检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Cai, Zhefei Fan, Yingle Fang, Tao Wu, Wei Laboratory of Pattern Recognition and Image Processing Hangzhou Dianzi University Hangzhou310018 China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Zhejiang310058 China

The accuracy of skin lesion segmentation is of great significance for the subsequent clinical diagnosis. In order to improve the segmentation accuracy, some pioneering works tried to embed multiple complex modules, or used the huge Transformer framework, but due to the limitation of computing resources, these type of large models were not suitable for the actual clinical environment. To address the coexistence challenges of precision and lightweight, we propose a visual saliency guided network (VSGNet) for skin lesion segmentation, which generates saliency images of skin lesions through the efficient attention mechanism of biological vision, and guides the network to quickly locate the target area, so as to solve the localization difficulties in the skin lesion segmentation tasks. VSGNet includes three parts: Color Constancy module, Saliency Detection module and Ultra Lightweight Multi-level Interconnection Network(ULMI-Net). Specially, ULMI-Net uses a U-shaped structure network as the skeleton, including the Adaptive Split Channel Attention (ASCA) module that simulates the parallel mechanism of biological vision dual pathway, and the Channel-Spatial Parallel Attention (CSPA) module inspired by the multi-level interconnection structure of visual cortices. Through these modules, ULMI-Net can balance the efficient extraction and multi-scale fusion of global and local features, and try to achieve the excellent segmentation results at the lowest cost of parameters and computational complexity. To validate the effectiveness and robustness of the proposed VSGNet on three publicly available skin lesion segmentation datasets (ISIC2017, ISIC2018 and PH2 datasets). The experimental results show that compared to other state-of-the-art methods, VSGNet improves the Dice and mIoU metrics by 1.84% and 3.34%, respectively, and with a 196× and 106× reduction in the number of parameters and computational complexity. This paper constructs the VSGNet integrating the biological vision m

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

A Web-Based HD Telemedicine System for Remote Psychotherapy

A Web-Based HD Telemedicine System for Remote Psychotherapy

引用

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Ling Li Hua Yang Hang Su Yihua Cao Shibao Zheng Institution of Image Communication and Information Processing Department of EE Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiao Tong University Shanghai China

With the accelerated global urbanization and life rhythm, an increasing physical and mental stress has been imposed, which led to a variety of problems that could not be ignored. This paper proposes a novel web-based telemedicine system that is focusing on psychotherapy. Considering the requirement of the psychological treatment, the function of system contains high definition video monitoring, two-way voice talkback, physiology parameters monitoring and data management based on database. The solution of the system is presented in the paper, including the hardware and software design. Some key issues in the system, including HD video processing, physiological parameters processing, are also discussed. Finally, the demonstration system and performance evaluation are presented.

关键词： Medical services Biomedical monitoring High definition video Servers Telemedicine Databases Decoding

来源：评论

学校读者我要写书评

暂无评论

Coarse carrier and timing synchronization for interleaved OFDMA uplink system

Coarse carrier and timing synchronization for interleaved OF...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Ruiqin Miao Jun Sun Lin Gui Jian Xiong Institute of Image Communication and Information Processing Department of Electronic Engineering Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9781424444618

In orthogonal frequency division multiple access (OFDMA) uplink system, estimations of time delay and carrier frequency offset (CFO) are both particularly challenging. In this paper, a coarse CFO and time delay estimation method is proposed for interleaved OFDMA uplink system. By exploiting the special scheme of interleaved OFDMA, the repetitive time-domain training symbol is designed, and the training sequences for different users have good autocorrelation and cross-correlation properties. Furthermore, the time delay and CFO estimation metrics are presented by making certain correlation between the received training symbol and the local sequence. Through searching peak of the proposed metrics, integral CFO of many subcarriers spaces for each user can be estimated, and then timing delay for each user can be found. Simulations illustrate the proposed estimation scheme can get good performance under multipath channel.

