2022 14th International Conference on Signal Processing Systems (ICSPS)最新文献

DTMR: Industrial Digital Twin Architecture for New Production Line Design in Mixed Reality Environment 混合现实环境下新生产线设计的工业数字孪生体系结构

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00149

Jinjun Xia, Ting Jin, Lingjie Fan

引用次数: 0

Control Point Compression and Optimization Algorithm Based on Improved Particle Swarm Optimization in Non-Uniform Rational B-Spline Fitting 基于改进粒子群优化的非均匀有理b样条拟合控制点压缩与优化算法

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00069

Mingxia Li, Wenjiang Wu, Na Liu, Rongli Gai, Yitong Guo

引用次数: 0

Functional-Penetrated Interactive System Towards Virtual-Real Fusion Environments 面向虚实融合环境的功能渗透交互系统

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00151

Dongdong Weng, Wenjie He, Shushan Guo, Dong Li

{"title":"Functional-Penetrated Interactive System Towards Virtual-Real Fusion Environments","authors":"Dongdong Weng, Wenjie He, Shushan Guo, Dong Li","doi":"10.1109/ICSPS58776.2022.00151","DOIUrl":"https://doi.org/10.1109/ICSPS58776.2022.00151","url":null,"abstract":"Current mixed reality technology cannot completely map the information in the physical world to the virtual environment, and the user must take off the head-mounted display to deal with the affairs in the real environment when using the mixed reality system. This greatly reduces the immersion created by the virtual reality system, and also reduces work efficiency. In order to realize the user's direct interaction with the physical world in the virtual environment without destroying the immersion of the virtual reality system, this paper proposes a functional-penetrated interactive system towards the virtual-real fusion environment, which extracts the visual information of objects from the real scene captured by the RGB camera through deep neural networks, completes virtual-real registration and presents it in real time in the virtual environment, and finally enables the user to complete the manipulation of the physical objects in the virtual environment. In addition, the system also allows the user to dynamically adjust the virtual-real fusion ratio according to the user's needs, which achieves a balance between the immersion of the virtual-real fusion environment and the interaction efficiency of the system. Experimental results show that the system can provide users with more realistic physical feedback, with higher interaction freedom and universality.","PeriodicalId":330562,"journal":{"name":"2022 14th International Conference on Signal Processing Systems (ICSPS)","volume":"57 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116448193","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 Stereovision EEG Channel Selection Method Based on Cross Increment Entropy Maximization 基于交叉增量熵最大化的立体视觉脑电信号通道选择方法

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00045

Wei Zhou, Tingting Zhang, L. Xia, Xiaofeng Liu

引用次数: 0

Model Compression Based on SAR-Optical Image Mapping Task 基于sar -光学图像映射任务的模型压缩

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00088

Sijie Wang, Jianjiang Zhou, Tianzhu Yu

{"title":"Model Compression Based on SAR-Optical Image Mapping Task","authors":"Sijie Wang, Jianjiang Zhou, Tianzhu Yu","doi":"10.1109/ICSPS58776.2022.00088","DOIUrl":"https://doi.org/10.1109/ICSPS58776.2022.00088","url":null,"abstract":"In recent years, due to the scarcity of resources for pairing SAR images with optical images, image mapping tasks have become an important research direction in the field of Earth observation. Conditional Generative Adversarial Networks have demonstrated their superior performance and great potential on the task of SAR-Optical image translation. However, a more complex network means a larger amount of computing and more computing resource consumption, which makes task deployment and application landing become more challenging. In this paper, we propose a compression algorithm based on the image mapping model, which can minimize the number of parameters and the computational resource costs of the model, while preserving its performance of the model most. We analyze the structure and parameter distribution of the image generator, and design a lightweight mapping module based on Depthwise Separable Convolution. In view of the sensitivity of Conditional Generative Adversarial Networks to structure, we design an automatic channel pruning algorithm based on Neural Architecture Search. This algorithm further compresses the number of parameters on the lightweight generator to speed up inference. Finally, we test on the SAR-Optical image mapping task, and the model under the compression algorithm has a better mapping effect than the model of the same scale. The algorithm achieves a better mapping effect at a lower cost of computing resources, and provides more possibilities for the deployment and development of image mapping tasks.","PeriodicalId":330562,"journal":{"name":"2022 14th International Conference on Signal Processing Systems (ICSPS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114600764","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

Fully Adaptive Constant Module Sequence Set Design for Waveform-Agile Coherent Radar System in the Presence of Signal-Dependent Clutter 信号相干杂波存在下波形捷变相干雷达系统的全自适应恒模序列集设计

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00015

Shiyi Li, Jindong Zhang, Daiyin Zhu

引用次数: 0

An Underwater Wideband Multi-Highlight Active Target Velocity Estimation Method Based on Cepstrum and Matched Filter 一种基于倒谱和匹配滤波器的水下宽带多高光目标速度估计方法

