Alcatel

Fabio Valente

Silvio Cucchi

Ludovic Noirie

Georg Post

To selectively route stand-by packets in input modules to destination output modules via a switching matrix, distributed arbitration functions are executable by successive arbitration cycles. Each cycle comprises: a first phase executable by each input controller to send each output controller requests representative of the quantities of required stand-by packets; a second phase executable by each output controller to determine the quantity of admissible packets depending on the requests; a third phase executable by a central arbitration unit to determine allowed aggregate quantities depending on all the admissible quantities; and a fourth phase executable by each input controller to determine the allowed packet quantities depending on the admissible quantities and of the allowed aggregate quantities.

Packet-switched system for communication network node

In order to switch selectively via a packets switching matrix waiting in the input modules (IMi) to address output modules, an arbitration function (CSC) selects by successive cycles, from all the pairs of input and output modules, separate subsets. Each cycle comprises p successive phases (x) associated respectively to p arbitration functions. Processing units (PUi) each execute the p functions, each function acting on three parameters termed 'residual required quantity', 'input capacity' and &#x201c;output capacity&#x201d;, the values of which are related to a single pair and are set at the start of the cycle. Each phase consists of N successive steps (y) associated respectively to said subsets, each step being executed in parallel by the processing units (PUi) in order to calculate by means of the arbitration functions the &#x201c;partial&#x201d; accepted quantity values and to reset the parameters for the next step. Application to telecommunication networks, particularly multiservice.

Packets switching system for telecommunications network node

A method is described for estimating the motion for image sequences carrying out a decimation of the function used for the extraction of the characteristic parameters of an image block. The method is iterated by decreasing the function decimation and carrying out the block-matching on a set of the best matchings of the preceding steps. The method does not require the recalculation of the parameters on the reference image for each block to be matched; moreover, in the extraction of the characteristic parameters of a block, the use of the Integral Projections is not mandatory but one of the possible variants only (FIG. 1).

Growing community of inventors

Lonigo, Italy

Fabio Valente