发布求助
文献互助 智能选刊 最新文献

2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)最新文献

筛选
英文 中文
Non-linear metric learning with multiple features for person re-identification 多特征非线性度量学习用于人的再识别
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889265
Jianguo Jiang, Hao Liu, Meibin Qi
{"title":"Non-linear metric learning with multiple features for person re-identification","authors":"Jianguo Jiang, Hao Liu, Meibin Qi","doi":"10.1109/ChinaSIP.2014.6889265","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889265","url":null,"abstract":"In video surveillance, person re-identification across disjoint camera views has important applications. Many factors make it difficult to tackle such as the varieties of varying lighting conditions, viewing angles, body gestures, background clutter and occlusion. To address the problem, several methods exploited combination or the fusion of multiple features, or built models. However, in these methods, contributions of different features were determined too subjectively or the use of differences between different samples is inadequate in building model. For these problems, a novel method is proposed by us, which combines multiple kernel learning (MKL) and distance metric learning (DML) to fully employ the information of several different features in the process of re-identification and build the most descriptive and robust model. Furthermore, the distance metric learning method is improved according to the practical and the related parameters of kernels can be self-selected by our method. Experiments are conducted on benchmarking dataset, and the experimental results suggest that our approach achieves encouraging performance.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"110 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129075865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Speech enhancement and features compensation algorithms for continuous speech recognition 连续语音识别的语音增强和特征补偿算法
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889195
Christian Arcos, M. Grivet, A. Alcaim
{"title":"Speech enhancement and features compensation algorithms for continuous speech recognition","authors":"Christian Arcos, M. Grivet, A. Alcaim","doi":"10.1109/ChinaSIP.2014.6889195","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889195","url":null,"abstract":"The degradation of the speech signal due to adverse conditions generates low accuracy rates in speech recognition systems. The authors propose mixing two methods: pre-extraction of features for speech enhancement and post-extraction of features for features compensation. According to their main focus, they are fundamentally oriented to minimize the misfit caused by noise insertion in the speech signal. These methods will be applied before and after the extraction of features, respectively, therefore allowing the best possible estimation of the clear signal from its degraded version.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"1989 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125491422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Research on visual object tracking by dynamic and static metric 基于动态和静态度量的视觉目标跟踪研究
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889303
Lichao Zhang, Duyan Bi, Yufei Zha, Dong Nan, Li Zhou
{"title":"Research on visual object tracking by dynamic and static metric","authors":"Lichao Zhang, Duyan Bi, Yufei Zha, Dong Nan, Li Zhou","doi":"10.1109/ChinaSIP.2014.6889303","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889303","url":null,"abstract":"Color feature is used in object model of classical kernel tracking algorithm, but the static feature is hard to adapt to the changing object with abrupt movement and rotation in the background whose color distribution is similar to object's. Considering that local dynamic feature extracted by classical optical flow can describe the object's dynamic characteristics, a new tracking method is proposed based on dynamic metric. In order to obtain accurate denotation, the variance matrix is used to estimate the error ellipse which is adaptive to the object's scale and rotation. The experiments show that the proposed algorithm can achieve better tracking results compared with other related algorithms when the target moves abruptly and rotates under the condition of complicated background.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123025485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Video quality assessment via supervised topic model 基于监督主题模型的视频质量评估
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889321
Qun Guo, Xiaoqiang Lu, Yuan Yuan
{"title":"Video quality assessment via supervised topic model","authors":"Qun Guo, Xiaoqiang Lu, Yuan Yuan","doi":"10.1109/ChinaSIP.2014.6889321","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889321","url":null,"abstract":"Video quality assessment (VQA) plays a very important role in many video processing and communication systems. Since video signals are ultimately delivered to human observers, an accurate objective video quality metric should agree well with judgment of human visual system (HVS). In this paper, a novel full-reference VQA scheme is developed to measure the perceived video quality in both local and global aspects. First, to account for the crucial impact of motion on perception, effective quality features are extracted from the local spatio-temporal volumes which are generated around the motion trajectories in the video. Second, a statistical model is utilized to discover the latent relation between local quality and global perceived quality. Experimental results on LIVE database demonstrate promising performance of the proposed metric in comparison with state-of-the-art VQA metrics.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132843895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
A relaxation method to articulated trajectory reconstruction from monocular image sequence 单眼图像序列关节轨迹重建的松弛方法
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889270
Bo Li, Yuchao Dai, Mingyi He, A. Hengel
{"title":"A relaxation method to articulated trajectory reconstruction from monocular image sequence","authors":"Bo Li, Yuchao Dai, Mingyi He, A. Hengel","doi":"10.1109/ChinaSIP.2014.6889270","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889270","url":null,"abstract":"In this paper, we present a novel method for articulated trajectory reconstruction from a monocular image sequence. We propose a relaxation-based objective function, which utilises both smoothness and geometric constraints, posing articulated trajectory reconstruction as a non-linear optimization problem. The main advantage of this approach is that it remains the re-constructive power of the original algorithm, while improving its robustness to the inevitable noise in the data. Furthermore, we present an effective approach to estimating the parameters of our objective function. Experimental results on the CMU motion capture dataset show that our proposed algorithm is effective.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133070129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Nonlinear squeezing transform for weak signal detection 用于微弱信号检测的非线性压缩变换
