Proceedings of the 6th International Conference on Digital Signal Processing最新文献

Joint Power and Bandwidth Allocation for 3D Video SoftCast 3D视频软播的联合功率和带宽分配

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529600

Saqr Khalil Saeed Thabet, Emmanuel Osei-Mensah, Lei Luo, Ce Zhu

{"title":"Joint Power and Bandwidth Allocation for 3D Video SoftCast","authors":"Saqr Khalil Saeed Thabet, Emmanuel Osei-Mensah, Lei Luo, Ce Zhu","doi":"10.1145/3529570.3529600","DOIUrl":"https://doi.org/10.1145/3529570.3529600","url":null,"abstract":"Unlike digital video transmission systems, SoftCast avoids the cliff effect and achieves a linear video quality transition that is commensurate with the wireless channel conditions. When SoftCast is applied to three-Dimension Video (3DV) transmission, resource allocation issues arise: 1) allocating the limited power budget to texture and depth to achieve the optimal overall quality. 2) distributing the suitable number of texture and depth chunks to adapt to bandwidth constraints. This work aims to efficiently solve the optimal joint power and bandwidth allocation problem. First, a power-distortion optimization problem is formulated to calculate the optimal Power Allocation Ratio (PAR) between texture and depth, then mapped to an unconstrained problem and solved using the Lagrangian multiplier. Finally, based on the closed-form of the optimal solution, an iterative algorithm is proposed to choose the suitable number of texture/depth chunks for a given bandwidth constraint. The proposed method achieves better performance than its counterpart default fixed-ratio power allocation between texture/depth. Further, we observe a graceful video quality transition with the improvement of channel conditions under bandwidth constraints.","PeriodicalId":430367,"journal":{"name":"Proceedings of the 6th International Conference on Digital Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115649013","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

Kalman Filter Using SOV Model with Maximum Versoria Criterion for Short-Term Traffic Flow Forecasting 基于最大Versoria准则的SOV模型卡尔曼滤波短期交通流预测

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529579

Tingting Jiang, Zhao Zhang

引用次数: 0

Parameter Estimation of LFM Signal Based on Improved Fractional Fourier Transform 基于改进分数阶傅里叶变换的LFM信号参数估计

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529607

Guanyu Qiao, D. Dai, Caikun Zhang

引用次数: 0

A SAR Image Denoising Method for Target Shadow Tracking Task 一种用于目标阴影跟踪的SAR图像去噪方法

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529598

Yankun Huang, Guangcai Sun, M. Xing

引用次数: 1

Efficient Cable Surface Defect Detection with Deep Learning 基于深度学习的高效电缆表面缺陷检测

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529595

Guo-Chung Chen, Feng Xu, Guihua Liu, Yanjie Chen, Zhiqiang Liang

{"title":"Efficient Cable Surface Defect Detection with Deep Learning","authors":"Guo-Chung Chen, Feng Xu, Guihua Liu, Yanjie Chen, Zhiqiang Liang","doi":"10.1145/3529570.3529595","DOIUrl":"https://doi.org/10.1145/3529570.3529595","url":null,"abstract":"Efficient detection of cable surface defects can prevent and reduce the potential dangers in the process of high voltage transmission. In order to achieve efficient detection of cable surface defects and solve the problem of low detection accuracy of small and unobvious defects on cable surface, we propose an efficient cable surface defect detection model with deep learning. Firstly, the lightweight backbone feature extraction network is used to extract the preliminary defect features. Secondly, the parallel convolution module and serial convolution module are designed to obtain abundant defect features and reduce the number of model parameters. Then, the feature fusion module is designed to fuse the shallow features with deep features to enhance the features of small and unobvious defects. Finally, the obtained features are put into the corresponding detection head to get the final prediction results. The experimental results on local cable dataset show that our method achieves favorable trade-off between the accuracy, speed and model size of the cable surface defect detection, which meets the requirements of high accuracy, high speed and small model in industrial application.","PeriodicalId":430367,"journal":{"name":"Proceedings of the 6th International Conference on Digital Signal Processing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125598021","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

