检索结果-内蒙古大学图书馆

GAN-based data augmentation of prohibited item X-ray images in security inspection

Optoelectronics Letters 2020年第3期16卷 225-229页

作者： ZHU Yue ZHANG Hai-gang AN Jiu-yuan YANG Jin-feng Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of ChinaTianjin 300300China Institute of Applied Articial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen PolytechnicShenzhen 518055China

Convolutional neural networks(CNNs)based methods for automatic discriminant of prohibited items in X-ray images attract attention ***,it is difficult to train a reliable CNN model using the available X-ray security image databases,since they are not enough in sample quantity and ***,generative adversarial network(GAN)has been widely used in image generation and regarded as a power model for data *** this paper,we propose a data augmentation method for X-ray prohibited item images based on ***,the network structure and loss function of the self-attention generative adversarial network(SAGAN)are improved to generate the realistic X-ray prohibited item ***,the images generated by our model are evaluated using GAN-train and *** results of GAN-train and GAN-test are 99.91%and 98.82%*** implies that our model can enlarge the X-ray prohibited item image database effectively.

关键词： networks database network

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach Based on Wavelet-ICA for SAR image Speckle Suppression

A Novel Approach Based on Wavelet-ICA for SAR Image Speckle ...

引用

2006 8th International Conference on signal processing

作者： Xiaoguang Lu Ping Han Renbiao Wu Jingxiong Huang Tianjin Key Lab for Advanced Signal Processing P.O.Box 9North CampusCivil Aviation University of China ShenZhen Key Lab for Intelligent Information Processing ShenZhen University

ISBN: (纸本)0780397371

In this paper we propose a novel speckle suppression method based on the joint of wavelet transform(WT) and independent component analysis (ICA).The method employs ICA to process the wavelet coefficients of images,extracting the independent components which represent the uncorrupt images. Experimental results based on SAR(Synthetic Aperture Radar) images of MSTAR(Moving and Stationary Target Acquisition and Recognition) dataset show that the proposed method suppresses speckle effectively,and outperforms ICA and Lee filter.

关键词： SAR ICA Wavelet A Novel Approach Based on Wavelet-ICA for SAR image Speckle Suppression

来源：评论

学校读者我要写书评

暂无评论

Categorizing finger-vein images using a hierarchal approach

引用

2012 International Conference on Service-Oriented Computing, ICSOC 2012

作者： Tan, Dun Yang, Jinfeng Xu, Chenghua Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China China Institute of Electronics Chinese Academy of Science China

ISBN: (纸本)9783319029603

To improve the efficiency of finger-vein recognition system over a large database, this paper proposed a level-based framework for automatically categorizing finger-vein images. The proposed framework consists of two layers. The first is based on appearance features, and the second is based on content features. In each layer, an improved k-means algorithm is employed for clustering finger-vein images. Finally,the POC (Phase-Only-Correction) algorithm is applied for image matching. Experimental results demonstrate that the proposed method exhibits an exciting performance in recognition efficiency improvement. © Springer International Publishing 2013.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Object tracking based on local feature points

Object tracking based on local feature points

引用

International Congress on image and signal processing

作者： Wang, Haili Zhang, Liang Training Center of Engineering Technology Civil Aviation University of China Tianjin China Tianjin Key Lab. for Advanced Signal Processing Civil Aviation University of China Tianjin China

ISBN: (纸本)9781424465149

This paper presents a novel local-feature-based algorithm to track objects through frames. Real-time performance and occlusion are great challenges in object tracking. Local features are more distinctive than global features in dealing with occlusion. SURF (Speeded-Up Robust Feature) can robustly identify objects in clutter scene and occlusion. However, initial SURF algorithm has difficulty in matching accurately. Combined NN/SN (ratio of closest and next closes distances) with RANSAC (Random Sample Consensus) algorithm and location correlation of corresponding features between two frames is proposed to reduce false match and speed up the matching procedure. This method exhibits very good performance in high reliable applications, for its effectiveness and reduced complexity. Simulation on PETS database proves it effective. ©2010 IEEE.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

A novel preprocessing approach for SAR ATR

A novel preprocessing approach for SAR ATR

引用

2006 CIE International Conference on Radar, ICR 2006

作者： Ping, Han Renbiao, Wu Jingxiong, Huang Tianjin Key Lab for Advanced Signal Processing North Campus Civil Aviation University of China P.O.Box 9 Tianjin 300300 China Shenzhen Key Lab for Intelligent Information Processing Shenzhen University 518060 China

ISBN: (纸本)0780395824

In this paper, a new preprocessing approach is proposed for SAR ATR. The effect of DC (Direct Current) bias among images on the ATR performance is studied and a new preprocessing method is proposed. The alignment, amplitude compensation and DC bias removal can be done efficiently in the frequency domain. Experimental results are provided to demonstrate the performance of the proposed approach. © 2006 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

A robust vector tracking loop structure based on potential bias analysis

引用

Chinese Journal of Aeronautics 2024年第4期37卷 405-420页

作者： Qiongqiong JIA Yiran LUO Bing XU Li-Ta HSU Renbiao WU Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of ChinaTianjin 300300China Interdisciplinary Division of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University999077Hong KongChina Department of Geomatics Engineering University of CalgaryCalgary T2N1N4Canada

This paper proposes a robust vector tracking loop structure based on potential bias analysis. The influence of four kinds of biases on the existing two implementations of Vector Tracking Loops(VTLs) is illustrated by theoretical analysis and numerical simulations, and the following findings are obtained. Firstly, the initial user state bias leads to steady navigation solution bias in the relative VTL, while new measurements can eliminate it in the absolute VTL. Secondly, the initial code phase bias is transferred to the following navigation solutions in the relative VTL, while new measurements can eliminate it in the absolute VTL. Thirdly, the user state bias induced by erroneous navigation solution of VTLs can be eliminated by both of the two VTLs. Fourthly,the multipath/NLOS likely affects the two VTLs, and the induced tracking bias in the duration of the multipath/NLOS would decrease the performance of VTLs. Based on the above analysis,a robust VTL structure is proposed, where the absolute VTL is selected for its robustness to the two kinds of initialization biases;meanwhile, the instant bias detection and correction method is used to improve the performance of VTLs in the duration of the multipath/NLOS. Numerical simulations and experimental results verify the effectiveness of the proposed robust VTL structure.

