检索结果-内蒙古大学图书馆

23rd IEEE international workshop on Multimedia Signal processing (IEEE MMSP)

作者： Sippel, Frank Seiler, Juergen Kaup, Andre Friedrich Alexander Univ Erlangen Nurnberg FAU Multimedia Commun & Signal Proc Cauerstr 7 D-91058 Erlangen Germany

ISBN: (纸本)9781665432870

Using light spectra is an essential element in many applications, for example, in material classification. Often this information is acquired by using a hyperspectral camera. Unfortunately, these cameras have some major disadvantages like not being able to record videos. Therefore, multispectral cameras with wide-band filters are used, which are much cheaper and are often able to capture videos. However, using multispectral cameras requires an additional reconstruction step to yield spectral information. Usually, this reconstruction step has to be done in the presence of imaging noise, which degrades the reconstructed spectra severely. Typically, same or similar pixels are found across the image with the advantage of having independent noise. In contrast to state-of-the-art spectral reconstruction methods which only exploit neighboring pixels by block-based processing, this paper introduces non-local filtering in spectral reconstruction. First, a block-matching procedure finds similar non-local multispectral blocks. Thereafter, the hyperspectral pixels are reconstructed by filtering the matched multispectral pixels collaboratively using a reconstruction Wiener filter. The proposed novel procedure even works under very strong noise. The method is able to lower the spectral angle up to 18% and increase the peak signal-to-noise-ratio up to 1.1dB in noisy scenarios compared to state-of-the-art methods. Moreover, the visual results are much more appealing.

关键词： Spectral reconstruction Spectroscopy Multi-spectral Imaging Hyperspectral Imaging

来源：评论

学校读者我要写书评

暂无评论

DisCrossFormer: A Deep Light-Weight image Super Resolution Network Using Disentangled Visual Signal processing and Correlated Cross-Attention Transformer Operation

DisCrossFormer: A Deep Light-Weight Image Super Resolution N...

引用

IEEE workshop on Machine Learning for Signal processing

作者： Alireza Esmaeilzehi Mohammad Javad Rajabi Hossein Zaredar M. Omair Ahmad The Edward S. Rogers Sr. Department of Electrical and Computer Engineering University of Toronto Toronto Ontario Canada Department of Computer Engineering Amirkabir University of Technology Tehran Iran Department of Electrical and Computer Engineering Concordia University Montreal Quebec Canada

ISBN: (数字)9798350372250

ISBN: (纸本)9798350372267

Deep neural networks that employ transformer operations have provided state-of-the-art performances for the task of image super resolution (SR). However, processing the non-local information in the visual signals by the transformers often involves increasing the network complexity. In order to develop a light-weight SR network that can process non-local information for providing superior performance, in this paper, we propose the correlated cross-attention operation. Further, we design a novel overall architecture for our SR network, which processes the disentangled information of the low-resolution images based on the presence of various objects in the visual signals. Disentangling the information of the input low-resolution images facilitates learning by paying more attention to processing a certain number of objects (and not all of them) in the visual signals at a time. The results of various experiments show the effectiveness of both ideas in generating super-resolved images with higher qualities.

关键词： Visualization Conferences Superresolution Machine learning Artificial neural networks Benchmark testing Transformers Complexity theory Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Multiscale Graph Construction Using non-local Cluster Features

Multiscale Graph Construction Using Non-Local Cluster Featur...

引用

IEEE workshop on Machine Learning for Signal processing

作者： Reina Kaneko Hayate Kojima Kenta Yanagiya Junya Hara Hiroshi Higashi Yuichi Tanaka Osaka University Japan Tokyo University of Agriculture and Technology Japan

ISBN: (数字)9798350372250

ISBN: (纸本)9798350372267

This paper presents a multiscale graph construction method using both graph and signal features. Multiscale graph is a hierarchical representation of the graph, where a node at each level indicates a cluster in a finer resolution. To obtain the hierarchical clusters, existing methods often use graph clustering; however, they may ignore signal variations. As a result, these methods could fail to detect the clusters having similar features on nodes. In this paper, we consider graph and node-wise features simultaneously for multiscale clustering of a graph. With given clusters of the graph, the clusters are merged hierarchically in three steps: 1) Feature vectors in the clusters are extracted. 2) Similarities among cluster features are calculated using optimal transport. 3) A variable k-nearest neighbor graph (V $k$ NNG) is constructed and graph spectral clustering is applied to the V $k$ NNG to obtain clusters at a coarser scale. Additionally, the multiscale graph in this paper has non-local characteristics: Nodes with similar features are merged even if they are spatially separated. In experiments on multiscale image and point cloud segmentation, we demonstrate the effectiveness of the proposed method.

