检索结果-内蒙古大学图书馆

第十四届中国卫星导航年会

作者： Qiongqiong Jia Weipeng Li Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China

The Popular of Global Navigation Satellite System(GNSS) is attributed to its good ***,the performance of a conventional GNSS receiver is severely degraded or even failed to provide services in complex *** Position Estimation(DPE) combines all the visible satellite signals for energy accumulation in the navigation domain first,and then the navigation solution is estimated directly from the accumulation *** the navigation performance of GNSS can be effectively improved in complex environments by ***,the signal accumulation of DPE requires calculating the correlation values of all the visible satellite signals at each candidate grid in the navigation domain,the computation load of which limits its *** alleviate this problem,a GPU-based parallel implementation of the DPE receiver is designed,which decomposes the operations involved in the joint accumulation into three levels of parallel *** effectiveness of the designed parallel implementation of the DPE receiver is verified by experiment *** the availab.e hardware in our lab.ratory,the designed DPE implementation improves the efficiency to approximately 146 times on average over the conventional DPE implementation.

关键词： Direct position estimation Complex environments GPU Parallel processing Joint accumulation

来源：评论

学校读者我要写书评

暂无评论

Sparse Bayesian Network for Fast Micro-Doppler Analysis

Sparse Bayesian Network for Fast Micro-Doppler Analysis

引用

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Zhang, Jiongge Dong, Hang Tian, Long He, Xiongpeng Sun, Huimin Liu, Yuan Pilot School of Software Engineering Xidian University Xi'an China Key Lab. of Radar Signal Processing Xidian University Xi'an China Electronic Engineering Research Institute Xi'an China Nanyang Technological University Singapore

ISBN: (纸本)9798350368741

Micro-Doppler Analysis (MDA) of rigid-body targets is crucial for various practical downstream tasks such as target imaging and recognition. Radar echoes from micro-moving targets typically represent non-stationary signals and are often described using the parameterized Time-Varying Auto Regressive (TVAR) model. Sparse Bayesian Learning (SBL) is commonly employed to estimate time-invariant coefficients, thereby achieving high-resolution micro-Doppler time-frequency distributions. Despite its effectiveness, SBL-based optimization methods often face inefficiency due to the computational burden of inverse operation. To address this challenge and enhance the efficiency of MDA based on TVAR model, we propose a Sparse Bayesian Network (SBN) that unfolds a fast Mean Field SBL (MF) using a deep variational autoencoding framework. This method retains the optimization effectiveness of SBL while incorporating the inference efficiency of Deep Neural Networks (DNNs). Our proposed method demonstrates strong generalization capabilities, performing well on both simulated and measured radar echoes. © 2025 IEEE.

关键词： Micro-Doppler Analysis (MDA) Rigid-body Target Sparse Bayesian Network (SBN)

来源：评论

学校读者我要写书评

暂无评论

DACNet: Single Image Dehazing Network Based on Attention Mechanism

DACNet: Single Image Dehazing Network Based on Attention Mec...

引用

Intelligent Communications and Computing (ICC), International Conference on

作者： Yongling Liu Ping Han Wanwei Wang Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China Tianjin China

Aiming at the problem that atmospheric scattering model-based haze removal methods are prone to degradation of haze removal performance due to inaccurate parameter estimation, a single-image haze removal network based on the attention mechanism is proposed for direct restoration of haze-free images. The network consists of encoder and decoder, where the traditional convolution is replaced by combining dilated convolutions with different dilated rates for acquiring and processing haze-related image features. Due to the different weighted information contained in different channel features, an increased attention mechanism is used to enhance the feature representation of important channels through adaptive learning channel features, thereby enabling the encoder to pay more attention to channel information in the haze region. In the encoding and decoding structure, dilated convolution and attention mechanism are used in combination for image dehazing for the first time. By targeting the network to pay attention to the regions with high fog distribution while increasing the sensory field to obtain global information. The method presented in this paper improves the ability of network to process hazy images and brings a new breakthrough in the field of hazy image processing. Experiments show that the algorithm proposed in this paper achieves significant improvements in both subjective and objective indicators comparing with many state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Infrared Small Target Detection Algorithm Based on Improved Deeplab.3+

Infrared Small Target Detection Algorithm Based on Improved ...

