Gianluca Gera

Advanced image-processing tools for counting people in tourist site-monitoring applications

This work aims at demonstrating the usefulness of exploiting novel image-processing tools for moving-object detection and classification in the context of an actual application involving the remote monitoring of a tourist site. The application concerns outdoor people counting for tourist-flow estimation in a constrained environment. The technical problems to be solved are concerned with: (a) the design and implementation of low-complexity background updating and change detection algorithms able to adapt themselves to the time-varying illumination scene conditions, and (b) the integration of real-time pattern-recognition tools in order to distinguish group of persons to be counted from other objects present in the scene. The achieved results have proven that the proposed system makes it possible to obtain reliable people counting in different environmental situations, with an absolute mean error at most equal to 10%.

Color-based video stabilization for real-time on-board object detection on high-speed trains

This paper is concerned with a particular application of image stabilization. Image stabilization is a necessary step to reduce the effect of camera motion when, as in this case, image sequences are acquired from a mobile platform. In this work, in order to find an efficient motion estimator, two one-dimensional characteristic curves are extracted from each video frame. Such curves are then compared in consequent frames to estimate image displacement. The proposed algorithm is suitable for real time processing and provides good performance; in order to verify its validity, it has been tested on a variety of color video-sequences taken from the point of view of trains moving along railways tracks. Results are provided in order to compare the proposed approach with a feature-based stabilization method.

A New Method for Real Time Abandoned Object Detection and Owner Tracking

In this paper, a surveillance system able at detecting abandoned objects automatically is proposed. In particular the implemented system aims at detecting the presence of abandoned objects or in a guarded indoor environment and at tracking the owner while he is in the scene and advise if another person take the abandoned object instead of the owner.

W‐band physical layer design issues in the context of the DAVID–DCE experiment

This paper aims at focusing on the aspects concerning the physical layer design for an innovative satellite communication experiment. Such an experiment, denoted by the acronym DAVID–DCE (Data and Video Interactive Distribution—Data Collection Experiment) is based on the exploitation of the W-band (75–110 GHz) for high-bit-rate satellite transmission. The potential advantages of using of the W-band are mainly related to the great bandwidth availability, and to the absence of interference. Moreover, an expected result of the experiment is a substantive improvement in the communication systems performances in the presence of meteorological phenomena (e.g. rain) as compared with the more conventional Ka-band satellite transmission. On the other hand, problems to be faced concern the non-ideal behaviours of hardware devices employed for high-frequency digital transmission. In particular, carrier recovery and timing recovery are the most crucial signal-processing tasks to be carefully considered in the design of the physical level of the system, because they considerably suffer from hardware impairments. The purpose of this work is to illustrate the proposed solutions in terms of the most critical modulation, demodulation and synchronization design issues, together with the effects of non-ideal behaviours of hardware components on BER performances. Copyright

An efficient carrier recovery scheme for high-bit-rate W-band satellite communication systems

Recent efforts in satellite communication research considered the exploitation of higher frequency bands as a valuable alternative to conventional spectrum portions. An example of this can be provided by the W-band (70-110 GHz). Recently, a scientific experiment carried on by the Italian Space Agency (ASI), namely the DAVID-DCE experiment, was aimed at exploring the technical feasibility of the exploitation of the W-band for broadband networking applications. Some preliminary results of DAVID research activities pointed out that phase noise and high Doppler-shift can severely compromise the efficiency of the modulation system, particularly for what concerns the aspects related to the carrier recovery. This problem becomes very critical when the use of spectrally efficient M-ary modulations is considered in order to profitably exploit the large amount of bandwidth available in the W-band. In this work, a novel carrier recovery algorithm has been proposed for a 16-QAM modulation and tested, considering the presence of phase noise and other kinds of non-ideal behaviors of the communication devices typical of W-band satellite transmission. Simulation results demonstrated the effectiveness the proposed solution for carrier recovery and pointed out the achievable spectral efficiency of the transmission system, considering some constraints about transmitted power, data BER and receiver bandwidth

Performance evaluation of MC-CDMA techniques for variable bit-rate transmission in LEO satellite networks

This work is aimed at investigating the use of multi-carrier CDMA (MC-CDMA) techniques in variable bit-rate transmission over low-earth-orbit (LEO) satellite channels by means of realistic simulations. It is known from the literature that MC-CDMA techniques are much more resilient with respect to multi-user interference effects in multipath fading channels than single-carrier DS/CDMA ones. Moreover, MC-CDMA exhibits a natural capability to deliver multirate services simply by assigning to each user a variable-cardinality set of subcarriers. The achieved simulation results clearly confirmed the expected improved robustness of MC-CDMA techniques transmitting multirate data streams in frequency selective LEO satellite channels, with respect to state-of-the-art DS/CDMA transceivers.

Early fire and smoke detection based on colour features and motion analysis

This work addresses the issue of fire and smoke detection in a scene within a video surveillance framework. Detection of fire and smoke pixels is at first achieved by means of a motion detection algorithm. In addition, separation of smoke and fire pixels using colour information (within appropriate spaces, specifically chosen in order to enhance specific chromatic features) is performed. In parallel, a pixel selection based on the dynamics of the area is carried out in order to reduce false detection. The output of the three parallel algorithms are eventually fused by means of a MLP.

Neural network-based techniques for efficient detection of variable-bit-rate signals in MC-CDMA systems working over LEO satellite networks

For a few years, multicarrier modulations have been proposed as valuable alternatives with respect to state-of-the-art single carrier ones due to their resilience against interference and channel distortion effects. In particular, many studies are arising about multicarrier-CDMA (MC-CDMA) techniques that provide improved robustness and flexibility with respect to single-carrier spread-spectrum techniques. Satellite communications considered the employment of MC-CDMA for multimedia transmission very recently, especially for what concerns the delivery of variable-bit-rate services over low-earth-orbit (LEO) satellite networks. To this aim, the problems to be faced are mainly related to the development of efficient methodologies for satellite channel estimation, equalization and multi-user detection, in order to exploit in an optimal way the natural diversity inherent to MC-CDMA. In this paper we compare two different neural-network-based approaches for efficient reception of MC-CDMA signals in the case of asynchronous, multi-user, and variable-bit-rate transmission over LEO satellite channels. The first approach introduces neural networks for supporting receiver decision. The second more sophisticated approach exploits neural networks for joint channel estimation and symbol detection. Simulation results will be presented that demonstrate the improved effectiveness of the proposed methodologies, with respect to state-of-the-art MC-CDMA detection techniques, both in terms of reduced BER and in terms of low computational complexity.

Use of intelligent sensors and software radio technologies for optimal design of reconfigurable multimedia surveillance networks

In these last years, the increasing request for security coming from civil society led to intensive exploitation of the most advanced technological tools for solving problems related to remote monitoring of public sites. New-generation multimedia surveillance systems will be characterized by such key topics as distribution of processing capabilities among intelligent sensor and central processing levels, and dynamic reconfigurability of the wireless links thanks to innovative software radio technologies. In this work a joint analysis of such aspects is presented in order to provide optimal design strategies for new-generation multimedia surveillance networks, able to take into account the trade-offs between available computing and communications resources and required performance in terms of correct event detection and real-time processing.

A novel method for graffiti detection using change detection algorithm

In recent decades vandal acts and graffiti drawing problem have increased and have required a lot of public funding. To face this problem the communal administrations have invested in automatic video surveillance systems. To deal with this problem through image processing techniques, this paper presents a method for graffiti detection based on change detection algorithm and motion vector. The aim of this system is to detect the graffiti painting act while people are going to draw, identify them and distinguish the drawer.