检索结果-内蒙古大学图书馆

5th Euro-China Conference on Intelligent Data Analysis and Applications, ECC 2018

作者： Li, Na Wu, Lingfeng Li, Daxiang Center for Image and Information Processing Xi’an University of Posts and Telecommunications Xi’an710121 China Key Laboratory of Electronic Information Application Technology for Scene Investigation Ministry of Public Security Xi’an710121 China International Joint Research Center for Wireless Communication and Information Processing Xi’an710121 China

ISBN: (纸本)9783030037659

KCF (Kernelized Correlation Filter) is a classical tracking algorithm based on correlation filter, which has good performance in short-term tracking. But when the object is partially or fully occluded, or disappeared in the view, KCF doesn’t work well. In this paper, a long-term tracking algorithm based on KCF is proposed. HOG (Histogram of Oriented Gradient) and lab three-channel color information are employed to represent the object, and a re-detection module is added into the KCF tracking procedure. The peak ratio is introduced to control the start of the re-detection module, and a correlation filter model based on SURF feature points is re-learned to continuously track the occluded object. Experimental results on OTB dataset show that our algorithm has higher tracking accuracy than other five trackers, and is suitable for long-term tracking. © Springer Nature Switzerland AG 2019.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

image interpolation based on decomposition

Image interpolation based on decomposition

引用

IEEE International Symposium on Intelligent Signal processing and communication Systems (ISPACS)

作者： Nana Guo Li Song Xiaokang Yang Wenjun Zhang Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiaotong University Shanghai China

This paper proposes a new approach for interpolating natural images. Unlike other conventional interpolation methods, we exploit the characteristics of an image and decompose it into a texture part and a non-texture (cartoon) part. In the non-texture part, we interpolate it with bicubic interpolation which performs well for smooth areas. We deal the texture part with peak transform based interpolation which resets the image pixels to capture the characters of the texture through peak transform. The experiment results demonstrate our new interpolation method has higher PSNR and better subjective quality of the interpolated image, especially in the texture part.

关键词： image resolution Interpolation image edge detection Boats Hair

来源：评论

学校读者我要写书评

暂无评论

Low complexity reconfigurable architecture for the 5/3 and 9/7 discrete wavelet transform

引用

Journal of Systems Engineering and Electronics 2006年第2期17卷 303-308页

作者： Xiong Cheng yi Tian Jinwen Liu Jian Coll. of Electronic Information Engineering South Center Univ. for Nationalities Wuhan 430074 P.R. China Inst. of Pattern Recognition & Artificial Intelligence Key Lab. of Education Ministry for Image Processing and Intelligent Control Huazhong Univ. of Science & Technology Wuhan 430074 P.R. China

Efficient reconfigurable VLSI architecture for 1-D 5/3 and 9/7 wavelet transforms adopted in JPEG2000 proposal, based on lifting scheme is proposed. The embedded decimation technique based on fold and time multiplexing, as well as embedded boundary data extension technique, is adopted to optimize the design of the architecture. These reduce significantly the required numbers of the multipliers, adders and registers, as well as the amount of accessing external memory, and lead to decrease efficiently the hardware cost and power consumption of the design. The architecture is designed to generate an output per clock cycle, and the detailed component and the approximation of the input signal are available alternately. Experimental simulation and comparison results are presented, which demonstrate that the proposed architecture has lower hardware complexity, thus it is adapted for embedded applications. The presented architecture is simple, regular and scalable, and well suited for VLSI implementation.

关键词： VLSI discrete wavelet transform lifting scheme embedded decimation reeonfigurable.

来源：评论

学校读者我要写书评

暂无评论

Learning super resolution with global and local constraints

Learning super resolution with global and local constraints

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Kai Guo Xiaokang Yang Rui Zhang Songyu Yu Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiaotong University Shanghai China

In learning based single image super-resolution (SR) approach, the super-resolved image are usually found or combined from training database through patch matching. But because the representation ability of small patch is limited, it is difficult to guarantee that the super-resolved image is best under global view. To tackle this problem, we propose a statistical learning method for SR with both global and local constraints. Firstly, we use maximum a posteriori (MAP) estimation with learned image priors by fields of experts (FoE) model, and regularize SR globally guided by the image priors. Secondly, for each overlapped patch, the higher-order Markov random fields (MRFs) is used to model its local relationship with corresponding high-resolution candidates, then belief propagation is used to find high-resolution image. Compared with traditional patch based learning method without global constraint, our method could not only preserve the global image structure, but also restore the local details well. Experiments verify the idea of our global and local constraint SR method.

关键词： Strontium image resolution image databases Markov random fields Belief propagation image restoration Signal resolution Spatial databases image communication Information processing

来源：评论

学校读者我要写书评

暂无评论

An improving MFCC features extraction based on FastICA algorithm plus RASTA filtering

引用

Journal of Computers 2011年第7期6卷 1477-1484页

作者： Zhao, Huan Hu, Lian Peng, Xiujuan Wang, Gangjin Yu, Fei Xu, Cheng School of Information Science and Engineering Hunan University Changsha China Jiangsu Provincial Key Lab of Image Processing and Image Communications Nanjing University of Posts and Telecommunications Nanjing China

FastICA is a kind of independent component analysis (ICA), which is robust and high performance algorithm, it can strongly remove signal correlation and ensure each signal to be independence. Through perceptual test, improving that RASTA is an idea which can denoise effectively. First, we remove signal correlation through FastICA algorithm, then we use RASTA filter to filtering the ceptral coefficients. Finally, we reduce dimension of the cepstral coefficients by the variances of cepstral coefficients in different dimension and obtain our features. By the HTK3.3, the speech feature extraction which was presented in this paper show the better robust in recognition experiment. © 2011 ACADEMY PUBLISHER.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

image super-resolution based on a novel edge sharpness prior

Image super-resolution based on a novel edge sharpness prior

引用

International Conference on Pattern Recognition

作者： Qing Yan Yi Xu Xiaokang Yang Kai Chen The Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmition Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9781467322164

Edges are of significant importance in visual resolution perception. In this paper, we propose a novel image super-resolution method by enhancing the edges in the low resolution image. We first define a new edge sharpness feature: gradient profile sharpness (GPS), which considers both the absolute magnitude and the spatial scattering of edge gradient profile. Then we learn the relationship between GPSs in high resolution images and low resolution images, and we formulate a linear GPS transform to provide gradient prior for image reconstruction. Our GPS can represent edge sharpness perceptually well. And our super-resolution method can output harmonious and faithful images with better reconstruction quality.

