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

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

Stereo matching using aggregated likelihood and multi-scale prior

Stereo matching using aggregated likelihood and multi-scale ...

引用

2012 3rd IEEE/IET International Conference on Audio, Language and image processing, ICALIP 2012

作者： Wang, Liang Liu, Tianliang Zhu, Xiuchang Jiangsu Provincial Key Lab. of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing 210003 China

ISBN: (纸本)9781467301718

This paper proposes a novel global stereo matching method using aggregated likelihoods and multi-scale priors. The likelihoods of dense stereo correspondences as data term can be robustly expressed by aggregated matching costs based on Weber feature descriptors in an asymmetrical linear filtering model. The multi-scale priors on disparity surface are designed to capture scene smooth term from larger neighborhood besides 4-connected neighborhood. The presented stereo approach being relatively simple does not rely on image segmentation and any scene semantic analysis. Experiments demonstrate that the proposed stereo matching algorithm can produce the dense smooth disparity results comparable to those of excellent stereo matching techniques. © 2012 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust piecewise planar stereo with modified segmentation cues in urban scenes

Robust piecewise planar stereo with modified segmentation cu...

引用

2nd International Conference on Multimedia Technology, ICMT 2011

作者： Jiao, Zengtao Liu, Tianliang Zhu, Xiuchang Jiangsu Provincial Key Lab. of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing 210003 China

ISBN: (纸本)9781612847740

This paper proposes a robust piecewise planar multiview stereo (MVS) approach specifically designed for urban scenes. These architectural scenes are problematic for traditional computer vision methods. In our work, we focus on exploiting some useful constraints of artificial structures such as piecewise coplanarity and boundaries of superpixels. Firstly, we reconstruct quasi-dense 3D point clouds of urban scenes using patches-based MVS (PMVS) method. Secondly, a set of 3D candidate planes are generated by the obtained point clouds without any assumption on the normals of planes, unlike famous Manhattan-world assumption. Then, we segment multi-view images with watershed algorithm and modify the contours of superpixels by the classical Douglas-Peucker approximation algorithm to fit the contours to the boundaries of objects in urban scenes as much as possible. Finally, we use the candidate planes as lab.ls and superpixels as nodes to formulate our Markov Random Field (MRF) optimization problem, then a piecewise planar depth map for each view is recovered by solving the optimization problem using graph-cuts. Experiments show that our method outperforms previous approaches in terms of accuracy. © 2011 IEEE.

关键词： Superpixels

来源：评论

学校读者我要写书评

暂无评论

Stereo Matching based on Robust Likelihoods and MST Leveraged Smoothness Priors

Stereo Matching based on Robust Likelihoods and MST Leverage...

引用

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

作者： Tianliang Liu Liang Wang Xiuchang Zhu Jiangsu Provincial Key Lab of Image Processing and Image Communication College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications

ISBN: (纸本)9781467321969

This paper proposes a global stereo correspondence using robust matching likelihoods and minimum spanning tree （MST） leveraged smooth priors in a probabilistic graphical model framework. The matching likelihoods of the stereo correspondence can be robustly constructed as data term by aggregating initial matching costs from Weber local descriptors using an unsymmetrical guided filtering in a linear model. The disparity priors are devised as smooth term to characterize the smoothness constraints leveraged by the MST structure. The presented stereo approach provides an effective and efficient way to reflect robust visual dissimilarity and resolve local and regional discontinuities. Experiments demonstrate that the proposed global stereo matching method can produce piecewise smooth, accurate and dense disparity map, while removing effectively the visual ambiguity of the stereo matching problem.

关键词： stereo vision Markov random field Weber descriptor minimun spanning tree QPBO optimization

来源：评论

学校读者我要写书评

暂无评论

Flicker-Free Adaptive Enhancement for Infrared Video 13

Flicker-Free Adaptive Enhancement for Infrared Video

引用

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

作者： Wei, Caixia Gan, Zongliang Nanjing University of Posts and Telecommunications Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing China

ISBN: (纸本)9781665407854

Infrared videos often suffer from low contrast and insufficient texture. In order to improve poor visual effect, a novel infrared video enhancement method is proposed, which contains intra-frame brightness enhancement and inter-frame brightness continuity adjustment. In intra-frame brightness enhancement, it has two steps including global contrast enhancement and local details enhancement. To global contrast enhancement, the processed image contrast by geometric distribution, and it is incorporated into an optimization problem with a sorted histogram of each frame to yield a modified histogram. To local details enhancement, after Retinex decomposition, the reflection component is magnified by boundary preserving filter, and this strategy can effectively suppress noise in relatively uniform regions. Furthermore, to maintain inter-frame brightness continuity, adaptive parameters are introduced through optical flow to control the combination ratio of geometric distribution histogram, in which the enhancement degree of each frame can be adjusted according to inter-frame similarity and the moving region are enhanced adaptively according to the change of each frame. Experimental results demonstrate that proposed algorithm can effectively enhance the contrast and detail of infrared video, and improve the visual effect in subjective and objective quality evaluation. © 2021 IEEE.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

A novel improved binarized normed gradients based objectness measure through the multi-feature learning 8th

A novel improved binarized normed gradients based objectness...

