2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)最新文献

筛选
英文 中文
Enhanced TFRC congestion control mechanism based on refined network states division 基于精细网络状态划分的增强TFRC拥塞控制机制
Zengkuan Song, Yongfei Zhang, Mingliang Zhou
{"title":"Enhanced TFRC congestion control mechanism based on refined network states division","authors":"Zengkuan Song, Yongfei Zhang, Mingliang Zhou","doi":"10.1109/ChinaSIP.2015.7230542","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230542","url":null,"abstract":"Video-streaming traffic has been the majority traffic over the Internet in recent years and TCP-Friendly Rate Control (TFRC) is the most promising protocol to load it. However, TFRC is unable to detect network fluctuation timely in a short time scale. This weakness results in decrease of Quality of Service (QoS) and TCP friendliness. In this paper, we propose an enhanced TFRC Control algorithm based on Network State division called NSTC. In short time scale, NSTC introduces variation trend of current available bandwidth to classify network into different states and identify whether TFRC needs to control its sending rate. The simulation experiment shows that compared with TFRC, NSTC sharply decreases packet loss and comprehensively improves QoS and friendliness.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127984520","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: 6
Joint power control and signature design for time-reversal uplinks 时间反转上行链路的联合功率控制和签名设计
Qinyi Xu, Yan Chen, K. Liu
{"title":"Joint power control and signature design for time-reversal uplinks","authors":"Qinyi Xu, Yan Chen, K. Liu","doi":"10.1109/ChinaSIP.2015.7230553","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230553","url":null,"abstract":"In the time reversal division multiple access (TRDMA) system, the signal-to-noise ratio (SNR) is boosted and the inter-user interference (IUI) is suppressed due to the temporal and spatial focusing effects of the time-reversal (TR) technique. However, since the focusing effects highly depend on the location-specific multipath profile, there exists a strong-weak focusing effect in the TRDMA uplink system where different users at different locations enjoy different level of focusing effects. In this paper, we formulate the strong-weak focusing effect in the multiuser TRDMA uplink system as a max-min signal-to-interference-noise ratio (SINR) balancing problem by means of joint power control and signature filter design. A novel two-stage adaptive algorithm that can guarantee the convergence is proposed. Numerical results show that our algorithm converges quickly, achieves a high energy-efficiency gain, and provides a performance guarantee to all users.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131229446","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
A new unsupervised convolutional neural network model for Chinese scene text detection 一种新的无监督卷积神经网络中文场景文本检测模型
Xiaohang Ren, Kai Chen, Xiaokang Yang, Yi Zhou, Jianhua He, Jun Sun
{"title":"A new unsupervised convolutional neural network model for Chinese scene text detection","authors":"Xiaohang Ren, Kai Chen, Xiaokang Yang, Yi Zhou, Jianhua He, Jun Sun","doi":"10.1109/ChinaSIP.2015.7230438","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230438","url":null,"abstract":"As one of the most popular deep learning models, convolution neural network (CNN) has achieved huge success in image information extraction. Traditionally CNN is trained by supervised learning method with labeled data and used as a classifier by adding a classification layer in the end. Its capability of extracting image features is largely limited due to the difficulty of setting up a large training dataset. In this paper, we propose a new unsupervised learning CNN model, which uses a so-called convolutional sparse auto-encoder (CSAE) algorithm pre-train the CNN. Instead of using labeled natural images for CNN training, the CSAE algorithm can be used to train the CNN with unlabeled artificial images, which enables easy expansion of training data and unsupervised learning. The CSAE algorithm is especially designed for extracting complex features from specific objects such as Chinese characters. After the features of articficial images are extracted by the CSAE algorithm, the learned parameters are used to initialize the first CNN convolutional layer, and then the CNN model is fine-trained by scene image patches with a linear classifier. The new CNN model is applied to Chinese scene text detection and is evaluated with a multilingual image dataset, which labels Chinese, English and numerals texts separately. More than 10% detection precision gain is observed over two CNN models.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125201441","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: 12
Single image super-resolution based on nonlocal similarity and sparse representation 基于非局部相似度和稀疏表示的单幅图像超分辨率
