发布求助
文献互助 智能选刊 最新文献

2016 IEEE International Conference on Digital Signal Processing (DSP)最新文献

筛选
英文 中文
Transparency-based Vision through haze 透过雾霾的透明视觉
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868608
Cheng Li, Peng He, Dejun Li, Duyan Bi
{"title":"Transparency-based Vision through haze","authors":"Cheng Li, Peng He, Dejun Li, Duyan Bi","doi":"10.1109/ICDSP.2016.7868608","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868608","url":null,"abstract":"Lightness illusions are such special visual phenomena that give solutions to lightness constancy and help for further image processing tasks such as haze removal. Based on the research of haze illusion, transparency theory and basic atmosphere transfer functions, we propose the tATF model to dehaze. With the idea of filtering, three parameters in the model are calculated respectively; especially the additional transparency term t is obtained by perceptual transparency experiments. Furthermore, a new quantitative standard haziness is naturally presented for evaluating the dehazing effect. Experimental results illustrate that the proposed method effectively yields haze-free images with better objective evaluation values.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125937740","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
Myocardial infarction detection and classification — A new multi-scale deep feature learning approach 心肌梗死检测与分类——一种新的多尺度深度特征学习方法
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868568
J. F. Wu, Y. Bao, S. Chan, H. C. Wu, Li Zhang, Xiguang Wei
{"title":"Myocardial infarction detection and classification — A new multi-scale deep feature learning approach","authors":"J. F. Wu, Y. Bao, S. Chan, H. C. Wu, Li Zhang, Xiguang Wei","doi":"10.1109/ICDSP.2016.7868568","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868568","url":null,"abstract":"This paper presents an efficient detection and classification algorithm of multiple-class myocardial infarction (MI) (i.e., prior and acute), which is one of mortality diseases for humans. However, feature extraction is one of the challenges in MI classification as the extracted features may not be optimized for class separation. To this end, we propose a new deep feature learning based MI detection and classification approach. It seeks to learn a representation of the extracted features that optimize the classification performance. Moreover, to further enhance the feature learning process, we incorporate multi-scale discrete wavelet transformation into the feature learning process to facilitate the extraction of MI features at specific frequency resolutions/scales. Finally, softmax regression is employed to build a multi-class classifier based on the learned optimal representation of the features. Experimental results using public ECG datasets obtained from the PTB diagnostic database show that the proposed approach can achieve better performance than other state-of-the-art approaches in terms of sensitivity and specificity. The effectiveness and good performance of the proposed approach may serve as an attractive alternative to MI classification or other related applications.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129687456","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: 21
Video stabilization based on adaptive local subspace of feature point classification 基于自适应局部子空间特征点分类的视频稳像
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868623
Shuangshuang Fang, Xiaohong Ma, Zhong Cao
{"title":"Video stabilization based on adaptive local subspace of feature point classification","authors":"Shuangshuang Fang, Xiaohong Ma, Zhong Cao","doi":"10.1109/ICDSP.2016.7868623","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868623","url":null,"abstract":"Video stabilization removes jitters from shaking videos, which enhances videos quality to achieve stable and comfortable ones. In this paper, we propose a novel method for video stabilization. First, we classify feature points into inliers and outliers based on the global motion estimation to exclude the feature points on moving objects to stabilize camera movements without the interference of outliers. Second, we assemble the trajectory matrix with inlier trajectories across adaptive frames to guarantee sufficient complete trajectories for factorization. Then every frame is smoothed in separate local subspace. This model is more flexible than a global subspace. In addition, to make the inter-frame transition consistent, we exploit homography consistency to alleviate the abrupt transition of inter-frame segments. Experiments demonstrate that our results are comparable with the state-of-the-art methods.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128243154","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
Improved region-of-interest based rate control for error resilient HEVC framework 改进的基于兴趣区域的错误率控制HEVC框架
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868563
Htoo Maung Maung, S. Aramvith, Y. Miyanaga
{"title":"Improved region-of-interest based rate control for error resilient HEVC framework","authors":"Htoo Maung Maung, S. Aramvith, Y. Miyanaga","doi":"10.1109/ICDSP.2016.7868563","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868563","url":null,"abstract":"In this paper, we propose the improvement of Region-of-Interest (ROI) rate control on our previously proposed error resilient framework for High Efficiency Video Coding (HEVC). Reference picture selection (RPS) method and ROI-based intra refresh method are jointly considered in our previous work [6]. In addition, we also proposed ROI-based CTU depth level decision algorithm for reducing the complexity of the algorithm. To enable coding unit (CU) level intra refresh, we also integrate ROI information into the existing rate control. The ROI information is used not only for intra refresh frame but also for every frame in this paper. Experimental results show that the improved rate control contributes to the better quality than the work in [6] and HEVC with reference picture selection (RPS). For 10% packet error rate, the average PSNR improvement for 720p sequences and WVGA sequences are about 0.5 dB and 0.2 dB respectively. The maximum PSNR improvement is 0.88 dB and the minimum value is 0.13 dB. In addition, we also evaluate the impact of ROI-based CTU depth level decision module over complexity reduction by comparing proposed algorithm with and without CTU depth level decision module. Results show that ROI-based CTU depth level decision module can reduce the computational cost from 1.2% to 11.37%.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127064348","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
Efficient representation learning for high-dimensional imbalance data 高维不平衡数据的高效表示学习
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868610
Bilal Mirza, Stanley Kok, Zhiping Lin, Yong Kiang Yeo, Xiaoping Lai, Jiuwen Cao, Jose Sepulveda
{"title":"Efficient representation learning for high-dimensional imbalance data","authors":"Bilal Mirza, Stanley Kok, Zhiping Lin, Yong Kiang Yeo, Xiaoping Lai, Jiuwen Cao, Jose Sepulveda","doi":"10.1109/ICDSP.2016.7868610","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868610","url":null,"abstract":"In this paper, a multi-layer weighted extreme learning machine (ML-WELM) is proposed for high-dimensional datasets with class imbalance. The recently proposed single hidden layer WELM method effectively tackles class imbalance but it may not capture high level abstractions in image datasets. ML-WELM provides efficient representation learning for big image data using multiple hidden layers and at the same time tackles the class imbalance problem using cost-sensitive weighting. Weighted ELM auto-encoder (WELM-AE) is also proposed for layer-by-layer class imbalance feature learning in ML-WELM. We used four imbalance image datasets in our experiments; ML-WELM performs better than the WELM method on all of them.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127468328","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
What makes for good multiple object trackers? 什么是好的多目标跟踪器?