Some Evaluations on Spectrogram Art Communications Exchanging Secret Visual Messages 对交换秘密视觉信息的谱图艺术传播的若干评价

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529583

N. Aoki, Kenichi Ikeda, H. Yasuda, Ying Shen, Jin Hou

引用次数: 0

Diffusion Constrained Least Mean M-estimate Algorithm for Adaptive Networks 自适应网络的扩散约束最小均值m估计算法

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529601

Wenjing Xu, Haiquan Zhao

引用次数: 1

CCTV Latent Representations for Reducing Accident Response Times 减少事故响应时间的CCTV潜在表征

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529582

Shafinul Haque

{"title":"CCTV Latent Representations for Reducing Accident Response Times","authors":"Shafinul Haque","doi":"10.1145/3529570.3529582","DOIUrl":"https://doi.org/10.1145/3529570.3529582","url":null,"abstract":"Emergency Medical Services’ response times to accidents are crucial to saving lives in vehicle accidents. Using deep learning to instantly detect accidents in public cameras and automatically alerting authorities could help this issue. However, this would require a large set of data on public cameras to train on, but this type of data hardly exists in a usable form. Current deep learning approaches to vehicle accidents typically use first-person cameras, which are not helpful for reducing response time as we do not have access to these cameras at all times. Also, public cameras such as closed-circuit television (CCTV) pick up a much larger amount of street activity than private cameras. Thus, we create a video dataset from live closed-circuit television, so we have access to the cameras at all times. We annotate the videos with metadata to help with future trend prediction as well as give further information for each video, as they are unlabeled. We create an unsupervised learning model to train on this video dataset, and visualize latent space representations of this data in order to cluster different types of street activity and pinpoint vehicle accidents. 1","PeriodicalId":430367,"journal":{"name":"Proceedings of the 6th International Conference on Digital Signal Processing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132323442","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

Improving Quantization Matrices for Image Coding by Machine Learning 基于机器学习的图像编码量化矩阵改进

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529590

Wei Ke, Ka‐Hou Chan

引用次数: 1

Interpretable Analysis and Pruning of Modulation Recognition Network Based on Deep Learning 基于深度学习的调制识别网络可解释性分析与剪枝

Proceedings of the 6th International Conference on Digital Signal Processing Pub Date : 2022-02-25 DOI: 10.1145/3529570.3529577

Fan Ni, Min Luo

{"title":"Interpretable Analysis and Pruning of Modulation Recognition Network Based on Deep Learning","authors":"Fan Ni, Min Luo","doi":"10.1145/3529570.3529577","DOIUrl":"https://doi.org/10.1145/3529570.3529577","url":null,"abstract":"Concerning poor interpretability and complexity of deep model in modulation recognition (MR) based on deep learning, an interpretable analysis and pruning framework of MR network based on Gradient-weighted Class Activation Mapping (Grad-CAM) is accordingly proposed in this paper. The framework first extracts the amplitude, phase and spectrum from the original modulated signal, and it uses the Smoothed Pseudo Wigner-Ville Distribution (SPWVD) to obtain the two-dimensional time-frequency spectrum of the modulated signal. Then, the key features in the deep model are visualized from the perspective of one-dimensional features and two-dimensional features at the input respectively. The framework visually displays and compares the differences and commonalities of the depth features of hidden layer with different models, extract the values of different filters of each layer in the deep neural network (DNN), and prune the network according to the values. The experiment results show that the interpretable and pruning framework of MR network based on Grad-CAM in this paper can achieve effective explanation and analysis on the MR network, and can greatly reduce the redundancy of the network. The running speed of the pruned network is 3.83 times higher than that of the original network. The size of the pruned network is 72% lower than that of the original network. Besides, the accuracy of the pruned network is 0.3% higher than that of the original network.","PeriodicalId":430367,"journal":{"name":"Proceedings of the 6th International Conference on Digital Signal Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121274068","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