检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Risheng Wang Tao Lei Wenzheng Zhou Qi Wang Hongying Meng Asoke K. Nandi School of Electronic Information and Artificial Intelligence Shaanxi University of Science and Technology Xi’an P. R. China Shaanxi University of Science and Technology Xi’an P. R. China School of Electrical and Control Engineering Shaanxi University of Science and Technology Xi’an P. R. China School of Computer Science and the Center for OPTical IMagery Analysis and Learning (OPTIMAL) Northwestern Polytechnical University Xi’an China Brunel University London Uxbridge Middlesex United Kingdom

The popular deep convolutional networks used for image super-resolution (SR) reconstruction often increase the network depth and employ attention mechanism to improve image reconstruction effect. However, these networks suffer from two problems. The first is the deeper network easily causes higher computational cost and more GPU memory usage. The second is traditional attention mechanism often misses the spatial information of images leading the loss of image detail information. To address these issues, we propose a lightweight non-local network (LNLN) for image super resolution in this paper. The proposed network makes two contributions. First, we use non-local module instead of normal attention module to obtain larger receptive field and extract more comprehensive feature information, which is helpful for improving image SR reconstruction results. Secondly, we use the depthwise separable convolution (DSC) instead of the vanilla convolution to reconstruct the residual block, which greatly reduces the number of parameters and computational cost. The proposed LNLN and comparative networks are evaluated on five commonly public datasets, and experiments demonstrate that the proposed LNLN is superior to state-of-the-art networks in terms of reconstruction performance, the number of parameters and storage space.

关键词： deep learning image super-resolution (SR) non-local module depthwise separable convolution (DSC)

来源：评论

学校读者我要写书评

暂无评论

A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling

arXiv

引用

arXiv 2019年

作者： Wang, Qi Gao, Junyu Yuan, Yuan School of Computer Science Unmanned System Research Institute Center for OPTical IMagery Analysis and Learning Northwestern Polytechnical University Xi’an710072 China School of Computer Science Center for OPTical IMagery Analysis and Learning Northwestern Polytechnical University Xi’anShaanxi710072 China

Street scene understanding is an essential task for autonomous driving. One important step towards this direction is scene labeling, which annotates each pixel in the images with a correct class label. Although many approaches have been developed, there are still some weak points. Firstly, many methods are based on the hand-crafted features whose image representation ability is limited. Secondly, they can not label foreground objects accurately due to the dataset bias. Thirdly, in the refinement stage, the traditional Markov Random Filed (MRF) inference is prone to over smoothness. For improving the above problems, this paper proposes a joint method of priori convolutional neural networks at superpixel level (called as "priori s-CNNs") and soft restricted context transfer. Our contributions are threefold: (1) A priori s-CNNs model that learns priori location information at superpixel level is proposed to describe various objects discriminatingly;(2) A hierarchical data augmentation method is presented to alleviate dataset bias in the priori s-CNNs training stage, which improves foreground objects labeling significantly;(3) A soft restricted MRF energy function is defined to improve the priori s-CNNs model’s labeling performance and reduce the over smoothness at the same time. The proposed approach is verified on CamVid dataset (11 classes) and SIFT Flow Street dataset (16 classes) and achieves a competitive performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Embedding structured contour and location prior in siamesed fully convolutional networks for road detection

arXiv

引用

arXiv 2019年

Road detection from the perspective of moving vehicles is a challenging issue in autonomous driving. Recently, many deep learning methods spring up for this task because they can extract high-level local features to find road regions from raw RGB data, such as Convolutional Neural Networks (CNN) and Fully Convolutional Networks (FCN). However, how to detect the boundary of road accurately is still an intractable problem. In this paper, we propose a siamesed fully convolutional networks (named as "s-FCN-loc"), which is able to consider RGB-channel images, semantic contours and location priors simultaneously to segment road region elaborately. To be specific, the s-FCN-loc has two streams to process the original RGB images and contour maps respectively. At the same time, the location prior is directly appended to the siamesed FCN to promote the final detection performance. Our contributions are threefold: (1) An s-FCN-loc is proposed that learns more discriminative features of road boundaries than the original FCN to detect more accurate road regions;(2) Location prior is viewed as a type of feature map and directly appended to the final feature map in s-FCN-loc to promote the detection performance effectively, which is easier than other traditional methods, namely different priors for different inputs (image patches);(3) The convergent speed of training s-FCN-loc model is 30% faster than the original FCN, because of the guidance of highly structured contours. The proposed approach is evaluated on KITTI Road Detection Benchmark and One-Class Road Detection Dataset, and achieves a competitive result with state of the arts. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Finite-time Consensus Tracking for Multi-motor System Based on Sliding Mode Control

Finite-time Consensus Tracking for Multi-motor System Based ...

