Abstract:
Method (10), in a system for aiding the guidance of a vehicle, for identifying marking stripes of road lanes comprising the phases of subjecting a road image to a convolution operation (14) with a mask matrix so as to identify discontinuities present in the image, comparing the result with a threshold value (16) and determining (18) a representation of the marking stripes, in which the mask matrix is set in such a way as to eliminate at least partially the discontinuities which do not correspond to the marking stripes.
Abstract:
The present invention relates to an analog voltage-signal selector device of the type comprising at least one plurality of comparator circuits (Ci) operating in parallel and each having at least a first and second input terminals and designed to receive respectively an analog voltage-comparison signal (RAMP) and analog voltage signals (Vi) of predetermined value and at least one output terminal for digital voltage signals (Voi). This selector device 1 also comprises at least one logic circuit (L) having a plurality of input terminals each connected to a corresponding output terminal of the comparator circuits (Ci) and at least one output terminal. Finally said selector 1 incorporates at least one plurality of latches (Mi) each having at least one input terminal connected to the output terminal of a corresponding comparator circuit (Ci) and at least one drive terminal coupled to the output terminal of the logic circuit (L) with each of said memory circuits (Mi) having at least one output terminal corresponding to an output of the selector.
Abstract:
An electronic device (100) for performing convolution operations comprises shift registers (106-120) for receiving binary input values (122-129) representative of an original matrix, synapses (142) for storing weights correlated with a mask matrix, and neurones (154, 156) for outputting (166, 168) a binary result dependent on the sum of the binary values weighted by the synapses (142), each synapse (142) having a conductance correlated with the weight stored and dependent upon the binary input value and each neurone (154, 156) generating the binary result in dependence on the total conductance of the corresponding synapses (142).
Abstract:
Method (10), in a system for aiding the guidance of a vehicle, for identifying marking stripes of road lanes comprising the phases of subjecting a road image to a convolution operation (14) with a mask matrix so as to identify discontinuities present in the image, comparing the result with a threshold value (16) and determining (18) a representation of the marking stripes, in which the mask matrix is set in such a way as to eliminate at least partially the discontinuities which do not correspond to the marking stripes.
Abstract:
The present invention relates to a digital-to-analog converter having a plurality of inputs (B0,B1,B2,B3) for digital signals, and an output (OUT) for an analog signal, and comprising a charge integration circuit (INT) having an input and an output coupled to the converter output, and a plurality of floating gate MOS transistors (M01, M11,M21,M31) corresponding to the plurality of converter inputs, having their source and drain terminals coupled all together and to the input (ND) of the integration circuit (INT), and having control terminals coupleable, under control from the inputs of the plurality, to different references (VCC,GND) of potential having selected fixed values.
Abstract:
Non-volatile memory cell with double level of polycrystalline silicon comprising a source region (38), a drain region (31), a channel region (34) between said source and drain regions, a floating gate (33), and a control gate (32) in which the channel region area extends into two lateral zones beneath the two gates and perpendicular to the source-drain direction.
Abstract:
A neural network (1) including a number of synaptic weighting elements (15, 17), and a neuron stage (5); each of the synaptic weighting elements (15, 17) having a respective synaptic input connection (11, 13) supplied with a respective input signal (x 1 , ..., x n ); and the neuron stage (5) having inputs (36, 37) connected to the synaptic weighting elements, and being connected to an output (39) of the neural network (1) supplying a digital output signal (O). The synaptic weighting elements (15, 17) are formed by memory cells programmable to different threshold voltage levels, so that each presents a respective programmable conductance; and the neuron stage (5) provides for measuring conductance (33-35, 43-45) on the basis of the current through the memory cells, and for generating a binary output signal on the basis of the total conductance of the synaptic elements.
Abstract:
The charge injection circuit of this invention comprises at least one pair of floating gate MOS transistors (M1,M2) having source and drain terminals which are coupled together and to an injection node (ND), and at least one corresponding pair of generators (G1,G2) of substantially step-like voltage signals (S1,S2) having an initial value and a final value, and having outputs respectively coupled to the control terminals of said transistors (M1,M2); the signal generators (G1,G2) being such that the initial value of a first (S1) of the signals is substantially the equal of the final value of a second (S2) of the signals, and that the final value of the first signal (S1) is substantially the equal of the initial value of the second signal (S2).