引用

8th International Conference on image and Graphics, ICIG 2015

作者： Zhao, Danfeng Hu, Yuanyuan Gan, Zongliang Chen, Changhong Liu, Feng Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783319219776

In this paper, we propose a novel improved binarized normed gradients (BING) objectness method based on the multi-feature boosting learning. A series of difference of gaussians (DoG) of the images with given parameters are used for the feature extraction stage, since the image DoG filter can better describe objects border. In addition, in training phase, the classifier can adaptively combine the features from different scales and different frequency components. Moreover, since the norm of the feature gradients is a simple 64D feature in the proposed framework, the computational complexity of the algorithm is in the same level compared with the BING measure. Experiments on the challenging PASCAL VOC 07 dataset show that the proposed method can not only achieve higher detection rate and average score than some current related objectness measures, but also lead to a very competitive accuracy of locating objects, even in some difficult cases. © Springer International Publishing Switzerland 2015.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Edge directed single image super resolution through the learning based gradient regression estimation 8th

Edge directed single image super resolution through the lear...

引用

8th International Conference on image and Graphics, ICIG 2015

作者： Si, Dandan Hu, Yuanyuan Gan, Zongliang Cui, Ziguan Liu, Feng Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783319219622

Single image super resolution (SR) aims to estimate high resolution (HR) image from the low resolution (LR) one, and estimating accuracy of HR image gradient is very important for edge directed image SR methods. In this paper, we propose a novel edge directed image SR method by learning based gradient estimation. In proposed method, the gradient of HR image is estimated by using the example based ridge regression model. Recognizing that the training samples of the given sub-set for regression should have similar local geometric structure based on clustering, we employ high frequency of LR image patches with removing the mean value to perform such clustering. Moreover, the precomputed projective matrix of the ridge regression can reduce the computational complexity further. Experimental results suggest that the proposed method can achieve better gradient estimation of HR image and competitive SR quality compared with other SR methods. © Springer International Publishing Switzerland 2015.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Robust face hallucination via similarity selection and representation 8th

Robust face hallucination via similarity selection and repre...

引用

8th International Conference on image and Graphics, ICIG 2015

作者： Liu, Feng Yin, Ruoxuan Gan, Zongliang Chen, Changhong Tang, Guijin Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783319219684

Face image super resolution, also referred to as face hallucination, is aiming to estimate the high-resolution (HR) face image from its low-resolution (LR) version. In this paper, a novel two-layer face hallucination method is proposed. Different from the previous SR methods, by applying global similarity selecting, the proposed approach can narrow the scope of samples and boost the reconstruction speed. And the local similarity representation step make the method have better ability to suppress noise for applications under severe condition. As a general framework, other useful algorithms can also be incorporated into it conveniently. Experiments on commonly used face database demonstrate our scheme has better performance, especially for noise face image. © Springer International Publishing Switzerland 2015.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

Retinex based flicker-free low-light video enhancement 1

引用

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

作者： Tu, Juanjuan Gan, Zongliang Liu, Feng Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

Videos captured in low light environment tend to be poor visual effect. To get better visual experience, a video enhancement algorithm based on improved center-surrounded Retinex and optical flow is proposed in this paper, which contains intra-frame brightness enhancement and inter-frame brightness continuity. In intra-frame brightness enhancement, reflection of each frame is estimated by adjusting the illumination using a weight factor, so that bright illumination is compressed to obtain a reflection with approximately uniform illumination. Then logarithmic image processing subtraction (LIPS) is adopted to enhance its contrast. To maintain inter-frame brightness continuity, the background and brightness changes of adjacent frames are measured using optical flow and just noticeable difference (JND) threshold, respectively. If the background and average brightness change little, their reflection brightness is almost the same, so LIPS parameter of previous frame is applied to current frame. Otherwise, current frame will be updated by calculating its own parameter. Experimental results demonstrate that proposed algorithm performs well in brightness continuity and detail enhancement. © Springer Nature Switzerland AG 2019.

关键词： Luminance

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：