关键词： Global Navigation Satellite System(GNSS) Vector Tracking Loop(VTL) Multipath Non-Line-of-Sight(NLOS) Tracking bias propagation Least Absolute Shrinkage and Selection Operator(LASSO)

来源：评论

学校读者我要写书评

暂无评论

An acoustic model of civil aviation's radiotelephony communication 8

An acoustic model of civil aviation's radiotelephony communi...

引用

8th International Conference on Computing and Pattern Recognition, ICCPR 2019

作者： Liu, Yuanqing Guo, Xiaojing Zhang, Haigang Yang, Jinfeng Key Lab for Advanced Signal Processing Civil Aviation University of China Tianjin China Civil Aviation University of China Tianjin China Shenzhen Polytechnic Shenzhen China

ISBN: (纸本)9781450376570

Civil Aviation's Radiotelephony Communication (CARC) in hina involves Chinese and English. Due to the particular grammatical structure and pronunciation of CARC, the universal cross-lingual acoustic model isn't applicable. For the purpose of achieving the Chinese-English speech recognition of CARC, this paper proposes a cross-lingual acoustic model using a sharedhidden- layer Convolution Depth Neural Network (CDNN) with hidden Markov model. It introduces the Convolution Neural Network (CNN) to overcome the diversity of speech signals. In order to shorten the training and decoding time, the Low Frame Rate (LFR) is added in the feature extraction stage. The experimental results show that the acoustic model based on CDNN is better applied to the domain of CARC. The introduction of CNN can further improve recognition performance. Adding the LFR effectively reduces the training time and the word error rate. © 2019 Association for Computing Machinery.

关键词： Radio telephone

来源：评论

学校读者我要写书评

暂无评论

Navigation domain multipath characterization using GNSS direct position estimation in urban canyon environment 35

Navigation domain multipath characterization using GNSS dire...

引用

35th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS+ 2022

作者： Huang, Jihong Sun, Rui Yang, Rong Zhan, Xingqun Chen, Wantong School of Aeronautics and Astronautics Shanghai Jiao Tong University Shanghai China Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China Tianjin China

ISBN: (纸本)9781713871361

Multipath is a common factor that degrade the performance of Global Navigation Satellite System (GNSS), especially in urban canyon and indoor environments. Due to the reflection of surrounding buildings, multiple Non-Line of Sight (NLOS) signals will arrive receiver antenna with various paths, and the Line of Sight (LOS) signals parameters such as the amplitude and phase will suffer significant distortions and fluctuation. However, due to the random feature of temporal, spatial and frequency diversity across the signal bands, it is difficult to accurately characterize the multipath effect. In this paper, a new attempt has been made to characterize the multipath fading in navigation domain using GNSS direct position estimation (DPE) algorithm. Live tests were conducted in viaduct and urban environments in Shanghai with both traditional two-step and DPE algorithm. The results show the robust of DPE no matter the receiver is moving or static. And the navigation domain manifolds for viaduct and urban scenarios are compared to characterize the multipath fading. The results demonstrate the feasibility of navigation domain multipath characterization using GNSS direct position estimation in urban canyon environment. © 2022 by Institute of Navigation. All rights reserved.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Kernel ICA for ground bounce removal with GPR

Kernel ICA for ground bounce removal with GPR

引用

International Radar Symposium, IRS 2005

作者： Gao, Qian Wu, Renbiao Li, Tang Yu, Jianping Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China Tianjin300300 China College of Information Engineering Shenzhen University Shenzhen518060 China

Landmines and unexploded ordnances are causing tremendous problems in a large number of areas throughout the world today. The ultra wideband GPR Ground Penetrating Radar is a useful tool for plastic landmine detection. For shallowly buried plastic mine, removing the ground bounce with much more energy than useful signal and with the same arrival time as useful signal is very important to following detection, SAR imaging and target recognition. This paper presents an adaptive ground bounce removal method based on Kernel ICA (KICA) algorithm and adaptive ICs selection. Experimental results based on field-test data show that the proposed method is performing very well.

关键词： Ground penetrating radar systems

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional PCA for SAR automatic target recognition

Two-dimensional PCA for SAR automatic target recognition

引用

2007 1st Asian and Pacific Conference on Synthetic Aperture Radar, APSAR 2007

作者： Xiaoguang, Lu Ping, Han Renbiao, Wu Tianjin Key Lab. for Advanced Signal Processing North Campus Civil Aviation University of China P.O.Box 9 Tianjin 300300 China

ISBN: (纸本)1424411882

In this paper, a new technique for Synthetic Aperture Radar (SAR) automatic target recognition (ATR) is developed, which is builded upon Two-Dimensional Principle Component Analysis (2DPCA). First, 2DPCA is applied to extract features in frequency domain, which is based on image matrix directly. Then support vector machine (SVM) is used for classification. Experimental results on MSTAR dataset show that the 2DPCA method both gives higher recognition rate, and are computationally more efficient than PCA. © 2007 IEEE.

关键词： Support vector machines

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：