, low-power acceleration system integrated with low-power hardware is crucial. This paper proposes a collaborative acceleration scheme for the YOLO network based on an FPGA convolution accelerator and simulated memristors, which successfully implements and accelerates the YOLOv4-Tiny model. First, a reconfigurable single-core accelerator operator is designed for various computational operations in the model. Second, taking advantage of the digital device characteristics of memristors and the hardware resources of the FPGA, a memristor simulation IP core is built to exploit its memory characteristics for convolution operations. Through the synergistic effect of the convolution accelerator and the simulated IP core, a hybrid acceleration of the detection model is achieved. The power consumption of the convolution accelerator is only 2.75W, and in testing, the detection time for a single image is 823ms with an average accuracy of over 0.95, achieving high detection performance. This provides an opportunity to explore and research the efficient acceleration of object detection networks with integrated storage and computation.

关键词： YOLO performance evaluation Power demand Accuracy Convolution Computational modeling Memristors Hardware IP networks Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Wireless sensor networks

引用

ABB Review 2006年第2期 39-42页

作者： Aakvaag, Niels Frey, Jan-Erik ABB Corporate Research Billingstad Norway ABB Automation Technologies Västerås Sweden

The development and applications of wireless sensor network (WSN) for computing and process monitoring, is discussed. A WSN is a network of many, spatially distributed devices using sensors to monitor conditions at different locations. The devices are self-contained units consisting of a microcontroller, power source, radio transceiver, and sensor element. The nodes are built with power conservation and can self organize their networks in an ad-hoc manner. WSN have the ability to self-heal, as if one node malfunctions, the network can find new ways to route data packets. Wireless solutions in industry have a wired infrastructure, in which the data emanates from the sensors and ripple through the network to some wired aggregation point. The WSN have benefits, including increased reliability, low cost of installation, plant-wide coverage, and deployment of temporary sensor networks for maintenance or troubleshooting.

关键词： Wireless telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing Road Extraction in remote sensing Imagery: A Lightweight Dilated Inception Deep Residual U-Net with Channel Attention (LDIDRU-CAN) Model and Pruning Strategies

Optimizing Road Extraction in Remote Sensing Imagery: A Ligh...

引用

International conference on computing and Networking Technology (ICCNT)

作者： Palvi Sharma Rakesh Kumar Meenu Gupta Ahmed J. Obaid Dept. of Computer Science & Engineering Chandigarh University Punjab India Faculty of Computer Science & Mathematics university of Kufa Najaf Iraq College of Technical Engineering National University of Science and Technology Dhi Qar Iraq

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The major challenge in Road Extraction is to extract accurate and complete road network and to get high accuracy while minimizing computational power and ensuring faster prediction. It plays important role in urban planning, disaster management, automatic vehicle navigation and GPS navigation. Several earlier studies used complex deep networks that required large amounts of computational power and large storage. In order to address issues such as high storage requirements, computational load, access to memory delays, and low hardware deployment efficiency this research work presents a novel network model called LDIDRU-CAN. The proposed model is fast, compact, and efficient and requires less storage. The objective of this work, is to compress the original model using structured pruning strategy. This strategy simplified the original model and reduced their computation cost as well as storage requirements. For the reduction of the parameters, we focused on the Row Scale Regular Pruning (RSRP) and Low Learning Rate (LLR) retraining. After applying RSRP pruning approach it reduces storage requirements, parameters, and also contributes to a more than 50% reduction in hardware resource consumption and successfully enhances the parallelism of the model. Testing and validations are performed on the Massachusetts Road Dataset. With only 45 M parameters and 180 MB model size, the suggested network achieves remarkable performance with 87.91% precision, 85.51% recall, 86.69% F1-score and 98.91% accuracy.

