2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)最新文献_第3页

Fast high-definition video background completion using features tracking 使用特征跟踪快速高清视频背景完成

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824726

Jocelyn Benoit, Eric Paquette

{"title":"Fast high-definition video background completion using features tracking","authors":"Jocelyn Benoit, Eric Paquette","doi":"10.1109/ISPACS.2016.7824726","DOIUrl":"https://doi.org/10.1109/ISPACS.2016.7824726","url":null,"abstract":"This paper presents an automatic video background completion approach based on invariant features tracking and image registration to find valid replacement regions. Previous exemplar-based methods provide good results for low-resolution video sequences, but suffer from long computation times and large memory consumption for high-definition sequences. We first select a candidate frame to complete a missing region using invariant features tracking and image registration. This greatly reduces computation times as it does not require the lengthy nearest neighbor searches seen in typical video completion methods. To minimize registration errors, we introduce a fast validation approach. Then, we propose an exposure correction method based on histogram specification to eliminate illumination inconsistencies in the completed regions. Finally, we complete the missing region with a multi-band blending approach to minimize boundary discontinuities. Our approach can achieve good quality results on high-definition videos, and it can deal with a variety of real-life problems, such as non-trivial camera movement and illumination changes. Furthermore, the proposed method requires low computation times which represent a 24–54 times speedup over previous methods. In addition to providing specific implementation details, this paper presents experimental results on a variety of videos and compares them to state-of-the-art methods in terms of visual quality and performance.","PeriodicalId":131543,"journal":{"name":"2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"2 5 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":"126288716","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

QLB: QoS routing algorithm for Software-Defined Networking QLB:软件定义网络的QoS路由算法

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824704

Piyawit Tantisarkhornkhet, Warodom Werapun

{"title":"QLB: QoS routing algorithm for Software-Defined Networking","authors":"Piyawit Tantisarkhornkhet, Warodom Werapun","doi":"10.1109/ISPACS.2016.7824704","DOIUrl":"https://doi.org/10.1109/ISPACS.2016.7824704","url":null,"abstract":"Software-Defined Networking (SDN) is a new efficiently idea of programmable networks that separates the control plane from data plane of all network devices. Internet service provider is responsible for all the control decisions and communication among the forwarding elements from centralized controller. SDN provides the various optimized services. Quality of service (QoS) routing is a path computation method that is suitable for the different traffics generated by several applications, while utilization of network resources has increased. This agreement of service is defined by QoS requirements such as throughput, delay, jitter and packet loss etc. Multimedia applications often require assured from multi QoS constrained, causing the NP-complete problem which cannot be simply solved in polynomial time and high management complexity in the transition network. SDN is able to reduce complexity and it is used to efficiently implement traffic, hence SDN significantly values to development QoS routing. In this paper, we propose QoS routing algorithm called Quantized Level Balance (QLB) for SDN that considers one or many QoS parameters relating to the network application. To satisfy the requirements, QLB selects QoS parameters depending to the level of appropriate application service quality. We have replicated our algorithm on simulate topology with Scalable Video-streaming Evaluation Framework (SVEF). We measure the Peak Signal-to-Noise Ratio (PSNR) and Mean Opinion Score (MOS) of Scalable Video Coding (SVC) at the receiver. Our propose algorithm is improved than single-metric approach that may choose poor QoS parameter paths.","PeriodicalId":131543,"journal":{"name":"2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"45 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":"126480001","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: 5

Improving motorcycle anti-theft system with the use of Bluetooth Low Energy 4.0 利用低功耗蓝牙4.0技术改进摩托车防盗系统

