Low-power always-on face detection, tracking, recognition and/or analysis using events-based vision sensor

An apparatus for determining object detection events, the apparatus comprising:

• a sensor array comprising more than one sensor pixel;
• dedicated computer vision (CV) computation hardware capable of receiving sensor data from the sensor array and computing CV features using readings from neighboring sensor pixels of the sensor array;
• a classifier configured to receive an output of the dedicated CV computation hardware and perform operations based on the one or more computed CV features;
• and
• a first processing unit configured to:
• determine, from an output of the classifier resulting from performing the operations based on the one or more computed CV features that an object has been detected, and
• in response to the determination, generate an object-detected event to be received by a second processing unit and configured to trigger an operation to be performed by the second processing unit.

A method for sensing dynamic scene-based occurrences with an apparatus, the method comprising:

• receiving, with dedicated computer vision (CV) computation hardware, sensor data from a sensor array comprising more than one sensor pixel;
• computing, with the dedicated CV computation hardware, one or more CV features using readings from neighboring sensor pixels of the sensor array;
• performing, with a classifier, operations based on the one or more computed CV features;
• processing, with a first processing unit, an output of the classifier resulting from performing the operations based on the one or more computed CV features;
• and
• generating an event to be received by a second processing unit in response to the processing of the output of the classifier by the first processing unit, the event configured to trigger an operation to be performed by the second processing unit and indicating a reference occurrence for the second processing unit.

A method for determining object detection events, the method comprising:

• receiving, with dedicated computer vision (CV) computation hardware, sensor data from a sensor array;
• computing one or more CV features using readings from neighboring sensor pixels of the sensor array;
• performing, with a classifier, operations based on the one or more computed CV features;
• and
• using a first processing unit to:
• determine, from an output of the classifier resulting from performing the operations based on the one or more computed CV features that an object has been detected, and
• in response to the determination, generate an object-detected event to be received by a second processing unit and configured to trigger an operation to be performed by the second processing unit.