1,721,116 research outputs found
Fast and robust Face Detection
No full textThis chapter presents a fully automatic face detection system robust to moderate change in expression, posture and illumination. The final goal of this detection is to initialize a 3D face tracking, therefore is specialized for working on videos of good quality instead of still images. More in details we present two different face detection strategy based on slightly modified largely used Viola-Jones [1] object detector
InTERPRET: Multimedia techniques for augmEnted Reality: PResence and Emotion in virtual environmenT
No full text
A certification-based trust model for autonomic cloud computing systems
No full textAutonomic cloud computing systems react to events and context changes, preserving a stable quality of service for their tenants. Existing assurance techniques supporting trust relations between parties need to be adapted to scenarios where the assumption of responsibility on trust assertions and related information (e.g., in SLAs and certificates) cannot be done at a single point in time and by a single trusted third party. In this paper, we tackle this problem by proposing a new trust model grounded on a security certification scheme for the cloud. Our model is based on a multiple signatures process including dynamic delegation mechanisms. Our approach supports autonomic cloud computing systems in the management of dynamic content in security certificates, establishing a trustworthy cloud environment
Accurate 3D model based face tracking for facial expression recognition
No full textThe recovery of the 3-D movement of the face is an important operation for many applications like human machine interaction, video surveillance, MPEG-4 compression etc.
This paper presents a method to obtain from a video input, a normalized face in a frontal pose, by recovering the fullmotion
of the head using 3D head model. From some characteristic face points given on the first frame, an approximated 3D model of the face is reconstructed. Using this model, the full motion of the head is computed automatically.
Evidently, in order to compensate errors due to the rough 3D model, a combination of several techniques has been used to reach a strong robustness. The algorithm has
been tested on synthetic videos and it has been compared with a standard multi-camera system for the 3D tracking (Elite 2002 System). The results in both cases are good.
The proposed approach is part of a facial expression analysis system. Our aim is to detect the facial expression in situations characterized by a moderate head motion. For
this reason head motion recovering is fundamental. Once recovered the pose, we are able to obtain frontal normalized facial image that makes expression analysis easier
Upper-face expression features extraction system for video sequences
No full textNowadays there are not any reliable systems able to codify a video streaming according to the FACS. The few system that are able to do it works on frontal, or however not natural postures. The system we propose, takes advantage from a robust 3D tracking based on a 3D template, in order to
extract some features correlated to the facial expressions.
Moreover, this system provides for each feature a reliability level according to the presence of some occlusions, or due to some errors in tracking that could hide or make the reconstruction on the template, become critical
Localization and tracking of mobile antenna in urban environment
No full textIn mobile communication, many new services rely on the knowledge of mobile terminals location.
Mobile units location estimate is aimed at using the cellular network infrastructure and protocols to provide a reliable and accurate estimate of mobile terminals positions without the need for global
positioning systems such as GPS. In this paper a lookup table correlation techniques with multiple position estimation and optimal location is presented. The approach is based on advanced propagation models, designed for planning of mobile radio networks and on information that can be extracted from a GIS map of the interested
area in conjunction with Kalman prevision
filtering to improve precision in location and tracking
Fuzzy rule-based edge-restoration algorithm in HDTV interlaced sequences
No full textThis paper proposes an interpolation algorithm for conversion from the interlaced to the progressive scanning format. The proposed algorithm consists of two parts: an edge direction detection part and a fuzzy rule-based edge-restoration interpolation part. The different types of edge, peak, and monotonic slope patterns are considered in a spatial domain interpolation strategy. Edges with a certain vertical component look preserved in the interpolation using a fuzzy rule-based algorithm. The vertical resolution in the interpolated image is subjectively concealed by introducing vertical gradients in the interpolation. Computer simulations verify the effective performance of this image processing technology
Advanced localization of mobile terminal in cellular network
No full textThe growing diffusion of pervasive collaboration environments and technical advancement of sensing technologies have fostered the development of a new wave of online services whose functionalities are based on users’ physical position. Thanks to the widespread diffusion of mobile devices (e.g. cell phones), many services can be greatly enriched with data reporting where people are, how they are moving, or whether they are close by specific locations. Geolocation of mobile terminals relies on the cellular network infrastructure and protocols to provide a reliable and accurate estimate of mobile terminals’ position, without the need of global positioning systems, such as GPS. In this paper, we present a novel lookup table correlation technique for geolocation, with multiple position estimations and optimal location techniques. Our approach provides high precise location and tracking of mobile terminals by exploiting advanced propagation models for mobile radio networks design, and by querying Geographical Information Systems (GIS), in conjunction with Kalman predictive filtering
A semi-automatic and trustworthy scheme for continuous cloud service certification
Full text linkTraditional assurance solutions for software-based systems rely on static verification techniques and assume continuous availability of trusted third parties. With the advent of cloud computing, these solutions become ineffective since services/applications are flexible, dynamic, and change at run time, at high rates. Although several assurance approaches have been defined, cloud requires a step-change moving current assurance techniques to fully embrace the cloud peculiarities. In this paper, we provide a rigorous and adaptive assurance technique based on certification, towards the definition of a transparent and trusted cloud ecosystem. It aims to increase the confidence of cloud customers that every piece of the cloud (from its infrastructure to hosted applications) behaves as expected and according to their requirements. We first present a test-based certification scheme proving non-functional properties of cloud-based services. The scheme is driven by non-functional requirements defined by the certification authority and by a model of the service under certification. We then define an automatic approach to verification of consistency between requirements and models, which is at the basis of the chain of trust supported by the certification scheme. We also present a continuous certificate life cycle management process including both certificate issuing and its adaptation to address contextual changes. Finally, we describe our certification framework and an experimental evaluation of its performance, quality, applicability, and practical usability in a real industrial scenario, which considers Engineering Ingegneria Informatica S.p.A. ENGpay online payment system
- …