关键词： Point cloud compression image segmentation Machine learning algorithms image resolution Signal processing algorithms Machine learning Nearest neighbor methods Feature extraction Vectors Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Experimental Results of local Backprojection for Monostatic THz SAR Imaging

Experimental Results of Local Backprojection for Monostatic ...

引用

international workshop on Mobile Terahertz Systems (IWMTS)

作者： Yevhen Ivanenko Aman Batra Viet Thuy Vu Mats I. Pettersson Thomas Kaiser Blekinge Institute of Technology Karlskrona Sweden University of Duisburg-Essen Duisburg Germany

ISBN: (数字)9798350365832

ISBN: (纸本)9798350365849

The use of THz frequencies has enabled the opportunity to perform synthetic-aperture radar (SAR) imaging at the sub-mm level. It is of great interest for applications where high-resolution remote sensing in short range is required. However, with the increase of the operating frequencies from microwave to THz, the SAR image formation algorithms work with a larger amount of data and become more sensitive to phase errors that can be caused by insufficient signal sampling rate or physical factors that cause platform deviations. This motivates the use of fast image formation capable to handle phase errors. In this paper, we present the experimental results on the performance of the local backprojection (LBP) algorithm for processing THz SAR signals. The LBP algorithm has been tested with the real data in the frequency range 0.325–0.5 THz. The results demonstrate the efficiency of the LBP algorithm for the SAR scene reconstruction and highlight the necessity of the use of two times higher signal upsampling to achieve reconstruction accuracy similar to the global backprojection algorithm.

关键词： Terahertz wave imaging Radar remote sensing Accuracy Heuristic algorithms Signal sampling approximation algorithms Radar polarimetry Reliability image reconstruction Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Person Re-identification Based on Fusion of Shared Feature Branches 1

引用

3rd international Conference on Artificial Intelligence Logic and Applications, AILA 2023

作者： Zhang, Yong Zhan, Zhilong Zong, Tuo Wang, Weiwen Bao, Xianyu Research Institute of Intelligent Information Shenzhen University Guangdong Shenzhen518060 China Shenzhen Cosun Sign Smart-Tech Co. Ltd. No. 1 and No.3 Workshop Guangdong Shenzhen518117 China Shenzhen Academy of Inspection and Quarantine No. 1011 Guangdong Shenzhen518045 China

ISBN: (数字)9789819978694

ISBN: (纸本)9789819978687

Based on improvement of the existing person re-identification network model and investigating person re-identification related problems on open datasets, a pedestrian re-identification method that incorporates shared feature branching as well as a fused attention mechanism is proposed. First, the benchmark network framework of pedestrian re-identification method is formed by image pre-processing method, generalized average pooling and loss function together, and BNNeck structure is added to optimize the problem of inconsistent multi-loss objectives before obtaining classification features. Second, the global feature branching structure is proposed to be assisted by shared feature branching, which can effectively assist global feature branching to obtain more distinguishable pedestrian features and the attention network is combined with person re-recognition using a network structure that fuses non-local modules with channel attention to fully utilize the feature information of pedestrian images. Finally, the performance improvement of the benchmark network with shared feature branching and the fused attention mechanism approach is demonstrated by experiments on the re-identification dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Algorithms for image processing of Micro-Objects of Medical Diagnostics Systems

Algorithms for Image Processing of Micro-Objects of Medical ...

引用

international Russian Smart Industry Conference (SmartIndustryCon)

作者： Isroil I. Jumanov Rustam A. Safarov Department of “Artifical intellegence and information systems” Samarkand State University named after Sharof Rashidov Samarkand Uzbekistan Department of Control Theory and Information Security Samarkand State University named after Sharof Rashidov Samarkand Uzbekistan

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

Constructive approaches, principles, models for optimizing the identification of micro-objects based on the use of statistical, dynamic models with mechanisms for filtering noise, foreign particles on images of medical objects and pollen grains have been developed. Methods for optimizing the identification of micro-objects with the selection of characteristic objects in the image, the combination of image models with the mechanisms of segmentation, filtering, transformation, and alignment of the laser image processing zone with the CAD model are proposed. Algorithms for selecting the contours of objects on an image using a border detector in the transverse direction to each vector of the CAD model have been developed. Modeling of images of microsamples for medical diagnostics of chest diseases was carried out. The width, straightness of the boundaries of structural objects, local defects, parameters of regulation and synchronization of the components of the vision system are determined. Algorithms for image processing under conditions of a priori insufficiency, uncertainty of parameters, and low accuracy of data processing are studied. A mechanism for suppressing impulse noise and noise is implemented based on various filtering methods, preserving the boundaries of objects and small-sized parts. Mathematical expressions for estimating identification errors due to non-stationarity, inadequacy of approximation, interpolation, extrapolation of the image contourare obtained, which are synthesized with cubic, biquadratic, interpolation spline functions and wavelet transforms. A software package for recognition and classification of micro-objects has been developed.

