Multimedia Systems Group

Tehrān, Iran

Multimedia Systems Group

Tehrān, Iran

Time filter

Source Type

Adeli-Mosabbeb E.,Iran University of Science and Technology | Fathy M.,Iran University of Science and Technology | Zargari F.,Multimedia Systems Group
Imaging Science Journal | Year: 2012

Automatic analysis of human motion includes initialisation, tracking, pose recoveryand activity recognition. In this paper, a computing framework is developed to automaticallyanalyse human motions through uncalibrated monocular video sequences. A model-basedkinematics approach is proposed for human gait tracking. Based on the tracking results, 3Dhuman poses and gait features are recovered and extracted. The recognition performance isevaluated by using different classifiers. The proposed method is advantageous in its capability ofrecognising human subjects walking non-parallel to the image plane. © RPS 2012.


Goudarzi P.,Multimedia Systems Group
International Journal of Communication Networks and Distributed Systems | Year: 2015

Ownership cost modelling and optimisation for any communication service is a challenging issue. In most previous researches, only the initial expenses are considered which are inefficient. In the current work, a more accurate cost modelling has been introduced that merges both the operational and capital costs to estimate total cost of ownership. A probabilistic approach based on stochastic optimisation theory has been devised. The mentioned approach takes into account the cost perturbations associated with constructing components of hierarchical video content delivery systems with unknown management costs. It is tried to validate the sensitivity, scalability and efficacy of the proposed method through parametric analysis and extensive simulations for different network topologies. The numerical results show the properties of the proposed model and compare it with other heuristics (such as nature-inspired gravitational search algorithm) and also the traditional methods. © Copyright 2015 Inderscience Enterprises Ltd.


Sheikhan M.,Islamic Azad University at South Tehran | Pezhmanpour M.,Islamic Azad University at South Tehran | Moin M.S.,Multimedia Systems Group
Neural Computing and Applications | Year: 2012

Steganography is the science of hiding information in a media such as video, image or audio files. On the other hand, the aim of steganalysis is to detect the presence of embedded data in a given media. In this paper, a steganalysis method is presented for the colored joint photographic experts group images in which the statistical moments of contourlet transform coefficients are used as the features. In this way, binary particle swarm optimization algorithm is also employed as a closed-loop feature selection method to select the efficient features in tandem with improvement of the detection rate. Nonlinear support vector machine and two variants of radial basis neural networks, i. e., radial basis function and probabilistic neural network, are used as the classification tools and their performance is compared in detecting the stego and clean images. Experimental results show that even for low embedding rates, the detection accuracy of the proposed method is more than 80% along with 30% reduction in the size of feature set. © 2011 Springer-Verlag London Limited.


Goudarzi P.,Multimedia Systems Group | Nezami Ranjbar M.R.,Multimedia Systems Group
Computers and Electrical Engineering | Year: 2011

Delivering digital video content with enhanced quality of experience to the end users over error-prone multi-hop wireless networks is a challenging issue. In video transmission over such wireless networks, many network-based (packet loss, delay, etc.) and source-based (encoding quantization level etc.) parameters can impose some levels of impairment on the perceived video quality. In a video quality enhancement strategy, accurate video quality metrics play a crucial role in the designing process of optimal rate (bandwidth) allocation algorithms. Many cross-layer optimization (CLO) based rate allocation strategies have been developed for this purpose which consider different objective functions (congestion level, total packet loss, etc.) in wireless networks. The main contributions of the proposed work are twofold. At first, an optimal bandwidth allocation framework is being developed in which based on some network-specific constraints and by incorporating an accurate video quality metric, the total weighted quality of experience of some competing video sources is being optimized bases on cross-layer design techniques. Secondly, these optimal rates have been used for differentiated Quality of Experience (QoE) enforcement between multiple competing video sources. The resulting optimal rates can be used as rate-feedbacks for on-line rate adaptation of a moderate video encoder such as MPEG4. The aforementioned weight parameters are selected based on the importance of each video sequence's quality and can be associated with some previous service level agreement (SLA) based prices. Some numerical analysis have been presented to validate the theoretical results and to verify the claims. © 2010 Elsevier Ltd. All rights reserved.