引用

6th International Conference on Intelligent Computing and signal processing (ICSP)

作者： Mengfei Qi Guimin Jia Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China Tianjin China

Infrared small target detection aims to segment small targets from the infrared images. Aiming at the problem of infrared small target detection, an improved algorithm is proposed based on Deeplab.3+ network. For the encoding part of Deeplab.3+, considering the small size of infrared small targets, the dilation rate of ASPP module is adjusted to capture the features of small targets more effectively. For the small targets are prone to lose spatial information during feature extraction, a location enhancement module is introduced to supplement accurate location information and to improve the accuracy of detection. In order to preserve detail information, an additional feature map is added from the backbone network to fuse detail information and semantic information for the decoding part of Deeplab.3+. Experimental results have demonstrated that the proposed algorithm is capable of enhancing the detection performance of Deeplab.3+ network in the infrared small target detection task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling of the Multipath Effect on the Vector Tracking Loop

SSRN

引用

SSRN 2023年

作者： Jia, Qiongqiong Wu, Renbiao Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China Tianjin300300 China

The vector tracking loop (VTL), where the internal aiding is achieved with multi-channel information sharing, is generally superior to the traditional scalar tracking loop (STL). Multipath effect on the VTL is illustrated and theoretical models of multipath induced tracking bias to the VTL, for both the coherent and non-coherent discriminators, are established. Correctness of the established models are validated by numerical simulations. It is revealed that the multipath induced tracking bias to the VTL is dependent on the code phase offset, which is originated from its internal aiding nature. Conclusions are drawn based on the established models: multipath induced tracking bias to the VTL is not greater than it to the STL in constructive multipath case, while in destructive multipath case, the bias envelop of VTL is not superior to STL. We finally define the positive and negative maximum biases as the maximum VTL bias envelop to stand for the worst case performance. Abnormal phenomenon appears in the maximum VTL bias envelop is also analyzed in detail, with the conclusion that the discriminate curve distortion becomes more severe as the correlator spacing and the relative amplitude of the multipath signal increase. © 2023, The Authors. All rights reserved.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Improving Integrality of Detected Moving Objects Based on Image Matting

引用

Chinese Journal of Electronics 2025年第4期23卷 742-746页

作者： Liang Zhang Haili Wang Tao Deng Xiaomei He Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China Tianjin China Training Center of Engineering Technology Civil Aviation University of China Tianjin China

The integrality of moving objects is the basis for video-based object tracking and action analysis. But it often becomes unreliable as a result of shadow elimination when the object has similar properties with real shadow. The proposed methods manage to improve the integrality of detected moving objects as much as possible, by image matting operated on candidate shadow regions. Existing approaches for image matting require manual lab.ling of foreground and background. Considering the moving feature points in shadow may cause classification errors, we propose automatic scribbling methods based on Scale invariant feature transform (SIFT) and Speeded-up robust feature (SURF) respectively. Experiments demonstrate that our methods eliminate real shadow effectively and improve object segmentation in the case of object parts and shadows presenting similar characteristics.

关键词： Object segmentation Transforms Manuals Object tracking lab.ling

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

Speech Recognition Model of Civil Aviation Radiotelephony Communication Based on Improved Conformer

Speech Recognition Model of Civil Aviation Radiotelephony Co...