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868601
Yuqi Zhang, Yongzhen Huang, Liang Wang
{"title":"What makes for good multiple object trackers?","authors":"Yuqi Zhang, Yongzhen Huang, Liang Wang","doi":"10.1109/ICDSP.2016.7868601","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868601","url":null,"abstract":"This paper explores the importance of detection and appearance features for multiple object tracking. Extensive detectors including hand-crafted methods and deep learning methods have been tested. We found in this paper that simply improving detection performance can lead to much better multiple object tracking results. The data association methods used in this paper are Kalman Filter and Hungarian algorithm as proposed in [1]. CNN features and color histogram features are extracted as appearance features to measure similarities between objects. Our experiments show that appearance features can help with data association. We then combine detection and data association together as an overall system. The proposed system can track multiple objects at a speed of 17 fps with high accuracy.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132881059","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
Image deblurring with blur kernel estimation in RGB channels 基于模糊核估计的RGB通道图像去模糊
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868645
Xian-Hui Xu, Hongqing Liu, Yong Li, Yi Zhou
{"title":"Image deblurring with blur kernel estimation in RGB channels","authors":"Xian-Hui Xu, Hongqing Liu, Yong Li, Yi Zhou","doi":"10.1109/ICDSP.2016.7868645","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868645","url":null,"abstract":"Image deblurring aims to recover the clear image from the damaged image. The most existing blind image de-blurring approaches only consider estimating the blur kernel in the gray domain. In fact, for the color image produced by the digital camera, the blur effects for each color channel are usually different. This paper proposes an new approach to acquire more precise blur kernels to reconstruct image by estimating blur kernels through RGB channels independently instead of just using the gray domain. The numerical results demonstrate that proposed approach can achieve better performance compared with other state of the art methods.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132016019","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: 8
Enhancing action recognition in low-resolution videos using dempster-shafer's model 使用dempster-shafer模型增强低分辨率视频中的动作识别
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868644
Zhen Gao, Guoliang Lu, Peng Yan
{"title":"Enhancing action recognition in low-resolution videos using dempster-shafer's model","authors":"Zhen Gao, Guoliang Lu, Peng Yan","doi":"10.1109/ICDSP.2016.7868644","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868644","url":null,"abstract":"With the motivation of lower recognition performance as the resolution of processed action videos decreases, this paper presents a robust action recognition approach based on Dempster-Shafer (DS) theory with assumption that single video frames are independent for action discrimination. By the use of artificial neural network (ANN) estimators trained using single video frames, we first compute the basic belief assignment (BBA) for each video frame in the given query video. The Dempster's rule is then used to combine the resulting BBAs for a final threshold-based decision making. Through experiments conducted on extensive testing data with various levels of video resolutions, we demonstrated outperforming recognition performances by the proposed framework compared with state-of-the-art classifications using sequence matching, voting-based strategy and bag-of-words (BoW) method.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"582 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122693528","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
Recursive regression and Wiener deconvolution for coagulation optimization in water treatment plant 递归回归和维纳反卷积在水处理厂混凝优化中的应用
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868631
Chuhong Fei, T. Wong, Eric Morris, Ting Liu
{"title":"Recursive regression and Wiener deconvolution for coagulation optimization in water treatment plant","authors":"Chuhong Fei, T. Wong, Eric Morris, Ting Liu","doi":"10.1109/ICDSP.2016.7868631","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868631","url":null,"abstract":"A coagulation optimization strategy was developed which utilizes the Wiener deconvolution filter to estimate steady-steady values, and then updates the optimization model using recursive kernel regression. The regression-based dose controller is capable of maintaining a target turbidity level with changing raw water conditions. Various pilot test experiments were performed to validate the effectiveness of the proposed strategy.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121762080","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
Bandwidth blind estimation for OFDM OFDM的带宽盲估计
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868541
Mingqian Liu, Bingbing Li
{"title":"Bandwidth blind estimation for OFDM","authors":"Mingqian Liu, Bingbing Li","doi":"10.1109/ICDSP.2016.7868541","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868541","url":null,"abstract":"Traditional orthogonal frequency division multiplexing (OFDM) bandwidth estimation scheme can not acquire accurate estimation results in low signal to noise ratio (SNR) over multi-path channels. Besides, it acquires a great mount of computation. To deal with these problems, a novel bandwidth estimation scheme for OFDM is proposed. Firstly, the power spectrum of OFDM is estimated by the Welch method. And then, the spectrum is decomposed into many intrinsic mode functions (IMFs) by empirical mode decomposition (EMD) and the suitable IMFs are chosen according to the thresholds to reconstruct the spectrum. After that, the positions of the maximum and the minimum of the impulse are extracted in the reconstructed spectrum, which are used as the beginning and the end of the spectrum. Finally, the statistical average of the computed bandwidth is used as the final bandwidth. Simulation results show that the proposed scheme has higher precision and lower computation in low SNR over multi-path channels.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133761744","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 下一页 尾页
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