发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2020 4th International Conference on Digital Signal Processing最新文献

筛选
英文 中文
VESS 维斯
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408178
Sifan Yang, Qi Zheng, X. Hu, Guijin Wang
{"title":"VESS","authors":"Sifan Yang, Qi Zheng, X. Hu, Guijin Wang","doi":"10.1145/3408127.3408178","DOIUrl":"https://doi.org/10.1145/3408127.3408178","url":null,"abstract":"Comparing with traditional frame-based camera, event camera (also known as dynamic vision sensor) has received increasing attention due to various outstanding advantages. Inspired by biology, the camera naturally captures the dynamics of a scene with low latency, filtering out redundant information with low power consumption. Deep learning based instance segmentation, which are influential research in visual recognition tasks, could potentially take advantage of the benefits of event camera, but the event based application combined with deep learning still faces some challenges. In this work, we propose to develop event-based instance segmentation that unlocks the potential of the event data by combining event camera and deep learning. To make the best out of the event data, we propose a novel event representation method - variable event stream structure (VESS) for event-based instance segmentation. However, event-based datasets are rare, and none of them contains instance segmentation labels, we produce the accurate label specialized for instance segmentation on event camera. The proposed method before is verified on the dataset, and our work can reach an average Intersection over Union (IOU) of 55.75% in real-time and work properly under challenging environment like motion blur and extreme lighting condition.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115835549","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
Performance Analysis of Direction of Arrival Estimation Based on Deep Learning 基于深度学习的到达方向估计性能分析
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408156
Min Chen, X. Mao, Yi Gong
{"title":"Performance Analysis of Direction of Arrival Estimation Based on Deep Learning","authors":"Min Chen, X. Mao, Yi Gong","doi":"10.1145/3408127.3408156","DOIUrl":"https://doi.org/10.1145/3408127.3408156","url":null,"abstract":"In this paper, a new efficient direction of arrival (DOA) estimation approach based on the deep neural networks (DNN) is proposed, in which a nonlinear mapping that relates the outputs of the receiving antennas with its associated DOA is learning by using the DNN-based network. The novel network architecture is divided into two stages, the detection phase and the DOA estimation phase. Additional detection network attached in our structure dramatically reduces the size of the training set. It has been shown that the proposed method not only can achieve reasonably high DOA estimation accuracy, but also can reduce the computational complexity required by traditional superresolution DOA estimation algorithms such as multiple signal classification (MUSIC). The computer simulation results are performed to investigate the generalization and effectiveness of the proposed approach in different scenarios.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126764548","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
Type Recognition of Frequency Synthesizer Based on Convolutional Neural Networks 基于卷积神经网络的频率合成器类型识别
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408189
Xihang Yin, Xiaoyu Li, Yanyi Li
{"title":"Type Recognition of Frequency Synthesizer Based on Convolutional Neural Networks","authors":"Xihang Yin, Xiaoyu Li, Yanyi Li","doi":"10.1145/3408127.3408189","DOIUrl":"https://doi.org/10.1145/3408127.3408189","url":null,"abstract":"This paper mainly proposes a method of frequency synthesizer type recognition based on Convolutional Neural Networks (CNN). The unique influence of the internal structure of the frequency synthesizer on the output signal is proposed in this paper, the phase truncation model of the direct digital frequency synthesizer (DDS) and the model of fractional-N charge pump phase-locked loop (Fractional-N PLL) are constructed respectively. Two models are simulated to obtain signals with 40 frequency. The time-frequency images are obtained by Short-Time Fourier Transform (STFT), as the input of the CNN. The trained networks model could identify which frequency synthesizer the signal comes from. In this experiment, signals with 6 different signal-to-noise ratios (SNR) were used to verify the feasibility of the method. The results show that the CNN-based frequency synthesizer type recognition has a higher accuracy and can realize the type recognition of frequency synthesizer effectively.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121450326","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
uAVS3d
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408140
Zhenyu Wang, Bingjie Han, Ronggang Wang, Kui Fan, Wen Gao