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889338
Shibin Wang, Xuefeng Chen, Yan Wang, Baoqing Ding
{"title":"Nonlinear squeezing transform for weak signal detection","authors":"Shibin Wang, Xuefeng Chen, Yan Wang, Baoqing Ding","doi":"10.1109/ChinaSIP.2014.6889338","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889338","url":null,"abstract":"We introduce a novel algorithm, called nonlinear squeezing transform, to characterize the time-frequency pattern of nonstationary multi-component signals, especially for weak component detection. As a generally known, conventional time-frequency analysis (TFA) methods can characterize the time-frequency pattern of nonstationary signal. However, it is difficult to detect the weak component hidden in complex signals because the time-frequency information is influenced by the amplitude of the signal. Inspired by the calculation procedure of instantaneous frequency in the synchro-squeezing transform, nonlinear squeezing transform is presented, which is only relevant to the phase but is independent of the signal amplitude. The experiment on real signal shows that the method can effectively detect the weak component in complex signals, and the comparison study with some TFA methods also shows the advantages in weak signal detection.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133161251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Spectral efficiency of extended networks with randomly distributed transmitters and receivers 随机分布发射机和接收机的扩展网络的频谱效率
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889329
L. Cottatellucci
{"title":"Spectral efficiency of extended networks with randomly distributed transmitters and receivers","authors":"L. Cottatellucci","doi":"10.1109/ChinaSIP.2014.6889329","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889329","url":null,"abstract":"We consider an extended wireless network with transmit and receive nodes homogeneously distributed in ℝ2. The channel state information (CSI) is known at the centralized processing unit at the receiver side but not at the transmitters which transmit at equal power. By extending the definition of Euclidean random matrices (ERM) and their spectral analysis to two independent sets of points, we determine an approximated expression of the average maximum achievable rate per unit area of the system.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130223834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Diversity gain for MIMO-OTH radar target detection under product of complex Gaussian reflections 复高斯反射积下MIMO-OTH雷达目标探测的分集增益
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889332
Qi Ding, Qian He, Zishu He, Rick S. Blum
{"title":"Diversity gain for MIMO-OTH radar target detection under product of complex Gaussian reflections","authors":"Qi Ding, Qian He, Zishu He, Rick S. Blum","doi":"10.1109/ChinaSIP.2014.6889332","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889332","url":null,"abstract":"Consider a multiple-input multiple-output skywave over-the-horizon (MIMO-OTH) radar system withM transmit and N receive antennas employing the conventional optimal detector for a single complex Gaussian target. The signal from the mth transmit antenna reaches the target after being reflected by the ionosphere via Qm ray paths. Each of these multipath signals bounce off the target and reach the nth receiver after being reflected by the ionosphere again via Hmn ray paths. Thus the transmitted signals are reflected once off the target and twice by the ionosphere before arriving at the receive end, and any of these three reflections can be either categorized as being complex Gaussian or deterministic. If either one or two of the reflections are modeled as complex Gaussian while the others are modeled as deterministic, it is shown that the largest possible diversity gain is upper bounded by equation.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131850347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Efficient parameter estimation method for high dynaimc DSSS signal 高动态DSSS信号的有效参数估计方法
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889313
Shuang Wu, W. Cui, Lin Li, Jiangang Hou, J. Tian
{"title":"Efficient parameter estimation method for high dynaimc DSSS signal","authors":"Shuang Wu, W. Cui, Lin Li, Jiangang Hou, J. Tian","doi":"10.1109/ChinaSIP.2014.6889313","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889313","url":null,"abstract":"This paper proposes an efficient parameter estimation method (DIKT) based on Keystone transform (KT), dimension reduction and inverse Keystone transform (IKT) to counteract the high dynamic effects over a long coherent integration time. In this method, first-order KT is first applied to blindly correct the linear code phase drift. Then, dimension reduction is carried out meanwhile a new coordinate transformation, named IKT, is derived. After that, IKT is employed to remove the residual quadratic code phase drift, followed by Doppler rate estimation. After compensating the Doppler rate term, Doppler shift and initial range are finally estimated simultaneously. The proposed method can overcome high dynamic effects without prior-knowledge of the target. Furthermore, it has low computational complexity, making it easy for the hardware implement and real-time processing. Simulation results verify the effectiveness of the proposed method.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130277721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An LPI design for secure burst communication systems 安全突发通信系统的LPI设计
2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) Pub Date : 2014-07-09 DOI: 10.1109/ChinaSIP.2014.6889320
Yuxiao Yang, Jianjiang Zhou, Fei Wang, C. Shi
{"title":"An LPI design for secure burst communication systems","authors":"Yuxiao Yang, Jianjiang Zhou, Fei Wang, C. Shi","doi":"10.1109/ChinaSIP.2014.6889320","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2014.6889320","url":null,"abstract":"An LPI burst communication model based on conditional maximum entropy is presented in this paper. In this model, the conditional entropy of transmitting moments is the largest, and the prior data are used as the sample space, while Lagrange multipliers are selected as optimization variables. Hybrid Chaotic Particle Swarm Optimization (HCPSO) that is used in the model takes the dual programming of the conditional maximum entropy as objective function, and the conditional maximum entropy model is ultimately determined through this optimization algorithm. Compared with the usual method of fixed threshold, the simulation results show that the conditional maximum entropy method not only has longer effective communication time, but also can effectively increase the uncertainty of transmitting moments. The more the uncertainty of transmitting moments, the better the low probability of intercept performance is. So the burst communication has better performance of low probability of intercept using conditional maximum entropy model.","PeriodicalId":248977,"journal":{"name":"2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130591828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信