检索结果-内蒙古大学图书馆

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Xuelong, Hu Yan, Tang Jun, Cai School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China

ISBN: (纸本)9781424423118

Head-related Transfer Functions (HRTFs) refer to the spectral filtering from sound sources to listeners' eardrums or ear canals. As an effective model structure, the degree of the IIR filter approximation of the HRTFs, whose design and implementation is a specific spectrum function approximation process, is much lower than that of the FIR. Based on the assessment of HRTFs different importance for sound sources recognition in different spectrum bands, and associated with some perspectives of psychoacoustics in spatial hearing, adaptive and revalued coding genetic algorithm (GA) is applied to the approximation of the HRTFs zero-pole model. The results show that, on an average, the performance of adaptive GA is better than that of the traditional GA. ©2008 IEEE.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

Appearance model based moving object matching across disjoint camera views

引用

2nd International Conference on Opto-Electronics Engineering and Materials Research, OEMR 2013

作者： Yu, Kong Shuai Hu, Dong Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology The key lab of image processing and image communications of Jiangsu Province Nanjing University of Posts and Telecom Nanjing 210003 China

ISBN: (纸本)9783037857731

A new object tracking scheme for multi-camera surveillance with non-overlapping views is proposed in this paper. Brightness transfer function (BTF) is used to establish relative appearance correspondence between different views. Mixtures of probabilistic principal component analysis (MPPCA) is incooperated to learn the subspace of brightness transfer function with the concern to deal with multiple different brightness areas in a scene. The incremental major color spectrum histogram (IMCSH) is used as similarity measure for reliable matching. Experimental results with real world videos show the effectiveness of the proposed algorithm. © (2013) Trans Tech Publications, Switzerland.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

A Novel Method to Get Super-Resolution images from Low-Resolution Compressed Video

引用

The Journal of China Universities of Posts and Telecommunications 2005年第2期12卷 50-54页

作者： ZHOU Liang ZHU Xiu-chang Information Industry Ministry and Jiangsu Province Key Lab of Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing 210003 P. R. China

In order to resolve the problems of discontented restoration effect and confined applying scope which exist in the current compressed video restoration algorithms, a novel method to get super-resolution images from low-resolution compressed video is proposed in this paper. At first, a uniform model is presented and the restoration problem in the Bayesian framework is formulated under the MAP criterion, then the focus is put on the hybrid motion-compensation and transform coding schemes, at last the methods of getting the parameters are provided. The results of the simulation clearly demonstrate that our method not only has the properties of finer vision effect and wider applying scope, but also performs better than those of current classical algorithms in the aspects of Peak Signal Noise Ratio （PSNR） under the basis of the same condition.

关键词： super-resolutlon compressed video restoration

来源：评论

学校读者我要写书评

暂无评论

Mixed image de-noising method of Bayesian estimation and wavelet based on alpha-stable distribution

Mixed image de-noising method of Bayesian estimation and wav...

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Zhijian, Wang Xuelong, Hu Cheng, Li Liping, Wang School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Yangzhou Jiangsu 225001 China

ISBN: (纸本)9781424423118

This paper introduces a new kind of recovery method which is the combination of Bayesian estimation and wavelet threshold. Wavelet coefficients of signals show strong characteristics of the non-Gauss statistics, its probability density function can be modeled by alpha-stable priori distribution. This paper uses Bayesian estimation to obtain the low frequency coefficients, and deals with high frequency coefficients with the wavelet soft threshold, then restore signal by wavelet inverse transform. Bayesian estimation well retains the marginal information of signals, but the signal is still not very smooth recovery and wavelet soft threshold can maintain smooth characteristic. The mixed noise elimination methods of Bayesian estimation and wavelet enhance the peak SNR much greater than wavelet threshold, which has better recovery effect. ©2008 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Expression Recognition Based on Attention Mechanism and Length Feature of Facial Landmark 13

Expression Recognition Based on Attention Mechanism and Leng...

引用

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

作者： Yang, Qian Liu, Feng Zhao, Zhenglai Nanjing University of Posts and Telecommunications Nanjing China Nanjing University of Posts and Telecommunications Jiangsu Key Lab of Image Processing Image Communications Nanjing China

ISBN: (纸本)9781665407854

In view of the fact that the proportion of face in the whole image is small and the face posture is skew, which leads to the low accuracy of facial expression recognition, this paper proposes a two-branch neural network based on attention mechanism and length feature of facial landmark. The first branch is based on the modified VGG19 and the integration of the convolutional block attention module (CBAM), which focuses on the extraction of important features of expression. The second branch extracts 68 feature points from the face image, and calculates the Euler distance between these feature points to acquire the length information of 2278 dimensions, and is finally normalized and fed into the full connection layer. The network composed of the first branch and the second branch is trained by joint fine-tuning, where L2 regularization is added to prevent overfitting. The proposed method is tested and verified on Jaffe, CK + and FER +, and the highest accuracy is 93.48%,96.12% and 84.73% respectively. The performance of the proposed method is more advance than many existing algorithms, which shows that the proposed model has good accuracy and robustness. © 2021 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Dual-Domain Calibration and Distance-Driven Correlation Filter:A Probabilistic Perspective for UAV Tracking

引用

Computers, Materials & Continua 2023年第12期77卷 3741-3764页

作者： Taiyu Yan Yuxin Cao Guoxia Xu Xiaoran Zhao Hu Zhu Lizhen Deng Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjingChina School of Computer Science Qufu Normal UniversityQufuChina National Engineering Research Center of Communication and Network Technology Nanjing University of Posts and TelecommunicationsNanjingChina

