We demonstrate the channel assignment in a metropolitan wireless multi-radio mesh network with directional antennas. A channel assignment approach is presented using suitable algorithms with key components the interference model, the link ordering and the channel selection metric. We have implemented and evaluated the proposed channel assignment in an actual metropolitan mesh network which covers an area of 60 km2in the city of Heraklion and consists of 14 nodes, among which seven are core nodes with up to four 802.11a wireless interfaces each, and one for management and monitoring. Finally, we developed a Java application to demonstrate the channel assignment process in a metropolitan mesh network in a graphical environment.

We investigate the problem of channel assignment in a metropolitan wireless multi-radio mesh network with directional antennas. We first present a new conflict graph model for capturing the interference between links in a mesh network with a known wireless interface communication graph. Then we present a channel assignment procedure which accounts for interference both between links internal to the mesh network, and from external sources. Key components of the channel assignment procedure are the interference model, the link ordering, and the channel selection metric. We have implemented and evaluated the proposed channel assignment procedure in an actual metropolitan mesh network with link distances from 1.6 to 5 Km. The experimental results demonstrate how link ordering and the channel selection metric affect performance, in terms of the average packet delay and http latency. Moreover, the experimental results show that the proposed channel assignment procedure achieves performance that is within approximately 11% of a lower bound of the average packet delay, and significantly higher than the performance achieved with a simpler interference-unaware procedure.

A key question in video indexing is the effective use of all the possible sources of information. Hidden Markov models (HMM) and segment models (SM) provide powerful frameworks for audiovisual integration and structure knowledge encoding. However, incorporating punctual symbolic information, such as inlaid score labels, with these models is not straightforward. We demonstrate that using the score labels as an additional feature is not efficient and propose a novel algorithm to efficiently incorporate the score information in the Viterbi decoding process. This score oriented Viterbi search guarantees an optimal solution consistent with the available score information. Experimental results demonstrate the effectiveness of the method and its robustness to inlaid score detection errors

Efficient multimodal fusion is a key feature of future video indexing systems. Hidden Markov models provide a powerful framework for video structure analysis but they require all video modalities to be strictly synchronous. Taking as a case study tennis broadcasts analysis, we introduce into video indexing segment models, a generalization of hidden Markov Models, where the fusion of different modalities can be performed with relaxed synchrony constraints. Segment models were experimentally proved to perform marginally better compared to hidden Markov models

In this paper, we present a novel face detection approach based on a convolutional neural architecture, designed to robustly detect highly variable face patterns, rotated up to +/-20 degrees in image plane and turned up to +/-60 degrees, in complex real world images. The proposed system automatically synthesizes simple problem-specific feature extractors from a training set of face and nonface patterns, without making any assumptions or using any hand-made design concerning the features to extract or the areas of the face pattern to analyze. The face detection procedure acts like a pipeline of simple convolution and subsampling modules that treat the raw input image as a whole. We therefore show that an efficient face detection system does not require any costly local preprocessing before classification of image areas. The proposed scheme provides very high detection rate with a particularly low level of false positives, demonstrated on difficult test sets, without requiring the use of multiple networks for handling difficult cases. We present extensive experimental results illustrating the efficiency of the proposed approach on difficult test sets and including an in-depth sensitivity analysis with respect to the degrees of variability of the face patterns.