关键词： Accuracy Navigation Computational modeling Roads Urban planning Memory management Disaster management Parallel processing Computational efficiency Load modeling

来源：评论

学校读者我要写书评

暂无评论

Classifying Intermediate-redshift Galaxies in SDSS: Alternative Diagnostic Diagrams

引用

ASTROPHYSICAL JOURNAL 2024年第2期962卷 104-104页

作者： Feuillet, Lea M. Melendez, Marcio Kraemer, Steve Schmitt, Henrique R. Fischer, Travis C. Reeves, James N. Catholic Univ Amer Inst Astrophys & Computat Sci Dept Phys Washington DC 20064 USA Space Telescope Sci Inst 3700 San Martin Dr Baltimore MD 21218 USA Remote Sensing Div Naval Res Lab 4555 Overlook Ave SW Washington DC 20375 USA Space Telescope Sci Inst AURA ESA 3700 San Martin Dr Baltimore MD USA

We select a sample of 1437 active galactic nuclei (AGN) from the catalog of the Sloan Digital Sky Survey galaxy properties from the Portsmouth group by detection of the high-ionization [Ne v] 3426 angstrom emission line. We compare the fluxes of [Ne III] 3869 angstrom, [O III] 5007 angstrom, [O II] 3726, 3728 angstrom, and [O i] 6300 angstrom to that of [Ne v]. All four lines show a strong linear correlation with [Ne v], although lines from ions with lower ionization potentials have a lower correlation coefficient. We investigate the use of two forbidden line ratio diagnostic diagrams that do not rely on H alpha in order to classify high-redshift galaxies. These use the [Ne III]/[O II] line ratio plotted against [O III]/[O i] and [O III]/[O II], respectively. We use photoionization modeling to characterize the behavior of the narrow-line region in AGN and star-forming regions and test the validity of our diagnostic diagrams. We also use a luminosity cutoff of log L [O III] [erg s-1] = 42, which lowers the contamination of the AGN region by star-forming galaxies down to 10% but does not remove green pea and purple grape galaxies from the AGN region. We also investigate the OHNO diagram, which uses [Ne III]/[O II] plotted against [O III]/H beta. Using our new diagnostic diagrams, we are able to reliably classify AGN up to a redshift of z <= 1.06 and add more than 822 new AGN to the [Ne v]-selected AGN sample.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Star Formation Rates in [Ne v] 3426 Å Selected Active Galactic Nuclei: Evidence for a Decrease along the Main Sequence?

引用

ASTROPHYSICAL JOURNAL 2024年第2期968卷 91-91页

作者： Feuillet, Lea M. Melendez, Marcio Kraemer, Steve Schmitt, Henrique R. Fischer, Travis C. Reeves, James N. Catholic Univ Amer Inst Astrophys & Computat Sci Dept Phys Washington DC 20064 USA Space Telescope Sci Inst 3700 San Martin Dr Baltimore MD 21218 USA Naval Res Lab Remote Sensing Div 4555 Overlook AveSW Washington DC 20375 USA Space Telescope Sci Inst AURA ESA 3700 San Martin Dr Baltimore MD USA

Studying the behavior along the galaxy main sequence is key in furthering our understanding of the possible connection between active galactic nucleus (AGN) activity and star formation. We select a sample of 1215 AGN from the catalog of Sloan Digital Sky Survey galaxy properties from the Portsmouth group by detection of the high-ionization [Ne v] 3426 & Aring;emission line. Our sample extends from 1040 to 1042.5 erg s-1 in [Ne v] luminosity in a redshift range z = 0.17 to 0.57. We compare the specific star formation rates (sSFRs;SFR scaled by galaxy mass) obtained from the corrected [O ii] and H alpha luminosities, and the spectral energy distribution (SED)-determined values from Portsmouth. We find that the emission-line-based sSFR values are unreliable for the [Ne v] sample due to the AGN contribution, and proceed with the SED sSFRs for our study of the main sequence. We find evidence for a decrease in sSFR along the main sequence in the [Ne v] sample, which is consistent with results from the hard X-ray Burst Alert Telescope AGN sample, which extends to lower redshifts than our [Ne v] sample. Although we do not find evidence that the concurrent AGN activity is suppressing star formation, our results are consistent with a lower gas fraction in the host galaxies of the AGN as compared to that of the star-forming galaxies. If the evacuation of gas, and therefore suppression of star formation, is due to AGN activity, it must have occurred in a previous epoch.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse Tensor Discriminative Locality Alignment for Gait Recognition

Sparse Tensor Discriminative Locality Alignment for Gait Rec...