Qian Li, Zhenbo Lu, Cuirong Sun, Houqiang Li, Weiping Li
{"title":"Single image super-resolution based on nonlocal similarity and sparse representation","authors":"Qian Li, Zhenbo Lu, Cuirong Sun, Houqiang Li, Weiping Li","doi":"10.1109/ChinaSIP.2015.7230382","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230382","url":null,"abstract":"Images with high resolution (HR) are often desired and required in imaging applications. Super-resolution (SR) is a promising but still challenging task to obtain an HR image (or sequence) from the observed low-resolution (LR) image (or sequence). In this paper, we present an SR approach for single image, by combining the image observation model, image nonlocal similarity, and sparse representation of image patches. First, we regularize low rank of matrix that is composed of nonlocal similar patches, to obtain an initial estimate of HR image. Then, each patch of the estimated image is sparsely represented in terms of LR dictionary, and the sparse coding coefficients are used to generate an output HR patch in terms of HR dictionary, resulting in the enhancement of high-frequency components in the HR estimate. The two over-complete dictionaries are jointly learned from example patch pairs in advance. Finally, the refined HR estimate is further constrained by the observation model. Experimental results have shown that the proposed SR method has obvious visual improvement in preserving edges and structures, while achieving comparable overall objective quality to the state-of-the-art methods.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123260118","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
PVO-based reversible data hiding for encrypted images 基于pvo的加密图像可逆数据隐藏
Bo Ou, Xiaolong Li, Weiming Zhang
{"title":"PVO-based reversible data hiding for encrypted images","authors":"Bo Ou, Xiaolong Li, Weiming Zhang","doi":"10.1109/ChinaSIP.2015.7230521","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230521","url":null,"abstract":"This paper proposes a simple yet effective reversible data hiding (RDH) method for encrypted images. It guarantees exact data extraction and original image recovery from the marked encrypted image. Moreover, it is separable in the sense that the data extraction and the original image recovery can be independently processed. Specifically, we first encrypt the cover image by permutation in both block- and pixel-wise manners using a chaotic mapping. Then, we apply the pixel-value-ordering (PVO) embedding on each permuted block, to reversibly embed data into the encrypted image. Since the pixel value order is unchanged in each block after PVO embedding, the embedded data can be exactly extracted using the inverse PVO whether the marked image is decrypted or not. Experimental results show that the proposed method can provide a better decrypted marked image fidelity compared with some state-of-the-art works.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123284579","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: 11
A localized piecewise constant model with kernel mapping and convex optimization for image segmentation 基于核映射和凸优化的局部分段常数模型
Wenchao Cui, Guoqiang Gong, Ke Lu, Shuifa Sun, Fangmin Dong
{"title":"A localized piecewise constant model with kernel mapping and convex optimization for image segmentation","authors":"Wenchao Cui, Guoqiang Gong, Ke Lu, Shuifa Sun, Fangmin Dong","doi":"10.1109/ChinaSIP.2015.7230383","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230383","url":null,"abstract":"This paper presents a localized piecewise constant model for image segmentation. By taking the local image characteristics into account, the proposed model can effectively segment images with intensity inhomogeneity. Due to the introduction of a kernel-induced non Euclidean distance to its objective functional, our model is more robust to noise and outliers. Its objective functional includes two terms: a data term which evaluates the deviation of the image data from the local region-based piecewise constant model by kernel mapping, and a classic length regularization term for smoothing region boundaries. In order to obtain the global optimal and make the segmentation results independent of the initialization of the algorithm, we reconstructed the energy function to be convex and calculated it by using the Split Bregman theory. The promising experimental results on synthetic and real images validate the effectiveness of the proposed model.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125329411","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
Matched filter based spectrum sensing and power level recognition with multiple antennas 基于匹配滤波器的多天线频谱传感和功率电平识别
Qing Lv, F. Gao