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00055

Z. Xiao, Ning Han

{"title":"An Underwater Wideband Multi-Highlight Active Target Velocity Estimation Method Based on Cepstrum and Matched Filter","authors":"Z. Xiao, Ning Han","doi":"10.1109/ICSPS58776.2022.00055","DOIUrl":"https://doi.org/10.1109/ICSPS58776.2022.00055","url":null,"abstract":"In this paper, a multi-highlight target echo model is investigated, and the target is considered to be of a constant relative velocity to the sonar. The echo is usually equivalent to the superposition of reflections from single highlight. Due to the relative motion of the active sonar and the target, the echo is stretched or compressed. Moreover, noise and reverberation are existed in the underwater environment. All of the above degrade the performance of the target velocity estimation. As a nonlinear signal operation method, cepstrum can change the convolution operation in time domain into the summation operation in the cepstrum domain. Based on the good performance of cepstrum operation in detecting periodic signals, a cepstrum-based target velocity estimation method is proposed. In this method, a combined pulse signal is transmitted, and the received echo is successively subjected to Matched Filter and cepstrum operation, the position of the peak in the cepstrum domain is searched to estimate the velocity of the target. Simulation results demonstrated that the proposed method can estimate the target velocity precisely at low signal-to-noise ratio using small computational effort.","PeriodicalId":330562,"journal":{"name":"2022 14th International Conference on Signal Processing Systems (ICSPS)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124596329","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

SSIGAN: Semantic Segmentation via Improved Generative Adversarial Network 基于改进生成对抗网络的语义分割

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00140

Mengxu Lu, Zhenxue Chen, Hao Qin, Yujiao Zhang, Jingjing Ji

引用次数: 0

Change Detection Using Unsupervised Sensitivity Disparity Networks 基于无监督灵敏度视差网络的变化检测

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00084

Xiaochen Yuan, Jinlong Li

{"title":"Change Detection Using Unsupervised Sensitivity Disparity Networks","authors":"Xiaochen Yuan, Jinlong Li","doi":"10.1109/ICSPS58776.2022.00084","DOIUrl":"https://doi.org/10.1109/ICSPS58776.2022.00084","url":null,"abstract":"At present, algebraic operation methods in the field of change detection still holds the dominant position. However, in the face of disturbance features, due to the characteristics of poor expansibility, the performance of algebraic operation methods varies greatly in different scenes, and cannot meet the requirements of practical application. In this paper we propose a change detection model based on Sensitivity Disparity Networks (SDNs) for performing change detection in Bi-temporal Hyper-spectral images captured by AVIRIS sensor and HYPERION sensor over time. The SNDs consist of two deep learning models, Unchanged Sensitivity Networks (USNet) and Changed Sensitivity Networks (CSNet), they have sensitivity disparity in changed and unchanged pixels, and thus to generate effective argument region. Next, we re-evaluate the change probability of argument region, and merge the change result of the argument region with that by one of the SDNs. The detected Binary Change Map (BCM) of the scheme is thus obtained. To train and evaluate the proposed schema we employ two Bi-temporal Hyper-spectral image datasets which contain challenging pseudo-changed features (PCFs) and pseudo-invariant features (PIFs) cause by various external interference factors. The proposed schema outperforms the existing state-of-the-art algorithms on tested datasets. Experimental results show that the proposed schema has good universality and adaptability.","PeriodicalId":330562,"journal":{"name":"2022 14th International Conference on Signal Processing Systems (ICSPS)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129125149","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

Lightweight YOLOv4 Algorithm for Remote Sensing Image Detection 轻量级YOLOv4遥感图像检测算法

2022 14th International Conference on Signal Processing Systems (ICSPS) Pub Date : 2022-11-01 DOI: 10.1109/ICSPS58776.2022.00144

Li Ma, Tongdi He, Yong Sun, Bin Hu

{"title":"Lightweight YOLOv4 Algorithm for Remote Sensing Image Detection","authors":"Li Ma, Tongdi He, Yong Sun, Bin Hu","doi":"10.1109/ICSPS58776.2022.00144","DOIUrl":"https://doi.org/10.1109/ICSPS58776.2022.00144","url":null,"abstract":"Remote sensing images have the characteristics of complex backgrounds, high resolution, and small targets. Although the existing object detection algorithms can improve the detection accuracy, there are generally problems such as a large number of model parameters, high computational cost, and poor real-time performance. Aiming at the above problems, this paper designs a lightweight object detection algorithm GSC-YOLO based on YOLOv4 to achieve fast and accurate detection of remote sensing images. First, Ghostnet is used as the feature extraction network of GSC-YOLO to reduce the number of parameters and improve the detection speed; Secondly, the improved shuffle attention mechanism is introduced in the prediction head to make the model pay attention to important information and improve the detection accuracy; Finally, the Confidence Propagation Cluster algorithm CP-Cluster is used to post-process the prediction frame to improve the object recognition. Taking the preprocessed DOTA dataset as the experimental object, the experimental results show that the GSC-YOLO algorithm has a detection accuracy of 93.44%, a detection speed of 58 frames per second, and a model size of 43.65MB. Compared with the remote sensing image object detection algorithm based on YOLOv4, the detection accuracy is increased by 3.93%, the detection speed is increased by 1.87 times, and the model size is reduced by 5.62 times, which is more suitable for deployment on devices with limited resources.","PeriodicalId":330562,"journal":{"name":"2022 14th International Conference on Signal Processing Systems (ICSPS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114736789","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