Proceedings of the 4th International Symposium on Signal Processing Systems最新文献

Perception of Temporal Quality Fluctuation for HEVC Coded Surveillance Videos HEVC编码监控视频的时间质量波动感知

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532355

Zhuang Wang, Yanchao Gong, Kaifang Yang

引用次数: 1

Hierarchical Vision Transformer with Channel Attention for RGB-D Image Segmentation 基于通道关注的RGB-D图像分割层次视觉变换

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532352

Yali Yang, Yuanping Xu, Chaolong Zhang, Zhijie Xu, Jian Huang

{"title":"Hierarchical Vision Transformer with Channel Attention for RGB-D Image Segmentation","authors":"Yali Yang, Yuanping Xu, Chaolong Zhang, Zhijie Xu, Jian Huang","doi":"10.1145/3532342.3532352","DOIUrl":"https://doi.org/10.1145/3532342.3532352","url":null,"abstract":"Although convolutional neural networks (CNNs) have become the mainstream for image processing and achieved great success in the past decade, due to the local characteristics, CNN is difficult to obtain global and long-range semantical information. Moreover, in some scenes, the pure RGB image-based model is difficult to accurately identify the pixel classification and finely segment the edge of objects. This study presents a hierarchical vision Transformer model named Swin-RGB-D to incorporate and exploit the depth information in depth images to supplement and enhance the ambiguous and obscure features in RGB images. In this design, RGB and depth images are used as the two inputs of the two-branch network. The upstream branch applies the Swin Transform which is capable of learning global continuous information from RGB images for segmentation; the other branch performs channel attention on depth image to abstract the feature correlation and dependency between channels and generates a weight matrix. Then matrix multiplication on the feature maps in each stage of the down-sampling process is performed for weighted multi-modal feature extraction. Then this study adds the fused maps to the up-sampled feature maps of the corresponding size, which sufficiently compensates for the distortion of feature in the sampling process. The experiment results on the two benchmark datasets show that the proposed model makes the network more sensitive to edge information.","PeriodicalId":398859,"journal":{"name":"Proceedings of the 4th International Symposium on Signal Processing Systems","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129781067","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: 4

A Method of Dual-spectrum Feature Fusion for Face Recognition Under Non-ideal Lighting Conditions 非理想光照条件下人脸识别的双光谱特征融合方法

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532348

Da Ai, Weixin Fan, Kai Jia, Mingyue Lu, Y. Liu

引用次数: 0

A Pedestrian Re-identification Algorithm Based on 3D Convolution and Non_Local Block 基于三维卷积和非局部块的行人再识别算法

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532349

Xiaojun Bai, Feihu Jiang, Q. Zhao

引用次数: 1

Dangerous Behavior Recognition Based on Pose Estimation and Action Analysis 基于姿态估计和动作分析的危险行为识别

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532343

Xiaojun Bai, Z. Wang, Zhiying Zhang

{"title":"Dangerous Behavior Recognition Based on Pose Estimation and Action Analysis","authors":"Xiaojun Bai, Z. Wang, Zhiying Zhang","doi":"10.1145/3532342.3532343","DOIUrl":"https://doi.org/10.1145/3532342.3532343","url":null,"abstract":"In order to identify dangerous behaviors such as fighting in public area, proposed a deep learning model that combines human post estimation and action analysis for behavior recognition. The model takes video frame sequence as input, first make use of HRNet as backbone network to detect human body joints and generate human pose frame sequence, and then, make use of recurrent neural network for action analysis from the pose frame sequence, thus determine whether there is dangerous behavior in this video. In the first part, optimization was made on HRNet so as to reduce its parameter and improve the accuracy of joint location. In the second part, introduced Cubic LSTM as a comprehensive model for action recognition, which analysis the motion of human joints from both temporal sequence and spatial sequence, thus achieve better inference score. Experiments show that the recognition accuracy of the proposed method can reach 92.8%. In the last part, a dangerous behavior recognition system is developed based on this model, which use a monitoring host to analysis the captured video frames from cameras, and identify dangerous behavior from them automatically, thus serve for public security tasks.","PeriodicalId":398859,"journal":{"name":"Proceedings of the 4th International Symposium on Signal Processing Systems","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125137739","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