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824705

W. Koodtalang, T. Sangsuwan

{"title":"Improving motorcycle anti-theft system with the use of Bluetooth Low Energy 4.0","authors":"W. Koodtalang, T. Sangsuwan","doi":"10.1109/ISPACS.2016.7824705","DOIUrl":"https://doi.org/10.1109/ISPACS.2016.7824705","url":null,"abstract":"This paper proposes the improvement of motorcycle anti-theft system (MATS) utilizing Bluetooth Low Energy (BLE) 4.0. In the our previous work, the couple RFID passive tags were installed on motorcycles to detect the larceny conditions. The main problem was found in the last experiments that the RFID tags attached with the ignition key cannot be hung flexibly. Therefore, the BLE4.0, which is the low-power-consumption device, is dangle on the motorcycle's key and the RFID tags is installed on the bike's hidden body. The anti lost devices have been applied for responsibility of BLE-tags slave mode, installed on a key. The HM-11 BLE 4.0 module combination with an Arduino board has a function as the master mode, reading the MAC address (called ID) of BLE slave devices. The results show that the maximum distance, in which the BLE master module can detect the BLE slave's ID, is approximately 18 meters. The proposed method is reliable because the BLE devices can be hung on the key together while the motorbike is running on the speed not over than 80km/hr. Finally, the experimental results guarantee that, when relatively compared with the previous method, accuracy of the MATS is improved efficiently; moreover, this proposed system can actually be used in the real situation at the Prachinburi province, Thailand.","PeriodicalId":131543,"journal":{"name":"2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"60 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":"116132996","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

Quantitative study of facial expression asymmetry using objective measure based on neural networks 基于神经网络的客观测量面部表情不对称性定量研究

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824702

Tsuyoshi Makioka, Yuya Kuriyaki, K. Uchimura, T. Satonaka

引用次数: 3

Sound source tracking via two microphones based on MUSIC using PSO 基于PSO的MUSIC双麦克风声源跟踪

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824718

Kenta Omiya, K. Suyama

引用次数: 2

A 2nd-order Delta Sigma AD modulator using dynamic amplifier and dynamic SAR quantizer 采用动态放大器和动态SAR量化器的二阶Delta Sigma模数调制器

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824725

Chunhui Pan, H. San, Tsugumichi Shibata

引用次数: 8

An architecture design of SAD based template matching for fast queue counter in FPGA 基于模板匹配的快速队列计数器的FPGA结构设计

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824708

T. Adiono, Mahendra Drajat Adhinata, Novi Prihatiningrum, Ricky Disastra, Rachmad Vidya Wicaksana Putra, A. H. Salman

引用次数: 1

Simulation study for FFT-based Expand-Truncate equalizer under the measured outdoor channels 室外信道下基于fft扩展截断均衡器的仿真研究

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824756

Jia-Chyi Wu, Chi-Min Li, J. Huang

引用次数: 0

Automatic rule registration and deletion function on a packet lookup engine LSI 报文查找引擎LSI的规则自动注册和删除功能

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824693

T. Matsumura, K. Imamura, Yoshifumi Kawamura, Y. Matsuda

引用次数: 0

3D modeling based on multiple Unmanned Aerial Vehicles with the optimal paths 基于多架无人机最优路径的三维建模

2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2016-10-01 DOI: 10.1109/ISPACS.2016.7824715

Leye Wei, Xin Jin, Zhiyong Wu

{"title":"3D modeling based on multiple Unmanned Aerial Vehicles with the optimal paths","authors":"Leye Wei, Xin Jin, Zhiyong Wu","doi":"10.1109/ISPACS.2016.7824715","DOIUrl":"https://doi.org/10.1109/ISPACS.2016.7824715","url":null,"abstract":"Recently, advanced and automated devices are used for natural disasters project. Unmanned Aerial Vehicle (UAV) is considered as an advanced technology to be used in various areas where are hard for human to arrive at. This paper presents a novel method to build a 3D model of disaster areas based on multiple UAVs with the optimal paths. We divide disaster areas in-to key survey regions and normal survey regions based on partitioning the photo taken by a conventional satellite. Key survey regions which require a comprehensive survey contain much more complicated buildings and structures compared with those in normal survey regions. Some of the UAVs are used to comprehensively scan the key survey regions. The others are used to roughly scan the normal survey regions. All of the UAVs finish those scanning tasks in cooperation. A math model is built to find the optimal paths for multiple UAVs to scan the whole area with the minimum cost of time. The experimental results show that the number of photos reduces 41.07%, the scan time reduces 33.23% and the time consumed by building the 3D model reduces 38.75% compared with the other methods. To the best of our knowledge, the system is the first to use multiple UAVs to build 3D model.","PeriodicalId":131543,"journal":{"name":"2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"113 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":"121083454","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