检索结果-内蒙古大学图书馆

AMTrans:Auto-Correlation Multi-Head Attention Transformer for Infrared Spectral Deconvolution

清华大学学报自然科学版（英文版） 2025年第3期30卷 1329-1341页

作者： Lei Gao Liyuan Cui Shuwen Chen Lizhen Deng Xiaokang Wang Xiaohong Yan Hu Zhu College of Electronic and Optical Engineering & College of Flexible Electronics(Future Technology) Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjing 210003China National Engineering Research Center of Communication and Network Technology Nanjing University of Posts and TelecommunicationsNanjing 210003China School of Computer Science and Technology Hainan UniversityHaikou 570228China

Infrared spectroscopy analysis has found widespread applications in various fields due to advancements in technology and industry *** improve the quality and reliability of infrared spectroscopy signals,deconvolution is a crucial preprocessing *** by the transformer model,we propose an Auto-correlation Multi-head attention Transformer(AMTrans)for infrared spectrum sequence *** auto-correlation attention model improves the scaled dot-product attention in the *** utilizes attention mechanism for feature extraction and implements attention computation using the auto-correlation *** auto-correlation attention model is used to exploit the inherent sequence nature of spectral data and to effectively recovery spectra by capturing auto-correlation patterns in the *** proposed model is trained using supervised learning and demonstrates promising results in infrared spectroscopic *** comparing the experiments with other deconvolution techniques,the experimental results show that the method has excellent deconvolution performance and can effectively recover the texture details of the infrared spectrum.

关键词： spectroscopy spectral deconvolution transformer auto-correlation mechanism

来源：评论

学校读者我要写书评

暂无评论

Improvement and Realization of DSR Routing Protocol with QoS Support in Wireless Mesh Networks

引用

China communications 2009年第1期6卷 123-127页

作者： Gu Xiaoyan , Liu Feng image processing and image communications key lab, Nanjing University of Posts and Telecommunications, Nanjing 210003, China Image Processing and Image Communications Key Lab Nanjing University of Posts and Telecommunications Nanjing 210003 China

In Wireless Mesh Network,multimedia applications require the network to guarantee Quality-of-Service(QoS). A new QoS-aware routing protocol based on DSR named QDSR(QoS-DSR) is further proposed. QDSR guarantees the QoS of application, such as bandwidth and delay, defines routing cost function according to the number of hops of path and buffer and chooses the best path based on routing cost. Simulation results show that, compared with DSR, QDSR greatly improves the throughput, reduces the average end to end delay, improves the efficiency, satisfies the QoS of application better and has stronger applicability and expansibility.

关键词： Wireless Mesh network Quality-of-Service routing protocol bandwidth delay routing cost function

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-Stream Fusion Network for Underwater image Enhancement

引用

China communications 2024年第2期21卷 166-182页

作者： Guijin Tang Lian Duan Haitao Zhao Feng Liu Jiangsu Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and TelecommunicationsNanjing 210003China

Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual ***, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.

关键词： image enhancement multi-stream fusion underwater image

来源：评论

学校读者我要写书评

暂无评论

Free Viewpoint Action Recognition based on Self-similarities

Free Viewpoint Action Recognition based on Self-similarities

引用

2012 IEEE 11th International Conference on Signal processing(ICSP 2012)

作者： Jiao Wang Changhong Chen Xiuchang Zhu Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications

ISBN: (纸本)9781467321969

Action recognition is an important topic in computer vision and most current work focuses on view-dependent representations. In this paper, we develop a novel free viewpoint action recognition based on Self-similarity matrix (SSM), which tends to be stable across views. We choose Local Self-similarity (LSS) descriptor as our low-level feature, then SSM is calculated by computing the similarity between any pair of frame features. Each video sequence is represented using a diagonal descriptor vector extracted from the SSM. Support Vector Machines (SVM) is employed for classification. The encouraging experimental results on the public IXMAS multi-view data set demonstrate effectiveness of the proposed method.

关键词： local self-similarity descriptor self-similarity matrix diagonal feature action recognition view independent

来源：评论

学校读者我要写书评

暂无评论

A new super-resolution reconstruction method combining narrow quantization constraint set and motion estimation for H.264 compressed video

A new super-resolution reconstruction method combining narro...

引用

International Conference on image and Graphics

作者： Hu, Dong Zhao, Yingxue Xiao, Peng Jiangsu Provincial Key Lab of Image Processing and Image Communications Nanjing University of Posts and Telecommunications Nanjing 210003 China

ISBN: (纸本)9780769545417

Super-resolution (SR) reconstruction technique is mainly a task of reconstructing high resolution images from a sequence of low resolution images. The super-resolution technique for H.264 compressed video has been focused by many researchers recently. This paper briefly analyzes the narrow quantization constraint set method (NQCS), and then, in consideration of motion characteristic information of H.264 compressed video, proposes a new SR reconstruction method which combines NQCS with motion characteristic information, which are spatial domain motion estimation and frequency domain motion noise respectively. Experimental results of different standard test sequences compressed by H.264 are given. The simulation shows that both the NQCS+Mnoise method which combines NQCS with frequency domain motion noise, and the NQCS+M method which combines NQCS with spatial domain motion estimation, can get higher PNSR value than NQCS. Moreover, the NQCS+M method has better performance than NQCS+Mnoise method, and our proposed method is suitable for the SR reconstruction of H.264 compressed video. © 2011 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Unequal loss protection of embedded streams combining particle swarm optimization and local search

Unequal loss protection of embedded streams combining partic...