{"title":"uAVS3d","authors":"Zhenyu Wang, Bingjie Han, Ronggang Wang, Kui Fan, Wen Gao","doi":"10.1145/3408127.3408140","DOIUrl":"https://doi.org/10.1145/3408127.3408140","url":null,"abstract":"Compared with AVS2 and HEVC, the compression performance of the 3rd generation audio video coding standard (AVS3) has been greatly improved. For the preliminary application of this emerging coding standard, an efficient implementation of software-based decoder is necessary before the decoding chips are widely used. However, real-time decoding of UHD streams is still a big challenge for AVS3 standard. In this paper, we proposed a fast decoder design for AVS3, consisting of framework optimization, data structure and module optimizations, SIMD optimization, and parallel decoding. On the one hand, a non-redundant and cache-friendly decoding framework is proposed. In this framework, data structure and some key modules are optimized. On the other hand, SIMD instructions and frame-level parallelism are applied to fully accelerate decoding on a general-purpose processor. We also implemented an efficient AVS3 decoder (uAVS3d) in this paper. Experimental results show that, when decoding streams with bit depths of 10 and 8 on the i7--7800x processor, uAVS3d is 4.2 and 6.3 times faster than the AVS3 reference software with single-thread, respectively. uAVS3d has a speed-up of 6.2x when decoding with 17 threads comparing with single-thread on this processor, and can decode UHD streams in real-time. Additionally, uAVS3d has a decoding speed of 33.8 fps with single-thread for 1080p video on Huawei P10. Thus, uAVS3d can be used in most existing video applications on PC and mobile terminal device.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115307127","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
A Convex Optimization Algorithm for Total Rate Maximization in Block Diagonalization Based Ultra Dense Network 基于块对角化的超密集网络中总速率最大化的凸优化算法
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408128
Wanyu Yan, Hui Li, Limeng Dong
{"title":"A Convex Optimization Algorithm for Total Rate Maximization in Block Diagonalization Based Ultra Dense Network","authors":"Wanyu Yan, Hui Li, Limeng Dong","doi":"10.1145/3408127.3408128","DOIUrl":"https://doi.org/10.1145/3408127.3408128","url":null,"abstract":"Ultra dense network (UDN) has drawn widely attention due to its virtual cell structure in which users are served by multiple base stations (BS) could significantly boost the total capacity, and have vast potential for further development in next 5G wireless systems. Nevertheless, the interference between different users in UDN is still a critical issue and hence the quality of communications can be seriously affected. In this paper, we consider a UDN consisting of multiple virtual cells, and focus on maximizing the total user rate of this network. To eliminate the interference between each user, block diagonalization is used so that the original rate maximization problem can be transformed to a convex optimization problem. To solve this problem, an algorithm is proposed which is based on barrier method and in combination with Newton method and backtracking line search. Simulation results have validated that the proposed algorithm can have same performance but with significantly faster computing speed than the existing CVX solver.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127515484","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
Image Enhancement and Translation for RGB-D Indoor Scene Recognition RGB-D室内场景识别的图像增强与转换
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408174
Sifan Yang, Yue Wang, Yang Li, Guijin Wang
{"title":"Image Enhancement and Translation for RGB-D Indoor Scene Recognition","authors":"Sifan Yang, Yue Wang, Yang Li, Guijin Wang","doi":"10.1145/3408127.3408174","DOIUrl":"https://doi.org/10.1145/3408127.3408174","url":null,"abstract":"Most existing methods for RGB-D indoor scene recognition adopt the backbone networks designed for image recognition. They overly focus on global features but largely ignore the local features, resulting in unsatisfactory accuracy in practice. This paper proposes a T-like network called T-Net to comprehensively exploit both global and local features by multi-scale supervision. In detail, we add an image translation branch and introduce pixel-level semantic segmentation annotations along with the image-level labels, to jointly supervise the model to excavate more regions of objects. In addition, low-quality source images without image enhancement cause difficulty in extracting representative features. To address this issue, the Multi-Scale Retinex with Color Restoration (MSRCR) is introduced to enhance the brightness and contrast of the RGB images. We demonstrate that the proposed method achieves superior performance to the state-of-the-art methods on SUN RGB-D and NYU Depth v2 Datasets.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133751505","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
An Improved Multichannel Subspace Speech Enhancement Algorithm for Balance between Noise Reduction and Speech Distortion 一种兼顾降噪和语音失真的改进多通道子空间语音增强算法
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408131
Jingxian Tu, Yunzhou Yao, Guijiang Qin
{"title":"An Improved Multichannel Subspace Speech Enhancement Algorithm for Balance between Noise Reduction and Speech Distortion","authors":"Jingxian Tu, Yunzhou Yao, Guijiang Qin","doi":"10.1145/3408127.3408131","DOIUrl":"https://doi.org/10.1145/3408127.3408131","url":null,"abstract":"This paper proposes an improved multichannel subspace speech enhancement algorithm for balance between noise reduction and speech distortion. In the proposed algorithm, the weighting between noise reduction and speech distortion is adjusted adaptively. Moreover, the exact relational expression between this weighting and the input short time signal to noise (SNR) is given. When the weighting is bigger, more noise reduction and more speech distortion is achieved. Generally, the weighing value ranges from 0 to positive infinity, and the higher the input short time SNR is, the smaller the weighting is. Simulation results show that the proposed algorithm achieve the better performance in terms of the perceptual evaluation of speech quality than the conventional multichannel subspace speech enhancement algorithm.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117075944","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