{"title":"Matched filter based spectrum sensing and power level recognition with multiple antennas","authors":"Qing Lv, F. Gao","doi":"10.1109/ChinaSIP.2015.7230413","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230413","url":null,"abstract":"In this paper, we consider the spectrum sensing problem in a cognitive radio (CR) network with only one primary user (PU) and one secondary user (SU). PU is equipped with single antenna while SU is equipped with multiple antennas. The key different from the conventional spectrum sensing studies is that we assume PU could work on different transmit power levels to cope with different communication environments, which is a more practice-matching model. We also suppose that there is some cooperative mechanism between PU and SU so that SU could know PU's training symbols during sensing. In the propose scheme, SU needs not only to detect the presence of PU but also to identify PU's transmit power levels after it is “detected”. Hence, the whole problem is much more challenging than that in conventional CR. We design the matched filter spectrum sensing algorithm by assuming that the channel information is only partially known. Quite a few new performance metrics are provided to better testify the effectiveness of the proposed algorithm in this multiple primary transmit power (MPTP) scenario, and a number of closed-form performance analysis are also derived. Finally simulation results are presented to verify the proposed studies.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116517853","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: 29
An image-based collision detection optimization algorithm 一种基于图像的碰撞检测优化算法
Lixing Wang, Yingjing Shi, Rui Li
{"title":"An image-based collision detection optimization algorithm","authors":"Lixing Wang, Yingjing Shi, Rui Li","doi":"10.1109/ChinaSIP.2015.7230395","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230395","url":null,"abstract":"In this paper, we propose an image-based collision detection optimization algorithm in order to meet the high requirements of real-time and accuracy in the increasingly complex collision detection environment. The algorithm can deal with arbitrary model and will make efficient use of the GPU on the basis of RECODE and RAPID algorithm. In this paper, the algorithm flow will be divided into two stages: the pre-processing stage and the real-time collision detection stage. We will focus on the real-time collision detection stage in this paper. Experimental results show that the algorithm effectively reduces the average collision time compared to RECODE and RAPID algorithm.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117106469","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: 5
A printer forensics method using halftone dot arrangement model 一种采用半色调网点排列模型的打印机取证方法
Han Wu, Xiangwei Kong, S. Shang
{"title":"A printer forensics method using halftone dot arrangement model","authors":"Han Wu, Xiangwei Kong, S. Shang","doi":"10.1109/ChinaSIP.2015.7230527","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230527","url":null,"abstract":"In this paper, we present a printed image forensics method based on detection of halftone dots arrangement. The proposed method can be applied to identify printers and expose image forgery. The printed image is composed of halftone dots and these dots have regular arrangement. For a halftone dot, its adjacent halftone dots can be seen as the vertexes of a hexagon, we model the printer by 6 distance and 6 angles based on the halftone dot positions in the hexagon. In examination step, we apply Euclidean distance and K-means to identify printer and expose the forgeries, respectively. The experimental results have demonstrated the performance of proposed method both on printer identification and forgery detection.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129662072","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: 7
Camouflage modeling for moving object detection 用于移动目标检测的伪装建模
Xiang Zhang, Ce Zhu
{"title":"Camouflage modeling for moving object detection","authors":"Xiang Zhang, Ce Zhu","doi":"10.1109/ChinaSIP.2015.7230401","DOIUrl":"https://doi.org/10.1109/ChinaSIP.2015.7230401","url":null,"abstract":"Discriminative feature based modeling (DFM) is widely used for moving object detection, which, however, may tend to fail when encountering camouflage problems. In this paper we propose a new strategy, camouflage modeling (CM), to detect camouflaged moving objects. In view that a camouflage area is highly content dependent of foreground and the nearby background information, we model both the background and camouflaged foreground respectively, and further identify the truely camouflaged areas. Finally, DFM and CM are fused to perform complete object detection. Experiments are conducted on testing sequences to demonstrate the effectiveness of the proposed method.","PeriodicalId":420610,"journal":{"name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126953202","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: 5
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
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
小红书