Unmanned Aerial Vehicle(UAV)tracking has been possible because of the growth of intelligent information technology in smart cities,making it simple to gather data at any time by dynamically monitoring events,people,the environment,and other aspects in the *** traditional filter creates a model to address the boundary effect and time filter degradation issues in UAV tracking *** these methods ignore the loss of data integrity terms since they are overly dependent on numerous explicit previous regularization *** light of the aforementioned issues,this work suggests a dual-domain Jensen-Shannon divergence correlation filter(DJSCF)model address the probability-based distance measuring issue in the event of filter *** two-domain weighting matrix and JS divergence constraint are combined to lessen the impact of sample imbalance and *** new tracking models that are based on the perspectives of the actual probability filter distribution and observation probability filter distribution are proposed to translate the statistical distance in the online tracking model into response *** model is roughly transformed into a linear equality constraint issue in the iterative solution,which is then solved by the alternate direction multiplier method(ADMM).The usefulness and superiority of the suggested strategy have been shown by a vast number of experimental findings.

关键词： Dual-domain weighting distance measure correlation filter ADMM

来源：评论

学校读者我要写书评

暂无评论

Approaches to image retrieval using fuzzy set theory

Approaches to image retrieval using fuzzy set theory

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Li, Yang Xuelong, Hu Jun, Pan School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Jiangsu Prov. Key Lab. for Computer Information Processing Technology Suzhou University Suzhou Jiangsu 215006 China

ISBN: (纸本)9781424423118

This paper mainly presents two approaches for image retrieval. There is some faintness in color locating in quantification boundary when image color is quantized. The membership function in fuzzy set theory can describe the fuzzy transition preferably. In this paper, the membership function in HSI color space is adopted to solve the problem above. At the same time, spatial information is integrated with color feature to describe the image content more truly. Due to the importance of texture feature, gray concurrence matrix is extracted. In the second part of this paper, retrieval scheme combining four image feature descriptors is presented, and then follows Fuzzy Hamming Distance (FHD) which is used as a fuzzy similarity measure. We have performed an experiment on a 1000 images database and our results show higher retrieval accuracy. © 2008 IEEE.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Robust blind watermark algorithm of color image based on neural network

Robust blind watermark algorithm of color image based on neu...

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Xuelong, Hu Xu, Lian Lin, Chen Yongai, Zheng School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Shanghai University of Electrical Power Shanghai 200090 China

ISBN: (纸本)9781424423118

A new algorithm of color image blind watermarking based on BP neural network and wavelet significant tree is proposed. In YCbCr, the luminance component is decomposed with wavelet, and the wavelet significant tree can be found. Then the correlativity among nodes of wavelet significant tree is described by the nonlinear relationship responded by the trained BP neural network. Based on the relationship, the watermark is embedded into wavelet significant trees. Finally, the embedded watermark can be extracted without original image. The experimental results show that the embedded watermark can be extracted preferably in some common attacks, and this algorithm has better transparency and stronger robustness with some comparisons to other algorithms. © 2008 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Vehicle Type Classification via Adaptive Feature Clustering for Traffic Surveillance Video

Vehicle Type Classification via Adaptive Feature Clustering ...

引用

International Conference on Wireless communications and Signal processing

作者： Shu Wang Feng Liu Zongliang Gan Ziguan Cui Jiangsu Province Key Lab on Image Processing & Image Communications Nanjing University of Posts and Telecommunications

ISBN: (纸本)9781509028610

Vehicle type classification has become an important part of intelligent traffic. However traditional methods can not deal with the varying situations in the reality. In this paper, a novel method is proposed to handle this task in the real road traffic surveillance video. In order to distinguish different vehicles, we categorize vehicles into three types: compact cars, mid-size cars, and heavy-duty vehicles. For a certain video, our method has four steps. First, a deep convolutional neural network is used to detect vehicles in the candidate region and a data set would be generated. Second, the main features of vehicles can be extracted using a fully-connected network. Also, for the sake of higher accuracy, weak labels given by pre-trained extreme learning machine (ELM) are fused into the final features, adding prior information proportionally. Third, K-means is implemented to learn three vehicle-type cluster centers adaptively. Finally, vehicle type will be recognized according to the closest distance principal. Experimental results show that the recognition rate outperforms other traditional methods, verifying the feasibility and effectiveness of the proposed method.

关键词： Vehicle type classification Adaptive clustering Feature learning Deep learning Extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

Video object matching based on sift algorithm

Video object matching based on sift algorithm

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Xuelong, Hu Yingcheng, Tang Zhenghua, Zhang School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Prov. Key Lab for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Jiangsu Prov. Key Lab. for Computer Information Processing Technology Suzhou University Suzhou Jiangsu 215006 China

ISBN: (纸本)9781424423118

SIFT (Scale Invariant Feature Transform) is used to solve visual tracking problem, where the appearances of the tracked object and scene background change during tracking. The implementation of this algorithm has five major stages: scale-space extrema detection;keypoint localization;orientation assignment;keypoint descriptor;keypoint matching. From the beginning frame, object is selected as the template, its SIFT features are computed. Then in the following frames, the SIFT features are computed. Euclidean distance between the object's SIFT features and the frames' SIFT features can be used to compute the accurate position of the matched object. The experimental results on real video sequences demonstrate the effectiveness of this approach and show this algorithm is of higher robustness and real-time performance. It can solve the matching problem with translation, rotation and affine distortion between images. It plays an important role in video object tracking and video object retrieval. © 2008 IEEE.

关键词： Tracking (position)

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：