关键词： image edge detection Global Positioning System Spatial resolution Transforms Scattering image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A new no-reference stereoscopic image quality assessment based on ocular dominance theory and degree of parallax

A new no-reference stereoscopic image quality assessment bas...

引用

International Conference on Pattern Recognition

作者： Ke Gu Guangtao Zhai Xiaokang Yang Wenjun Zhang Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiaotong University Shanghai China

In recent years, while stereoscopic images were becoming widely applied and the corresponding technologies were substantially developed, very few stereoscopic image quality assessment metrics were proposed, especially under the condition that there is no reference image available. This paper proposes a new no-reference stereoscopic image quality assessment algorithm based on the ocular dominance theory and degree of parallax. All of our tests using the Toyama database draw two valuable conclusions. First, the performances of stereoscopic image quality assessment methods are significantly affected by difference of image qualities between the left and right images. Second, to offset the discriminations of different degrees of parallax caused by various 3D image contents is required indeed. Experiments and comparative studies are provided to confirm the effectiveness of our proposed new stereoscopic image quality metric.

关键词： Stereo image processing image quality Measurement Indexes Transform coding image coding Visualization

来源：评论

学校读者我要写书评

暂无评论

Blurred image Registration by Combined Invariant of Legendre Moment and Harris-Laplace Detector

Blurred Image Registration by Combined Invariant of Legendre...

引用

Pacific-Rim Symposium on image and Video Technology (PSIVT)

作者： Xiubin Dai Hui Zhang Huazhong Shu Limin Luo Tianliang Liu School of Computer Science and Engineering South-East University Nanjing China Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China

Since real imaging systems are imperfect, the acquired images are always distorted by blur, scale and rotation transformation. Then the registration of these degraded images has become an important task in many applications in which the moment invariants are usually efficient tools. However, the existing methods can only deal with the slightly distorted images and have the problems of information redundancy. Besides, some methods have overlapping constraint that the images to be aligned should be fully included into the reference images. In this paper, we proposed a novel method in which a new set of combined invariants based on Legendre moment holding for blur, rotation and scale degradation simultaneously were constructed as feature descriptors, and scale-invariant Harris-Laplace detector was applied to exact feature points. The experimental results show that our method can work well without overlapping constraint, especially when the distortion is great.

关键词： Detectors image registration Feature extraction Degradation Read only memory Redundancy Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A siamese network tracking algorithm based on hierarchical attention mechanism

A siamese network tracking algorithm based on hierarchical a...

引用

2020 International Symposium on Automation, Information and Computing, ISAIC 2020

作者： Zhang, Hu Hu, Dong Qiu, Yingcan Jiangsu Province’s Key Lab of Image Procession and Image Communications Nanjing210003 China Education Ministry’s Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing210003 China Education Ministry’s Engineering Research Center of Ubiquitous Network and Heath Service Nanjing210003 China Nanjing University of Posts and Telecommunications Nanjing210003 China

A siamese network tracking algorithm based on hierarchical attention mechanism is proposed in this paper. In order to obtain more robust target tracking results, different layer features are fused effectively. In the process of extracting features, attention mechanism is used to recalibrate the feature map, and AdaBoost algorithm is used to weight the target feature map, which improves the reliability of the response map. Besides, the Inception module is also introduced which not only increases the width of the network and the adaptability of the siamese network to the scale, but also reduces the parameters and improves the speed of network training. Experimental results show that this method can effectively solve the impact of background clutter and improve the accuracy of tracking. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Learning from Noisy labels with Coarse-to-Fine Sample Credibility Modeling 17th

Learning from Noisy Labels with Coarse-to-Fine Sample Cred...

引用

17th European Conference on Computer Vision, ECCV 2022

作者： Zhang, Boshen Li, Yuxi Tu, Yuanpeng Peng, Jinlong Wang, Yabiao Wu, Cunlin Xiao, Yang Zhao, Cairong YouTu Lab Shenzhen China Tongji University Shanghai China Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9783031250620

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via identifying noisy data with a coarse small-loss criterion to mitigate the interference from noisy labels, ignoring the fact that the difficulties of noisy samples are different, thus a rigid and unified data selection pipeline cannot tackle this problem well. In this paper, we first propose a coarse-to-fine robust learning method called CREMA, to handle noisy data in a divide-and-conquer manner. In coarse-level, clean and noisy sets are firstly separated in terms of credibility in a statistical sense. Since it is practically impossible to categorize all noisy samples correctly, we further process them in a fine-grained manner via modeling the credibility of each sample. Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set. Meanwhile, for samples categorized into the noisy set, a selective label update strategy is proposed to correct noisy labels while mitigating the problem of correction error. Extensive experiments are conducted on benchmarks of different modality, including image classification (CIFAR, Clothing1M etc.) and text recognition (IMDB), with either synthetic or natural semantic noises, demonstrating the superiority and generality of CREMA. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

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：