引用

International Conference on Multimedia and Signal processing

作者： Hu, Jiajing Hu, Dong Key Lab of Image Processing and Image Communications of Jiangsu Province Nanjing University of Posts and Telecom Nanjing 210003 China

ISBN: (纸本)9780769543567

FEC-based multiple description coding (MDC) is an effective method for the transmission of scalable video stream over noisy network. However, given the transmission bandwith, it's time-consuming to find the optimal packet number and packet length as well as reasonably allocate bits between source coding and channel coding across the packets. In this paper, we state the optimal unequal error protection(UEP) as a two-level optimization problem and use a rate-optimal solution in initial step of searching. Then, we propose a new scheme, which combines the particle swarm optimization (PSO) with the local search(LS) algorithms, so that optimal solution can be found in more efficient way. Experimental results for the 3D set partitioning in hierarchical trees (SPIHT) coders show that the new algorithm provides close to optimal average peak signal-to-noise ratio performance and that its' running time is obviously lower than that of previously known algorithms.© 2011 IEEE.

关键词： Particle swarm optimization (PSO

来源：评论

学校读者我要写书评

暂无评论

Improvement of virtual view rendering based on depth image

Improvement of virtual view rendering based on depth image

引用

International Conference on image and Graphics

作者： Hu, Dong Sun, Jianfei Xu, Ping Jiangsu Provincial Key Lab of Image Processing and Image Communications Nanjing University of Post and Telecommunications Nanjing 210003 China

ISBN: (纸本)9780769545417

Virtual view rendering has great importance in 3-D display. In order to get high-quality image of an arbitrary view from 2-D source image, improvement on depth-image based rendering (DIBR) is studied in this paper. By analyzing the process of virtual view rendering of DIBR, an improved method is proposed, which generates new view by modifying parallax of two views and incorporating image inpainting. The parallax is deduced from depth information, and modified afterwards according to parallax gradient, so as to reduce hole regions before generating new view by 3-D image warping. To further remove the remaining holes, image inpainting combining texture and depth information is incorporated. Experimental results show the superiority of the proposed method. © 2011 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Liver Tumor Segmentation Based on Three-Channel Cascaded SEU-Nets and C-LSTM 13

Liver Tumor Segmentation Based on Three-Channel Cascaded SEU...

引用

13th International Conference on Wireless communications and Signal processing, WCSP 2021

作者： Li, Yarong Hu, Dong Nanjing University of Posts and Telecommunications Jiangsu Province's Key Lab of Image Processing and Image Communications Nanjing China

ISBN: (纸本)9781665407854

An abdominal CT liver tumor segmentation algorithm based on three-channel cascade SEU-Nets and C-LSTM is proposed in this paper. Concerning the accuracy of most known algorithms is limited by using single-phase CT images, the proposed method takes advantage of the different characteristics of the lesion area in the venous phase, arterial phase and delayed phase, and the correlation between slices in enhanced CT images. It uses three-channel SEU-Nets as the encoder to extract image features of slices in three phases, and uses 3D convolution to extract the relationship between slices for the same location at different phases. And then it uses C-LSTM to extract the inter-slice sequence feature relationship. Finally, the decoder outputs fine segmentation of liver tumor output. 40 sets of high-quality abdominal-enhanced CT images of the liver and liver tumors used in the experiment were collected in the provincial central hospital and annotated by experts. Comparisons are carried out with well-known methods, such as improved CFCNs, H-DenseUNet network and DBAs-based multi-scale DC-CUNets segmentation network. Experimental results show that the average segmentation accuracy of proposed algorithm is 7.04% higher than that of the multi-scale DC-CUNets segmentation network based on DBAs, and the DICE coefficient is improved by 4.89%. © 2021 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Robust license plate detection through auxiliary information and context fusion model 2nd

Robust license plate detection through auxiliary information...

引用

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Wang, Ning Liu, Feng Gan, Zongliang Jiangsu Province Key Lab on Image Processing and Image Communications Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783030317256

License plate detection has wide applications in the intelligent transportation system, while it still remains challenges to improve the robustness under various shooting distance and observation angles. To get better performance, a novel convolutional-neural-network-based method is proposed, which is achieved with auxiliary information and context fusion model. First, the auxiliary information is employed in our framework, which corresponds with resolutions, orientations and shapes of license plates. Specifically, the multiple resolutions are collected through integrating multi-level features of convolution hierarchy. Besides the various scales and ratios, the region proposal network RPN with multi-angle anchors and branching structure is applied to generate proper proposals. Second, an effective context fusion model is designed to fully exploit the hidden correlation between license plates and contextual properties. The local and contextual features are independently learned in the dual pathways, which are later joint to form a powerful representation in subsequent layers. Comprehensive experiments on the publicly available datasets confirm the effectiveness of the proposed method. © Springer Nature Switzerland AG 2019.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

An efficient fast inter mode decision algorithm for h.264/avc ***

An efficient fast inter mode decision algorithm for h.264/av...

引用

2009 WRI International Conference on communications and Mobile Computing, CMC 2009

作者： Huang, Huaibin Hu, Dong Key Lab. of Image Processing and Image Communications of Jiangsu Province Nanjing University of Posts and Telecom Nanjing 210003 China

ISBN: (纸本)9780769535012

An efficient fast inter mode decision algorithm for the baseline H.264/AVC video coding is proposed in this paper. The main idea of the algorithm is to reduce the number of candidate modes for Rate Distortion Optimization(RDO) by using early mode detection in four different levels, viz. SKIP mode detection, type detection at macroblock-level, type detection at submacroblock-level and intra modes detection. In addition, the correlation of cost of current MB and the one of previous frame, as well as the cost's monotonous property are both used to help the mode decision. Compared to JM8.6 reference software, our algorithm can save encoding time 71.743% on average with negligible PSNR loss, which is very helpful for H.264/AVC inter frame encoding. © 2009 IEEE.

关键词： Electric distortion

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：