Abstract: A computer-implemented method of forecasting the semantic output of at least one frame, the method comprising the steps of receiving the input frames from a camera up to a predetermined time, processing via a down-sampling module of a neural network the plurality of input frames to receive a plurality of feature tensors, determining spatio-temporal correlations between the plurality of feature tensors, processing the plurality of feature tensors and the spatio-temporal correlations to receive at least one forecasted feature tensor, and processing via an up-sampling module of the neural network the at least one forecasted feature to receive at least one forecasted semantic output for a time larger than the predetermined time.

Abstract: A computer-implemented method of forecasting the semantic output of at least one frame, the method comprising the steps of receiving the input frames from a camera up to a predetermined time, processing via a down-sampling module of a neural network the plurality of input frames to receive a plurality of feature tensors, determining spatio-temporal correlations between the plurality of feature tensors, processing the plurality of feature tensors and the spatio-temporal correlations to receive at least one forecasted feature tensor, and processing via an up-sampling module of the neural network the at least one forecasted feature to receive at least one forecasted semantic output for a time larger than the predetermined time.

Abstract: A system comprises a microphone unit to be mounted in a first vehicle, which receives an audio signal from outside the first vehicle, processes the audio signal and outputs a microphone signal, a storage unit which stores a database containing, for each siren signal pattern of a plurality of siren signal patterns sounded by second vehicles, components of sparse models respectively corresponding to the plurality of siren signal patterns, and an identifying unit which matches the microphone signal with the components of the sparse models, and detects, based on a result of the matching, at least one of the second vehicles sounding a siren signal pattern of the plurality of siren signal patterns. According to an embodiment, the system further comprises a localizing unit which localizes the at least one second vehicle based on differences between timings of at least three microphone signals output from the microphone unit.

Abstract: A voice processing device includes plural microphones 22 disposed in a vehicle, a voice source direction determination portion 16 determining a direction of a voice source by handling a sound reception signal as a spherical wave in a case where the voice source serving as a source of a voice included in the sound reception signal obtained by each of the plural microphones is disposed at a near field, the voice source direction determination portion determining the direction of the voice source by handling the sound reception signal as a plane wave in a case where the voice source is disposed at the far field, and a beamforming processing portion 12 performing beamforming so as to suppress a sound arriving from a direction range other than a direction range including the direction of the voice source.

Abstract: A biological parameter of a subject is estimated, which is present on a support, the support comprising at least two sensors each measuring a variation of pressure, wherein at least one accelerometer is connected to the support. A sensor-specific model is provided for each of the at least two sensors based on signals from the at least two sensors, the signals corresponding to the variation of pressure measured by the at least two sensors, respectively. In a selection process, at every time frame T, one sensor is selected out of the at least two sensors, to be used for estimating the biological parameter of the subject, based on signals from the at least one accelerometer. In an estimation process, the biological parameter of the subject is estimated using, at every time frame T, the sensor-specific model provided for the selected one sensor.

Abstract: A system comprises a microphone unit to be mounted in a first vehicle, which receives an audio signal from outside the first vehicle, processes the audio signal and outputs a microphone signal, a storage unit which stores a database containing, for each siren signal pattern of a plurality of siren signal patterns sounded by second vehicles, components of sparse models respectively corresponding to the plurality of siren signal patterns, and an identifying unit which matches the microphone signal with the components of the sparse models, and detects, based on a result of the matching, at least one of the second vehicles sounding a siren signal pattern of the plurality of siren signal patterns. According to an embodiment, the system further comprises a localizing unit which localizes the at least one second vehicle based on differences between timings of at least three microphone signals output from the microphone unit.

Abstract: A noise removal device which removes noise included in a signal, includes: a statistical parameter calculation portion configured to calculate a parameter which expresses distribution of the noise based on the signal; and a noise removal portion configured to remove the noise from the signal by changing an element which relates to a process of removing the noise from the signal depending on the parameter which expresses the distribution of the noise.

Abstract: One embodiment of the present invention provides a transceiver for power line communication, including: a transmission unit configured to transmit a signal; and a reception unit configured to estimate characteristics of a transmission path. Further, another embodiment of the present invention provides a power line communication method, including the steps of: estimating transmission path characteristics; generating an interference avoiding mask based on interference of the estimated transmission path characteristics; selecting or cancelling, through use of the interference avoiding mask, a sub-carrier of a signal to be transmitted; and transmitting the signal.

Abstract: A device for electromagnetic noise reduction in a hybrid automotive vehicle includes at least one sensor that measures a conducted noise generated by at least one noise source, a reducer that reduces a radiated noise, referred to as modified, on a signal of interest made noisy by the modified radiated noise, where the reducer includes a determiner that determines the noise corrected signal of interest from a noisy signal of interest, where the determiner includes an estimator that estimates the modified radiated noise from the conducted noise, and a selector that selects a frequency for receiving a radiofrequency signal.

Abstract: A noise removal device which removes noise included in a signal, includes: a statistical parameter calculation portion configured to calculate a parameter which expresses distribution of the noise based on the signal; and a noise removal portion configured to remove the noise from the signal by changing an element which relates to a process of removing the noise from the signal depending on the parameter which expresses the distribution of the noise.

Abstract: Device for electromagnetic noise reduction in a hybrid automotive vehicle (12) comprising: at least one sensor (44A, 44B) for measurement of the conducted noise (BC,A, BC,B) generated by at least one noise source (18, 20); a reduction unit (33) for a radiated noise (Bim,A, Bim,B), referred to as modified, on a signal of interest (S2) made noisy by the modified radiated noise (Bim,A, Bim,B), where the reduction unit (33) includes means for determination of the noise corrected signal of interest from the noisy signal of interest (S2), where the means of determination include means for estimation of the modified radiated noise (Bim,A, Bim,B) from the conducted noise (BC,A, BC,B).

Abstract: A method for monitoring a biological parameter out of either the heartbeat and/or respiratory signal of an occupant on a member of a seat or bed, wherein a signal or signals received from one or a plurality of sensors connected to the member and capable of detecting the variation of pressure due to contact are processed by non-linear filtering. For example, the method is mounted on a vehicle and used. Also provided is a computer program including code instructions capable of controlling execution of the method of the invention when the method is executed by a computer. Further provided is a monitoring device for monitoring a biological parameter out of either the heartbeat and/or respiratory signal of an occupant on a member of a seat or bed.

Abstract: A method for monitoring a biological parameter out of either the heartbeat and/or respiratory signal of an occupant on a member of a seat or bed. The member supports sensors, receives the signal from each of the group of sensors, inputs the signal into an atom dictionary, selects some sensors according to the input, and performs monitoring using only the selected sensors. Also provided is a computer program including code instructions capable of controlling execution of the method of the invention when the method is executed by a computer. Further provided is a monitoring device for monitoring a biological parameter out of either the heartbeat and/or respiratory signal of an occupant on a member of a set or bed.

Abstract: A method for monitoring a biological parameter out of either the heartbeat and/or respiratory signal of an occupant on a member of a seat or bed. The member supports at least one sensor capable of detecting variation of pressure due to contact, and at least one accelerometer is connected to the member. A model of a transfer function between at least one signal from one accelerometer out of either the accelerometer and/or at least one accelerometer at the input and a signal from a sensor out of either the sensor and/or a plurality of sensors at the output is made, a noise value is estimated using this model, and the estimated noise value is removed from the signal from the sensor.