Diverse Subblock-Level Motion Derivation Schemes for AVS3 AVS3的各种子块级运动派生方案
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408138
Xi Xie, Kui Fan, Ronggang Wang
{"title":"Diverse Subblock-Level Motion Derivation Schemes for AVS3","authors":"Xi Xie, Kui Fan, Ronggang Wang","doi":"10.1145/3408127.3408138","DOIUrl":"https://doi.org/10.1145/3408127.3408138","url":null,"abstract":"AVS3 is the third generation audio video coding standard (AVS) developed by the AVS working group from 2018 and its base profile achieves roughly 20% bit rate saving compared to H.265/HEVC. In this paper, two subblock-level motion derivation methods, including enhanced temporal motion vector prediction (ETMVP) and planar mode based motion vector prediction (PMMVP), are proposed to diversify the motion derivation scheme and enhance the prediction efficiency of skip/direct mode in the AVS3 structure. Different from the traditional temporal motion vector prediction (TMVP), subblock-level motion vectors in ETMVP are derived by combining the traditional TMVP and motion vector difference predictor (MVDP). In PMMVP, the motion of each subblock is generated by interpolation from spatially neighboring blocks in a manner of intra planar mode. The newly introduced motions are developed as the additional motion candidates in skip/direct mode. The proposed method is implemented on top of the AVS3 reference software (HPM-3.2), and the experimental result shows that a 1.65% BD-rate reduction (up to -3.13%) is achieved under Random Access configuration.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124723196","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 Novel Feature Extraction Method for Underwater Acoustic Target Based on Parameter Optimized VMD and 1(1/2)-D Spectrum 基于参数优化VMD和1(1/2)-D谱的水声目标特征提取新方法
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408149
Dan Xu, Huiwen Zheng, Qiao Hu
{"title":"A Novel Feature Extraction Method for Underwater Acoustic Target Based on Parameter Optimized VMD and 1(1/2)-D Spectrum","authors":"Dan Xu, Huiwen Zheng, Qiao Hu","doi":"10.1145/3408127.3408149","DOIUrl":"https://doi.org/10.1145/3408127.3408149","url":null,"abstract":"Due to the difficulty of correctly extracting the features of underwater target radiated noise in the complicated environment, a novel feature extraction method for underwater acoustic target based on parameter optimized variational mode decomposition (VMD) and 1(1/2)-dimensional spectrum is proposed. Firstly, the number of modal components and quadratic penalty term are optimized by particle swarm optimization (PSO) algorithm, and the results of PSO algorithm are used as the input parameters of VMD algorithm. Then, the radiated noise signal of underwater acoustic target is decomposed into several intrinsic mode functions (IMFs) by VMD algorithm. Secondly, the envelope entropy of each IMF is calculated, and the IMF corresponding to the minimum envelope entropy is selected as the optimal component. The Hilbert envelope demodulation analysis is performed on the optimal component to obtain the envelope signal. Finally, the envelope signal is analyzed by 1(1/2)-dimensional spectrum analysis method to extract modulation features. The simulated and the ship's radiated noise signals are analyzed by the proposed method, and the results demonstrate that the modulation features of signals can be extracted successfully, which indicates that the proposed method is effective.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116393938","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
Sparse Construction Decorrelation Algorithm of Uniform Circular Array 均匀圆形阵列稀疏构造去相关算法
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408160
Liuliu Ni, Jifeng Zhang, Hui Chen
{"title":"Sparse Construction Decorrelation Algorithm of Uniform Circular Array","authors":"Liuliu Ni, Jifeng Zhang, Hui Chen","doi":"10.1145/3408127.3408160","DOIUrl":"https://doi.org/10.1145/3408127.3408160","url":null,"abstract":"This paper present a uniform circular array sparse reconstruction algorithm based on conjugate subarray to deal with decorrelation of uniform circular array. Using original point symmetry of circular array with even number of array elements, the algorithm constructs a pair of conjugate symmetric subarrays, then restores the rank of coherent signal source through spatial smoothness between subarrays and achieves direction-of-arrival (DOA) estimation of coherent signal source by using l1-norm sparse reconstruction. The algorithm makes full use of strong decorrelation of spatial smooth processing and high accuracy of sparse reconstruction estimation to achieve high accurate estimation of coherent signal source. Simulation results show that the algorithm has good decorrelation ability and high estimation performance.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"10 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120891676","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
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
小红书