引用

International Joint conference on Neural Networks

作者： Nengwen Zhao Lefei Zhang Bo Du Liangpei Zhang Dacheng Tao Jane You State Key Laboratory of Software Engineering School of Computer Wuhan University Department of Computing The Hong Kong Polytechnic University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering and Information Technology University of Technology

ISBN: (纸本)9781509006212

Gait recognition is a rising biometric technology which aims to distinguish people purely through the analysis of the way they walk, while the problem is that the dimensionality of the gait data is too high, so it is necessary to carry on dimensionality reduction task. Up to date, in the area of computer vision and pattern recognition, various dimensionality reduction algorithms have been employed for gait data, including the conventional vector representation based methods principal components analysis (PCA) and, locality preserving projection (LPP), and the recently proposed multi-linear subspace learning based approaches such as multilinear principal component analysis (MPCA). In this paper, inspired by the advantages of the tensor representation and manifold learning, we propose a novel sparse tensor discriminative locality alignment for human gait feature representation and dimensionality reduction algorithm, and sub-sequently apply the refined feature for gait recognition by a lazy classifier of the KNN. The proposed method adopts sparse multi-way projection based on the high-order version of discriminative locality alignment, by which the class separability is enhanced and the potential model overfitting is simultaneously avoided. Extensive experiments on the University of South Florida (USF) HumanID Gait Database show that the proposed method achieves better recognition rate compared with some existing classical dimensionality reduction algorithms.

关键词： Gait recognition dimensionality reduction images computer vision Tensor Locomotion Gait principal components analysis vector representation Alignment

来源：评论

学校读者我要写书评

暂无评论

HRRP Target Recognition Based on the Dual-mode Gram Angle Field Features and the Multi-level CNN

HRRP Target Recognition Based on the Dual-mode Gram Angle Fi...

引用

IEEE International conference on Signal and Image Processing (ICSIP)

作者： Erchun Xu Gang Xiong Shuning Zhang Huichang Zhao School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Institute of Navigation and Sensing Shanghai Jiao Tong University Shanghai China School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9781665446006

Aiming at the Carrier-Free Ultra-Wide-Band Radar (CF-UWBR) under the near-range conditions, a novel target recognition method based on the Gram Angle Field (GAF) feature extraction and the Inception v3 network is proposed in this paper. The one-dimensional high-Resolution Range Profile (HRRP) of CF-UWBR is highly sensitive to observation angle so that the performance of direct recognition using the original time-domain HRRP data is not satisfying. In response to this problem, the GAF method is employed to convert the HRRP data into a two-dimensional image firstly, to maintain and highlight the correlation features between the adjacent time points in the polar coordinate domain. Furthermore, the Inception v3 network is selected for the target recognition based on the dual-mode GAF features, due to the excellent performance with the fewer computing resources. The experimental results on the actual measured CF-UWBR data set indicated that the proposed method is superior in performance to the methods based on the Support vector Machine (SvM), the Gated Recurrent Unit (GRU) network, or the Convolutional Neural Network (CNN) with the original HRRP image. Especially when the dual-mode GAFs are used, the recognition accuracy of 97.63% can be achieved, about 1.95% higher than the STOA.

关键词： Support vector machines Correlation Target recognition Radar Logic gates Feature extraction Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Feature Based visualization Algorithm for Large-Scale Flow Data

Feature Based Visualization Algorithm for Large-Scale Flow D...

引用

International conference on Computer Modeling and Simulation, ICCMS

作者： Liang Zhong ChiTian He Xin Zhang Inst. of Remote Sensing Applic. Eng. Center Chinese Acad. of Sci. Beijing China

To analyze large amounts of numerical data, one of the most useful approaches is to use scientific visualization to transform them into graphical images. Flow visualization as one of the challenging topics has played important roles in oceanic data analysis. There are many techniques have been presented in the past decade, but most of them can't get high performance to visualize large-scale flow data in real time. To deduce the computational complexity brought by large flow dataset, feature-based expression will be a helpful way. However, how to get the result images quickly without costing much time for feature extraction and analysis is a very important problem to deal. Based on the common characteristic of flow and the unchangeable scale feather of spiral line, we present a new distributing strategy which needn't locate feature points very accurately and didn't rely on the type of feature fields. The visualization procedure not only can straight forward automatically but also can be changed with user's interactive command. The flow data obtained from the South Sea of China was verified and simulated. The result shows that this method using spiral strategy not templates to setting the seeds to emphasize the interesting fields is much faster and flexible, especially in large-scale flow data visualization.

关键词： Data visualization Large-scale systems Oceans Spirals Computational efficiency Image analysis Feature extraction Data flow computing Computational modeling Analytical models

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：