2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)最新文献

Effective monitoring of an air quality network 有效监察空气质素网络

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-05-23 DOI: 10.1109/ATSIP.2018.8364488

R. Baklouti, A. Hamida, M. Mansouri, M. Harkat, M. Nounou, H. Nounou

引用次数: 3

Ergodic capacity for fading channels in cognitive radio networks 认知无线电网络中衰落信道的遍历容量

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-03-22 DOI: 10.1109/ATSIP.2018.8364519

Raouia Masmoudi

{"title":"Ergodic capacity for fading channels in cognitive radio networks","authors":"Raouia Masmoudi","doi":"10.1109/ATSIP.2018.8364519","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364519","url":null,"abstract":"In this paper, we consider a Cognitive Radio (CR) system where two type of users try to access to the primary spectrum : a primary user (PU) owning the spectrum license and a secondary user (SU) who does not own the spectrum license. However, the secondary communication is allowed to coexist with the primary communication as long as the interference caused by SU to PU is below a tolerable threshold. We study the optimization problem which maximizes the SU's achievable ergodic capacity under different types of power constraints and for different fading channel models. Our goal is to calculate the optimal power allocation strategies for these optimization problems. We show that modelling with Rayleigh fading for the channel between SU transmitter and PU receiver is an advantageous way to ameliorate the SU ergodic capacity. Furthermore, we consider four combinations of power constraints, since the interference power constraint and the transmit power constraint can be restricted by a peak or an average threshold. We also show that the SU ergodic capacity under average transmit power constraint and average interference power constraint outperforms the one with peak power constraints. In this case, we propose a novel decoupling method. Our method reduces the complexity of the initial problem and makes our initial problem easier to solve.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124748957","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 computer vision system to detect diving cases in soccer 一种检测足球假摔的计算机视觉系统

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-03-21 DOI: 10.1109/ATSIP.2018.8364457

Hana' Al-Theiabat, Inad A. Aljarrah

{"title":"A computer vision system to detect diving cases in soccer","authors":"Hana' Al-Theiabat, Inad A. Aljarrah","doi":"10.1109/ATSIP.2018.8364457","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364457","url":null,"abstract":"Recently, motion analysis systems have been getting a lot of attention due to their potential in human motion analysis, which has a wide range of applications. One of these applications is analyzing tackle scenes in soccer games. In a tackle scene, players occasionally tend to deceive the referee by intentionally falling to get a free or penalty kick. In this paper, we propose a system to program human body tracking in order to analyze tackle scenes in soccer games. The main idea behind this system is to determine whether the falling player in the tackle scene is attempting to deceive the referee (diving) or not. In this system, the tackle scene goes through five main stages of processing; identification of the falling player, extraction of tracking points, motion tracking, features extraction and scene classification. The tracking component is implemented using Kanade-Lucas-Tomasi optical flow with the aid of pyramid levels and forward-backward error algorithm, while the classification is carried out using Weka software with Naive Bayes tree (NB tree) classifier. The proposed system is implemented and its performance is experimentally tested. The results show a potential to detect diving cases (deceiving in falling), with a classification accuracy of 84%.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129889941","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

Long-term superpixel tracking using unsupervised learning and multi-step integration 使用无监督学习和多步集成的长期超像素跟踪

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-03-21 DOI: 10.1109/ATSIP.2018.8364453

Pierre-Henri Conze, F. Tilquin, M. Lamard, F. Heitz, G. Quellec

引用次数: 1

Efficient image texture and structure preservation via a Rapid diffusion function with accelerator 有效的图像纹理和结构保存通过快速扩散功能与加速器

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-03-21 DOI: 10.1109/ATSIP.2018.8364526

S. Tebini, H. Seddik, E. B. Braiek

引用次数: 3

Feature selection and classification using multiple kernel learning for brain tumor segmentation 基于多核学习的脑肿瘤分割特征选择与分类

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-03-21 DOI: 10.1109/ATSIP.2018.8364470

Naouel Boughattas, Maxime Bérar, K. Hamrouni, S. Ruan

引用次数: 9

Electromagnetic study of the breast for biomedical applications 用于生物医学应用的乳房电磁研究

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-03-21 DOI: 10.1109/ATSIP.2018.8364478

Marwa Slimi, P. Mendes, B. Jmai, A. Gharsallah

引用次数: 2

Towards change detection in bi-temporal images using evidential conflict 基于证据冲突的双时相图像变化检测研究

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-03-21 DOI: 10.1109/ATSIP.2018.8364335

Fatma Haouas, Z. B. Dhiaf, A. Hammouda, B. Solaiman

引用次数: 4

State-of-the-art face recognition performance using publicly available software and datasets 最先进的面部识别性能使用公开可用的软件和数据集

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-03-21 DOI: 10.1109/ATSIP.2018.8364450

Mohamed Amine Hmani, D. Petrovska-Delacrétaz

{"title":"State-of-the-art face recognition performance using publicly available software and datasets","authors":"Mohamed Amine Hmani, D. Petrovska-Delacrétaz","doi":"10.1109/ATSIP.2018.8364450","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364450","url":null,"abstract":"We are interested in the reproducibility of face recognition systems. By reproducibility we mean: is the scientific community, and are the researchers from different sides, capable of reproducing the last published results by a big company, that has at its disposal huge computational power and huge proprietary databases? With the constant advancements in GPU computation power and availability of open-source software, the reproducibility of published results should not be a problem. But, if architectures of the systems are private and databases are proprietary, the reproducibility of published results can not be easily attained. To tackle this problem, we focus on training and evaluation of face recognition systems on publicly available data and software. We are also interested in comparing the best Deep Neural Net (DNN) based results with a baseline “classical” system. This paper exploits the OpenFace open-source system to generate a deep convolutional neural network model using publicly available datasets. We study the impact of the size of the datasets, their quality and compare the performance to a classical face recognition approach. Our focus is to have a fully reproducible model. To this end, we used publicly available datasets (FRGC, MS-celeb-lM, MOBIO, LFW), as well publicly available software (OpenFace) to train our model in order to do face recognition. Our best trained model achieves 97.52% accuracy on the Labelled in the Wild dataset (LFW) dataset which is lower than Google's best reported results of 99.96% but slightly better than FaceBook's reported result of 97.35%. We also evaluated our best model on the challenging video dataset MOBIO and report competitive results with the best reported results on this database.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131425313","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: 9

A real-time emotion recognition system for disabled persons 面向残疾人的实时情感识别系统

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) Pub Date : 2018-03-21 DOI: 10.1109/ATSIP.2018.8364339

Y. Rabhi, M. Mrabet, F. Fnaiech, M. Sayadi

引用次数: 6