Multilayer Blind Equalization Algorithm Of Neural Network For QAM Signal QAM信号的多层神经网络盲均衡算法

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532358

Chen-Yang Fan, Shuai Wang

{"title":"Multilayer Blind Equalization Algorithm Of Neural Network For QAM Signal","authors":"Chen-Yang Fan, Shuai Wang","doi":"10.1145/3532342.3532358","DOIUrl":"https://doi.org/10.1145/3532342.3532358","url":null,"abstract":"With the development of communication technology, the communication environment has become more and more complex, the linear channel environment no longer exists, and the neural network blind equalization algorithm has good effect on improving the communication quality. So the neural network blind equilibrium algorithm has also attracted a lot of attention. This paper focuses on the blind equalization algorithm of multilayer neural networks based on QAM(Quadrature Amplitude Modulation, a modulation method that performs amplitude modulation on two orthogonal carriers) signals. The iteration step factor with fixed parameters has slightly limitations on the convergence speed and MSE(Mean Square Error, is the average of the sum of the squares of the deviations of the data from the true value, that is, the average of the sums of the squares of the errors) in communication. In order to solve this problem, this paper proposes to transform the fixed-parameter iteration step factor into a variable iteration step factor that is associated with the MSE. In order to solve this problem, we take to change the iteration step factor of fixed parameters into a varying iteration step factor which is related to the mean square error, think of it as a variable parameter, so that the iteration step factor and the mean square error show a positive correlation, which can improve the convergence speed and the final convergence accuracy in the convergence process. Through algorithm analysis and computer simulation, it is shown that the convergence speed and convergence accuracy of the improved algorithm are improved.","PeriodicalId":398859,"journal":{"name":"Proceedings of the 4th International Symposium on Signal Processing Systems","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114929528","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

Design and Implementation of Health Status Management and Monitoring System for Airborne Test System 机载测试系统健康状态管理与监测系统的设计与实现

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532357

Dongsheng Hu, Ni Luo, Yanzhi Li

引用次数: 0

GBSAR Moving Target Detection Capability Evaluation and Refocus based Detection Algorithm GBSAR运动目标检测能力评估与重聚焦检测算法

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532347

Shuo Wang, Wenjie Shen, Yang Li, Yun Lin, Yanping Wang

{"title":"GBSAR Moving Target Detection Capability Evaluation and Refocus based Detection Algorithm","authors":"Shuo Wang, Wenjie Shen, Yang Li, Yun Lin, Yanping Wang","doi":"10.1145/3532342.3532347","DOIUrl":"https://doi.org/10.1145/3532342.3532347","url":null,"abstract":"Ground Based Synthetic Aperture Radar (GBSAR) can retrieve sub-millimeter deformation information of the mine slope by using differential interferometry, which is important to safe production in mining application. However, the continuous operation of vehicles in the mining area can block radar signal to slope. The movement of vehicles may also affect the slope stability. Therefore, using GBSAR to detect moving target signal and remove their influence to deformation retrieval is necessary. To our knowledge, the paper about moving target detection based on GBSAR has not been published. Considering current GBSAR systems are mostly single channel FMCW systems. In this paper, we evaluate the capability of moving target detection based on NCUT Risk Radar GBSAR. The GBSAR moving target signal model is analyzed. Then, detection methods utilize shift and defocusing characteristics are analyze. According to the analysis, a new time-domain phase compensation method with relative speed for azimuth moving target detection is proposed. The analysis and proposed method are verified by simulated data.","PeriodicalId":398859,"journal":{"name":"Proceedings of the 4th International Symposium on Signal Processing Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132321405","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

Simultaneous Recognition Algorithm of Human Activity and Phone Position Based on Multi-sensor Data Fusion 基于多传感器数据融合的人体活动和手机位置同时识别算法

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532345

Da Ai, Rui Hao, Chaolin Feng, Yuxuan Li, Y. Liu

引用次数: 0

Threshold Selection on Circular Histogram Using Renyi Entropy 基于Renyi熵的圆形直方图阈值选择

Proceedings of the 4th International Symposium on Signal Processing Systems Pub Date : 2022-03-25 DOI: 10.1145/3532342.3532351

Jin Jin, Jiu-lun Fan

引用次数: 0