引用

International Conference on Robotics and Automation Engineering (ICRAE)

作者： Tao Zhang Dengxiu Yu Zhen Wang Xiaoyue Jin Shengjin Li Feiping Du School of Mechanical Engineering Northwestern Polytechnical University AVIC Qingan Group Co.Ltd Xi'an China The Unmanned System Research Institution Northwestern Polytechnical University Xi'an China The Center for Optical Imagery Analysis and Learning Northwestern Polytechnical University Xi'an China School of Mechanical Engineering Northwestern Polytechnical University Xi'an China Science and Technology on Liquid Rocket Engine Laboratory Xi'an Aerospace Propulsion Institute Xi'an China

ISBN: (纸本)9781665406987

This study investigates a finite-time consensus tracking algorithm for synchronous coordination control of a multimotor system (MMS), which is extremely meaningful to some practical applications with the demand of high-precision performance and stringent convergence time. The graph theory is applied to realize the system modeling of the relationship between the internal parameters of MMS, which can reduce the complexity of the internal parameters of the system and make it more suitable for practical engineering. Then a distributed finite-time consensus controller based on sliding mode control for MMS is proposed, making the time costs in the reaching phase and sliding phase both finite. Simulations are given to illustrate the effectiveness of the proposed approach.

关键词： Costs Automation Systems modeling Consensus control Stability analysis Graph theory Topology

来源：评论

学校读者我要写书评

暂无评论

HYPERSPECTRAL UNMIXING VIA L1/4 SPARSITY-CONSTRAINED MULTILAYER NMF

HYPERSPECTRAL UNMIXING VIA L1/4 SPARSITY-CONSTRAINED MULTILA...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Zihan Zhang Qi Wang Yuan Yuan School of Computer Science and Center for OPTical IMagery Analysis and Learning Northwestern Polytechnical University Xi’an Shaanxi P. R. China

Hyperspectral unmixing, by extracting the fractional abundances of endmembers from the hyperspectral image (HSI), has raised wide attention in recent years. In last decade, non-negative matrix factorization (NMF) have been intensively studied for solving spectral unmixing problem. In this paper, we extend the multilayer NMF method by incorporating the L_(1/4) sparsity constraint, named L(1/4)-MLNMF. The L_(1/4) regularizer induces sparsity effectively. We propose an iterative estimation algorithm for L_(1/4)-MLNMF, which provides sparser and more accurate results than MLNMF. Experiments on a synthetic dataset and a real dataset show that the prposed method outperforms the similar competitors.

关键词： Hyperspectral imaging Reflectivity Nonhomogeneous media Cost function Sparse matrices Libraries

来源：评论

学校读者我要写书评

暂无评论

A MULTI-TASK ARCHITECTURE FOR REMOTE SENSING BY JOINT SCENE CLASSIFICATION AND IMAGE QUALITY ASSESSMENT

A MULTI-TASK ARCHITECTURE FOR REMOTE SENSING BY JOINT SCENE ...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Cong Zhang Qi Wang Xuelong Li School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL) Northwestern Polytechnical University Xi’an Shaanxi P.R. China

In this work, we propose a compact multi-task architecture based on deep learning for remote sensing scene classification and image quality assessment (IQA) simultaneously. The model can be trained in an end-to-end manner, and the robustness of classification is improved in our method. More importantly, by exploiting IQA and super-resolution, the accurate classification results can be obtained even if the images are distorted or with low quality. To the best of our knowledge, it is the first successful attempt to associate IQA with scene classification in a unified multi-task architecture. Our method is evaluated on the expanded UC Merced Land-Use dataset after data augmentation. In comparison with some other methods, the experimental results show that the proposed structure makes a great improvement on both classification and IQA.

关键词： Remote sensing Image quality Task analysis computer architecture Deep learning

来源：评论

学校读者我要写书评

暂无评论

VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection

arXiv

引用

arXiv 2019年

作者： Yuan, Yuan Xiong, Zhitong Wang, Qi Northwestern Polytechnical University Xi’an China School of Computer Science Center for Optical Imagery Analysis and Learning Northwestern Polytechnical University Xi’an China

—Although traffic sign detection has been studied for years and great progress has been made with the rise of deep learning technique, there are still many problems remaining to be addressed. For complicated real-world traffic scenes, there are two main challenges. Firstly, traffic signs are usually small-size objects, which makes it more difficult to detect than large ones;Secondly, it is hard to distinguish false targets which resemble real traffic signs in complex street scenes without context information. To handle these problems, we propose a novel end-to-end deep learning method for traffic sign detection in complex environments. Our contributions are as follows: 1) We propose a multi-resolution feature fusion network architecture which exploits densely connected deconvolution layers with skip connections, and can learn more effective features for small-size object;2) We frame the traffic sign detection as a spatial sequence classification and regression task, and propose a vertical spatial sequence attention (VSSA) module to gain more context information for better detection performance. To comprehensively evaluate the proposed method, we do experiments on several traffic sign datasets as well as the general object detection dataset and the results have shown the effectiveness of our proposed method. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

FEATURE SPARSITY IN CONVOLUTIONAL NEURAL NETWORKS FOR SCENE CLASSIFICATION OF REMOTE SENSING IMAGE

FEATURE SPARSITY IN CONVOLUTIONAL NEURAL NETWORKS FOR SCENE ...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Wei Huang Qi Wang Xuelong Li School of Computer Science and Center for OPTical IMagery Analysis and Learning(OPTIMAL) Northwestern Polytechnical University Xi’an Shaanxi P. R. China