关键词： Solid modeling Interpolation image segmentation Filtering Measurement by laser beam Laser modes Vectors Object recognition Synchronization Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

Algorithms for image processing of Micro-Objects of Medical Diagnostics Systems

Algorithms for Image Processing of Micro-Objects of Medical ...

引用

2025 international Russian Smart Industry Conference, SmartIndustryCon 2025

作者： Jumanov, Isroil I. Safarov, Rustam A. Samarkand State University named after Sharof Rashidov Department of 'Artifical intellegence and information systems' Samarkand Uzbekistan Samarkand State University named after Sharof Rashidov Department of Control Theory and Information Security Samarkand Uzbekistan

ISBN: (纸本)9798331511241

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Depth Completion via A Dual-Fusion Method 26

Depth Completion via A Dual-Fusion Method

引用

26th international Conference on Pattern Recognition / 8th international workshop on image Mining - Theory and Applications (IMTA)

作者： Yang, Shuwen Xiao, Luwei Zhang, Junhang Fu, Zhichao Ma, Tianlong He, Liang East China Normal Univ Shanghai Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Depth completion technology based on multi-level feature fusion (MF) strategy has recently achieved remarkable success. However, the existing MF-based methods treat RGB features and depth map features equally when performing modal fusion but ignore the difference in semantic richness and sparsity between them, which leads to the results generated by these methods overfitting the shape of RGB and harm to the accuracy of depth value. To address this problem, we proposed a novel dual fusion (DF) strategy for MF-based depth completion, which can prevent overfitting by weakening the influence of RGB features on the generated results through two fusion stages. The entire DF framework consists of two multi-level fusion modules. The first fusion module performs a simple fusion of RGB features and depth features, while the second fusion module enriches the sparse image representation with the previously obtained fused features. Besides, we utilize non-local sparse attention to solve the problem that ordinary convolution is not capable of expressing depth map features enough. We test our approach on the outdoor KITTI test set and achieve the state-of-the-art (SOTA) performance in RMSE. Extensive experiments on the indoor NYUv2 dataset and KITTI validation set further demonstrate that our approach outperforms existing MF-based methods.

关键词： Shape Convolution Semantics image representation Feature extraction Data mining

来源：评论

学校读者我要写书评

暂无评论

image compression and enlargement algorithms

引用

international Journal of Circuits, Systems and Signal processing 2021年 15卷 836-846页

作者： Burova, I.G. Dem’yanovich, Yu.K. Terekhov, A.N. Altynova, A.Yu. Satanovskiy, A.D. Babushkin, A.A. St. Petersburg State University 7/9 Universitetskaya nab St.Petersburg199034 Russia

In some cases, there are problems associated with the compression and enlargement of images. The use of splines is quite effective in some cases. In this paper, a new image compression algorithm is presented. The features of increasing the size of an image when using local polynomial or non-polynomial splines are considered. The main method for enlarging an image is based on the use of splines of the second and third order of approximation. Polynomial and trigonometric splines are considered. To speed up the process of enlarging the image, we used the parallelization techniques. © 2021, North Atlantic University Union NAUN. All rights reserved.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

IEEE 23rd international workshop on Multimedia Signal processing, MMSP 2021

IEEE 23rd International Workshop on Multimedia Signal Proces...

引用

23rd IEEE international workshop on Multimedia Signal processing, MMSP 2021

ISBN: (纸本)9781665432870

The proceedings contain 108 papers. The topics discussed include: hyperspectral image reconstruction from multispectral images using non-local filtering;a sub-band approach to deep denoising wavelet networks and a frequency-adaptive loss for perceptual quality;analysis of top-down connections in multi-layered convolutional sparse coding;blind image separation for document restoration using plug-and-play approach;regularizing the deep image prior with a learned denoiser for linear inverse problems;attention-based stylization for exemplar image colorization;rule of thirds and simplicity for image aesthetics using deep neural networks;leader and breakaway detection in racing sports videos;convolutional neural network-driven optimal prediction for image reversible data hiding;how to train no reference video quality measures for new coding standards using existing annotated datasets?;and a point-to-distribution joint geometry and color metric for point cloud quality assessment.

关键词：

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：