Goudarzi P.,Multimedia Systems Group
Wireless Communications and Mobile Computing | Year: 2013

In differentiated quality-of-experience enforcement (QoE) for video transmission over wireless networks, accurate video quality metrics play a crucial role in the designing process of optimal resource assignment algorithms. Many cross-layer optimization-based rate-allocation strategies, which consider different objective functions (congestion level, total packet loss, etc.), have been developed for this purpose. The main contributions of the proposed work are twofold. Firstly, an optimal resource assignment framework is being developed in which, based on some network-specific constraints and by incorporating appropriate video quality metrics, the total weighted QoE of some competing scalable video sources is being optimized based on cross-layer optimization techniques. Secondly, these optimal rates can be used for differentiated QoE enforcement between multiple competing scalable video sources. The resulting optimal rates can be considered as rate feedbacks for online rate adaptation of a moderate scalable video encoder such as H.264/MPEG-4 advanced video coding. The aforementioned weight parameters are selected based on the importance of each video sequence's quality and can be associated with some previous service level agreement-based prices. Some numerical analysis have been presented to validate the theoretical results and to verify the claims. Copyright © 2011 John Wiley & Sons, Ltd.


Goudarzi P.,Multimedia Systems Group
Journal of Mobile Multimedia | Year: 2011

Generally, real time applications needs different levels of the Quality of Service (QoS) which must be guaranteed by the underlying network infrastructure. Wireless Ad Hoc networks introduce many technological challenges in guaranteeing these stringent QoS requirements which must be addressed. Many optimization theoretic based bandwidth allocation strategies have been developed for guaranteeing some levels of QoS for some classes of competing real-time users in wireless ad hoc networks. The rapid increase in the development of different real-time applications with stringent maximum packet loss requirements in such environments and the existence of difficulties in satisfying the pre-specified QoS limits, is a great motivation for designing some type of differentiated QoS guaranteeing mechanisms that can satisfy the demands of this class of the real-time traffics. In the current work, a cross-layer optimization framework is being developed in which, based on the packet loss information from the lower layers, optimal bandwidths are assigned to the real-time applications which need some levels of the maximum packet loss guaranties. As, each real-time application needs a different level of maximum packet loss guarantee, a weighted aggregate packet loss objective function is being introduced. The weights are proportional with the importance of the packet loss mitigation for a specific application and may be associated with some negotiated Service Level Agreement (SLA). The simulation results verify the claims. © Rinton Press.


Goudarzi P.,Multimedia Systems Group | Hosseinpour M.,Multimedia Systems Group
IEEE Transactions on Consumer Electronics | Year: 2010

Quality of Experience (QoE) enhancement for a transmitted video sequence in Mobile Ad hoc NETworks (MANETs) is a challenging and important issue in networking research community. Intrinsic high levels of packet error probability in MANETs can cause high levels of distortion based on the position of packet loss in transmitted Intra-coded (I), Predicted (P) and Bi-predictive (B) frames. Hence, exact modeling of the impact of packet loss on the video quality and the resulting distortion is an important task. Many conventional distortion modeling techniques simply consider a linear relationship between the packet loss and distortion which is inaccurate. The main contributions of the current work are twofold. At first, an accurate model has been developed which can capture the exact effect of network packet loss on the video quality performance (and hence on the QoE) with Group Of Picture (GOP)-level granularity. Then, based on this model, an optimal bandwidth allocation strategy is being developed in MANETs which based on some network-specific constraints; the loss-induced distortion associated with a video source is being minimized using some cross-layer design techniques. Finally, the resulting optimal rates can be used as rate-feedbacks for on-line rate adaptation of an appropriate video encoder such as H.264/AVC. Numerical analysis has been presented to validate the theoretical results and to verify the claims. © 2006 IEEE.


Goudarzi P.,Multimedia Systems Group
International Journal of Computational Vision and Robotics | Year: 2015

Nature-inspired methods have attracted many attentions today for solving difficult and non-linear engineering problems. Some important examples include gravitational search algorithm (GSA), genetic algorithm (GA), DNA computing, artificial immune systems, fuzzy logic etc. Fair network resource allocation strategies are based on solving a form of constrained optimisation problem. There are plenty of high-speed fair rate allocation methods in the literature, some of them are based on fuzzy controllers for improving the convergence speed and are not necessarily optimal. Hence, in the current research, some recent important heuristics such as GA, GSA and their fuzzy-based counterparts have been used for finding the optimal allocated rates. Stability analysis is presented to guarantee the convergence property of the algorithm. After simulating, the results show that using the mixed fuzzy-GSA approach improves the conventional methods in convergence speed and results in fewer oscillations. Copyright © 2015 Inderscience Enterprises Ltd.

Loading Multimedia Systems Group collaborators
Loading Multimedia Systems Group collaborators