US 12,437,501 B2
Process for monitoring at least one element in a temporal succession of physical signals
Pierre Demaj, Nice (FR); and Laurent Folliot, Gourdon (FR)
Assigned to STMicroelectronics (Rousset) SAS, Rousset (FR)
Filed by STMicroelectronics (Rousset) SAS, Rousset (FR)
Filed on Oct. 18, 2022, as Appl. No. 17/968,148.
Claims priority of application No. 2111302 (FR), filed on Oct. 25, 2021.
Prior Publication US 2023/0131838 A1, Apr. 27, 2023
Int. Cl. G06V 10/62 (2022.01); G06V 10/44 (2022.01)
CPC G06V 10/62 (2022.01) [G06V 10/454 (2022.01); G06F 2218/02 (2023.01); G06F 2218/08 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
determining a probability of a presence of a feature to be tracked in a physical signal in a time sequence of physical signals using an artificial neural network having a single weight set, the physical signal being an input to the artificial neural network and capable of having different resolutions;
executing the artificial neural network in a nominal mode of operation in response to the probability of the presence of the feature being less than a threshold, the physical signal in the nominal mode being a physical signal having a nominal resolution;
executing the artificial neural network in an accelerated process mode of operation in response to the probability of the presence of the feature being greater than the threshold, a processing rate of the physical signal is increased in the accelerated process mode in comparison to the nominal mode, the physical signal in the accelerated process mode being a physical signal having a reduced resolution lower than the nominal resolution; and
tracking the feature in the time sequence of physical signals based on output data generated by executing the artificial neural network in the accelerated process mode.