Recently, the analysis of remote sensing images has attracted a lot of attention. In the domain of scene classification, deep learning methods, especially convolutional networks (CNNs), currently achieve the best results. Although the classification performance has reached a high level, there are still some factors limiting the improvement of classification accuracy. Based on obeservation of remote sensing scene images, we fing that some scenes are quite similar though they belong to different classes. To improve the classification performance between different scenes with similar characteristics, we propose a significant Feature Sparsity Layer that can be esaily embedded into various convolutional network architectures. The proposed layer can inhibit the confusing features meanwhile stress the discriminative features, and it is used to sparse the multi-layer feature map, which is extracted by the convolutional layers. The proposed method achieves the state-of-the-art results on three datasets UC Merced Land Use, Aerial Image Data and OPTIMAL-31, and competitive result on dataset WHU-RS19.

关键词： Remote sensing Feature extraction Training Airports Bridges Convolutional neural networks Deep learning

来源：评论

学校读者我要写书评

暂无评论

Frictional Granular Matter: Protocol Dependence of Mechanical Properties

引用

Physical Review Letters 2021年第7期126卷 075501-075501页

作者： Anaël Lemaître Chandana Mondal Itamar Procaccia Saikat Roy Yinqiao Wang Jie Zhang NAVIER UMR 8205 École des Ponts ParisTech IFSTTAR CNRS UPE Champs-sur-Marne 77420 France Department of Chemical Physics the Weizmann Institute of Science Rehovot 76100 Israel Center for OPTical IMagery Analysis and Learning Northwestern Polytechnical University Xi’an 710072 China Department of Chemical Engineering Indian Institute of Technology Ropar Punjab 140001 India School of Physics and Astronomy Shanghai Jiao Tong University 800 Dong Chuan Road 200240 Shanghai China Institute of Natural Sciences Shanghai Jiao Tong University 200240 Shanghai China

Theoretical treatments of frictional granular matter often assume that it is legitimate to invoke classical elastic theory to describe its coarse-grained mechanical properties. Here, we show, based on experiments and numerical simulations, that this is generically not the case since stress autocorrelation functions decay more slowly than what is expected from elasticity theory. It was theoretically shown that standard elastic decay demands pressure and torque density fluctuations to be normal, with possibly one of them being hyperuniform. However, generic compressed frictional assemblies exhibit abnormal pressure fluctuations, failing to conform with the central limit theorem. The physics of this failure is linked to correlations built in the material during compression from a dilute configuration prior to jamming. By changing the protocol of compression, one can observe different pressure fluctuations, and stress autocorrelations decay at large scales.

关键词： Elasticity Mechanical & acoustical properties Stress

来源：评论

学校读者我要写书评

暂无评论

Experimental and Numerical Verification of Anomalous Screening Theory in Granular Matter

arXiv

引用

arXiv 2021年

作者： Mondal, Chandana Moshe, Michael Procaccia, Itamar Roy, Saikat Shang, Jin Zhang, Jie Dept. of Chemical Physics The Weizmann Institute of Science Rehovot76100 Israel Racah Institute of Physics The Hebrew University of Jerusalem Jerusalem9190 Israel Center for OPTical IMagery Analysis and Learning Northwestern Polytechnical University Xi’an710072 China Department of Chemical Engineering Indian Institute of Technology Punjab Ropar140001 India School of Physics and Astronomy Shanghai Jiao Tong University Shanghai200240 China Institute of Natural Sciences School of Physics and Astronomy Shanghai Jiao Tong University Shanghai200240 China

The concept of mechanical screening is widely applied in solid-state systems. Examples include nucleation of defects in crystalline materials, scars and pleats in curved crystals, wrinkles in strongly confined thin sheets, and cell-rearrangements in biological tissue. Available theories of such screening usually contain a crucial ingredient, which is the existence of an ordered reference state, with respect to which screening elements nucleate to release stresses. In contradistinction, amorphous materials in which a unique reference state does not exist, nevertheless exhibits plastic events that act as screening geometric charges with significant implications on the mechanical response. In a recent paper [Phys. Rev. E 104, 024904] it was proposed that mechanical strains in amorphous solids can be either weakly or strongly screened by the formation of low or high density of plastic events. At low densities the screening effect is reminiscent of the role of dipoles in dielectrics, in only renormalizing the elastic moduli. The effect of high density screening has no immediate electrostatic analog and is expected to change qualitatively the mechanical response, as seen for example in the displacement field. On the basis of experiments and simulations, we show that in granular matter, strong screening results in significant deviation from elasticity theory. The theoretical analysis, which accounts for an emergent inherent length scale, the experimental measurements and the numerical simulations of frictional granular amorphous assemblies are in agreement with each other, and provide a strong support for the novel continuum theory. © 2021, CC BY.

关键词： Amorphous materials

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：