关键词： Timing Delay estimation Delay effects Frequency conversion Frequency estimation Frequency synchronization Time domain analysis Autocorrelation Extraterrestrial measurements Multipath channels

来源：评论

学校读者我要写书评

暂无评论

A QoE friendly rate adaptation method for DASH

A QoE friendly rate adaptation method for DASH

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Yuming Cao Xiaoquan You Jia Wang Li Song Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Multi Media Processing and Transmissions Shanghai

MPEG-DASH introduced open standards into HTTP streaming, which was a huge step forward. The scope of the MPEG-DASH standard was limited to the Media Presentation Description (MPD) format of the manifest files as well as the segmentation standards for the server, but did not include the client application as part of their standards. Particularly a good representation switching algorithm at DASH client should adapt to time varying bandwidth with better QoE (Quality of Experience). In this paper, we propose a QoE friendly rate adaptation method which can achieve less switching times and more gradual quality change. To achieve these purposes, we propose a fixed-interval buffer model, which keeps the representation level unchanged whenever the media buffer size is within the preset interval. We also design a step-wise switch-up method to prevent buffer overflow and a switch-down method based on intermediate quality level to prevent buffer underflow. A quick boot algorithm is introduced to fully improve the performance of the proposed scheme. Experimental results show that the proposed algorithm can achieve more satisfactory results compared with existing ones.

关键词： Bandwidth Bit rate Switches Heuristic algorithms Streaming media Standards Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Sub clustering K-SVD: Size variable dictionary learning for sparse representations

Sub clustering K-SVD: Size variable dictionary learning for ...

引用

IEEE International Conference on image processing

作者： JianZhou Feng Li Song XiaoKang Yang Wenjun Zhang Institute of Image Communication & Information Proc Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiaotong University Shanghai China

Sparse signal representation from overcomplete dictionaries have been extensively investigated in recent research, leading to state-of-the-art results in signal, image and video restoration. One of the most important issues is involved in selecting the proper size of dictionary. However, the related guidelines are still not established. In this paper, we tackle this problem by proposing a so-called sub clustering K-SVD algorithm. This approach incorporates the subtractive clustering method into K-SVD to retain the most important atom candidates. At the same time, the redundant atoms are removed to produce a well-trained dictionary. As for a given dataset and approximation error bound, the proposed approach can deduce the optimized size of dictionary, which is greatly compressed as compared with the one needed in the K-SVD algorithm.

关键词： Dictionaries Matching pursuit algorithms Clustering algorithms Pursuit algorithms Signal representations Signal processing image restoration Signal restoration Guidelines Clustering methods

来源：评论

学校读者我要写书评

暂无评论

Adaptive mutation particle filter based on diversity guidance

Adaptive mutation particle filter based on diversity guidanc...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Jin-Xia Yu Yong-Li Tang Wen-Jing Liu College of Computer Science and Technology Henan Polytechnic University Jiaozuo China Jiangsu Provincial Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China Department of Computer Science and Technology Tsinghua University Beijing China

Aimed at the deficiency of the resampling algorithm in PF, diversity measures ESS (effective sample size) and PDF (population diversity factor) are evaluated respectively. Combined with the estimation result, diversity measures PDF is used for adaptively tuning the resampling threshold. By integrating the operation of particle mutation after resampling into PF and using the above mechanism of diversity guidance, the AMPF algorithm (Adaptive Mutation PF) is presented so as to assure the diversity of particle sets. With the simulation program using matlab 7.0 to track a single target motion from a fixed visual observation points, the performance of diversity measures and AMPF are evaluated and the validity of the proposed method is verified.

关键词： Particle measurements Atmospheric measurements Particle filters Algorithm design and analysis Mathematical model Tuning Estimation

来源：评论

学校读者我要写书评

暂无评论

Comparison of regressors on 3D visual discomfort prediction

Comparison of regressors on 3D visual discomfort prediction

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Runfeng Huang Jun Zhou Xiao Gu Ya Zhang Alan C. Bovik Shanghai Key Laboratory of Digital Media Processing and Transrnissions Shanghai China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Laboratory for Image and Video Engineering University of Texas at Austin Austin USA

ISBN: (纸本)9781467390453

Most stereoscopic 3D (S3D) image visual discomfort predictors use the Support Vector Regressor (SVR) as the regression model. However, there are other good regression models such as the Random Forests (RF) and Gradient Boost Regression Tree (GBRT). Here we study the efficacy of these regression models for S3D image visual discomfort prediction. We deployed several regression models to predict the visual discomfort scores on S3D images using three kinds of features extracted from the images in the IEEE-SA and EPFL S3D image databases. So the prediction performance was evaluated to compare the performance of the different regression models. We also studied the issue of over-fitting which can affect model performance. The comparison results show that it is feasible and reliable to apply Random Forests or GBRT for S3D visual discomfort prediction with better performance than SVR.