引用

2022 International Conference on Automation, Robotics and Computer Engineering, ICARCE 2022

作者： Xiao, Zewei Jia, Guimin Shi, Bo Civil Aviation University of China Tianjin Key Lab for Advanced Signal Processing China Civil Aviation University of China College of Electronic Information and Automation Tianjin China

ISBN: (纸本)9781665475488

Radiotelephony communication has a special grammatical structure and pronunciation, and it is difficult to apply the model of generic speech recognition directly to the field of radiotelephony communication. We propose a Conv1DSlide-Conformer model for speech recognition of radiotelephony communication. The sliding-window attention mechanism is used instead of the self-attention mechanism to improve the decoding speed of the model and increase the adaptability of the model to radiotelephony communication. The convolutional module is used instead of the feedforward neural network module to make the encoder focus more on local information. The improved Conformer model processes the FBANK features of radiotelephony communication and can extract high-dimensional features that better fit the characteristics of radiotelephony communication. The use of concatenated temporal classification (CTC) combined with a data augmentation strategy assists training to speed up convergence during model training and reduce the complexity of model training. Decoding is assisted by CTC and language models to improve the performance of speech recognition. The experimental results show that the improved Conformer speech recognition model in this paper reduces the word error rate to 8.1% and 7.8% on the actual Chinese radiotelephony communication speech dataset. © 2022 IEEE.

关键词： Radio telephone

来源：评论

学校读者我要写书评

暂无评论

Clutter Suppression of Wind Farm for Airborne Radar Based on EFA

Clutter Suppression of Wind Farm for Airborne Radar Based on...

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Zhang, Ying Zhang, Xinyun He, Weikun Wang, Xiaoliang Civil Aviation University of China Tianjin Key Lab for Advanced Signal Processing Tianjin China

ISBN: (纸本)9781665498142

With the rapid development of wind power generation, the clutter generated by wind farms may lead to the problems such as decreased detection probability, increased false alarm rate, and target track divergence. Research on the wind farm clutter mitigation technology for airborne radar is vital. Considering the special problems of the wind farm clutter mitigation for airborne radar, such as the less prior information and the more complicated spectrum of the echoes, it is difficult to suppress the wind farm clutter with non-Gaussian and dynamic characteristics. In this paper, the extended factored approach (EFA) algorithm is used to suppress the wind farm clutter through space-time adaptive processing of airborne array radar echoes. The EFA algorithm does not need the prior information of wind farm clutter or a large number of training data and can adaptively form null with a certain width in the Doppler domain. The null is used to suppress the wind farm clutter, which can avoid the interference of the wind farm clutter on the detection of aircraft targets and improve the detection probability of airborne radar. The experiment results verify the effectiveness of the proposed method. © 2021 IEEE.

关键词： airborne radar clutter suppression extended factored approach wind farms

来源：评论

学校读者我要写书评

暂无评论

IRSEnet: Differentially Private Image Generation with Multi-Scale Feature Extraction and Residual Channel Attention 13

IRSEnet: Differentially Private Image Generation with Multi-...

引用

13th International Conference on Intelligent Control and Information processing, ICICIP 2025

作者： Li, Jiahao Wang, Zhongshuai Ghazali, Kamarul Hawari Bin Yan, Suqing Lan, Rushi Sun, Xiyan Luo, Xiaonan Guangxi Key Lab. of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Centre for Advanced Industrial Technology University of Malaysia Pahang Al-Sultan Abdullah Pahang Pekan26600 Malaysia Int. Joint Research Lab. of Spatio-temporal Information and Intelligent Location Services Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9798331516147

Privacy-preserving image generation is particularly crucial in fields like healthcare, where data are both sensitive and limited. However, effective privacy preservation often compromises the visual quality and utility of the generated images due to privacy budget constraints. To address this issue, in this paper, We propose a novel network architecture, IRSEnet, which combines multi-scale feature extraction technology and residual channel attention mechanisms, aiming to enhance the visual quality of generated images and improve the performance of downstream classification tasks under differential privacy. The differential privacy mechanism ensures the security of sensitive data during training, while the multi-scale feature extraction module enhances feature extraction capabilities through parallel convolutional layers at multiple scales. Additionally, the channel attention module dynamically adjusts channel weights to focus on the most discriminative features. Experimental results demonstrate that this model significantly improves the utility of generated images and the accuracy of downstream classification tasks while preserving privacy. Future work will explore the application of this approach on larger datasets and across more diverse tasks. © 2025 IEEE.

关键词： Differential privacy

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：