关键词： Visualization Feature extraction Kernel Predictive models Vegetation Radio frequency Analytical models

来源：评论

学校读者我要写书评

暂无评论

Extraction method of microscopic moving particle basing on multimodal background model

引用

ICIC Express Letters, Part B: Applications 2015年第12期6卷 3153-3158页

作者： Zhang, Yanbin Yang, Zhangzhen Zhang, Hui Qin, Lei Image Processing and Image Communication Lab Jiangsu Key Lab of Wireless Communications Nanjing University of Posts and Telecommunications No. 66 New Mofan Road Nanjing210003 China Jiangsu Key Lab of Wireless Communications Nanjing University of Posts and Telecommunications No. 66 New Mofan Road Nanjing210003 China

Target extraction is a key technology for image measurement of moving particles distributed in fluidic system. In this paper, we propose a novel moving particle extraction method based on multimodal characteristic of the image. For the proposed particle extraction method, we firstly analyze the origin of multimodal characteristic of image background in the microscopic observation system, and then we design multimodal background model for particle extraction. For improving the performance of the model, we exploit the moving principle in the micro channel, and discuss the setting of learning rate. The experimental results demonstrate that the proposed methods achieve good performance compared with several traditional methods. © 2015, ICIC Express Letters Office. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Angel Girl of Visually Impaired Artists: Painting Navigation System for Blind or Visually Impaired Painters

Angel Girl of Visually Impaired Artists: Painting Navigation...

引用

IEEE Visual communications and image processing (VCIP)

作者： Hang Liu Menghan Hu Guangtao Zhai Huijing Huang Wa Zhang Qingli Li Yinghong Tian Yanling Shi Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University China Institute of Image Communication and Information Processing Shanghai Jiao Tong University China

For those who love painting but unfortunately have visual impairments, holding a paintbrush to create a work is really a difficult task. For the purpose of solving this problem, a painting navigation system for visually impaired painters is introduced through the live demonstration. When painting, the developed system can endow visually impaired persons with the ability to perceive the surrounding environment, thus helping them realize their dream of painting. To achieve this goal, we designed four main modules viz., QR code based drawing board positioning module, brush real-time positioning module, color recognition module and human-computer interaction module, and integrated them into the system. In the validation experiments, the blindfolded users can successfully create a painting with the help of the developed navigation system. Moreover, the users told us that this system provided them with good experience. In a way, this painting navigation system can be seen as "angel's eyes" of visually impaired painters. The demo video of the proposed painting navigation system is available at: https://***/10.6084/***.9760004.v1.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multilevel DCT-based zerotree image coding

Multilevel DCT-based zerotree image coding

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Kankan Zheng Liang Zhang Rong Xie Institute of Image Communication and Network Engineering & Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiao Tong University Shanghai China

image and video coding is fundamental to data storage and transmission. JPEG 2000 is the latest international image coding standard which exploits wavelet transform for image compression. Zerotree coding structure is an efficient algorithm for coding of wavelet transform coefficients. However, implementation complexity of wavelet transform and long coding process of zerotree structure may limit the application in some cases. In this paper, an idea of multilevel DCT-based zerotree image coding is proposed, in which Wavelet Transform (WT) is replaced by Discrete Cosine Transform (DCT) and DCT coefficients are regrouped into subbands of different frequencies. Furthermore, a new zerotree coding structure is proposed to reduce the complexity of zerotree coding process. A conventional zerotree with a parent-child relation of 2×2 offspring is expanded to the one of 4×4 offspring. Coefficients reorder and inverse DCT are needed when DCT transform size is not a power of 4. This expansion makes each parent node of zerotree coding structure have more child nodes and, therefore, reduce the complexity of encoding process. Simulation results of images with different spatial resolutions are presented to show the advantage of the proposed algorithm. The proposed multi-level DCT-based zerotree image coding algorithm performs similar coding performance as the SPIHT method. The zerotree coding structure with a parent-child relation of 4×4 pixels can significantly reduce the complexity of high-bitrate coding process without sacrificing image subjective quality.

关键词： Discrete cosine transforms image coding Encoding Spatial resolution Wavelet transforms Bit rate

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：