Distributed Camera System

A system, comprising:

• a central station coupled with a communications network connected to a plurality of cameras installed at a plurality of locations respectively, wherein each respective camera in the plurality of cameras has:
• a non-volatile memory to store first data representative of images captured by the respective camera;
• and
• a logic circuit configured to perform matrix computations;
• wherein the central station is configured to transmit, to the plurality of cameras via the communications network, second data representative of an item model;
• wherein when the item model is stored in the respective camera, the logic circuit is configured to perform computations of a first artificial neural network using the first data as an input and to generate an output of the first artificial neural network, the output having a classification of whether the images are relevant to an item of interest characterized by the item model;
• and
• wherein in response to the output having a first classification that the images are relevant to the item of interest, the respective camera is configured to transmit a report including the images, via the communications network, to the central station.

A method, comprising:

• communicating, by a central station over a communications network with a plurality of cameras configured at a plurality of locations respectively, wherein each respective camera in the plurality of cameras has:
• a non-volatile memory to store first data representative of images captured by the respective camera;
• and
• a logic circuit configured to perform matrix computations;
• generating, by the central station, an item model configured, when stored in a random access memory of the respective camera, to cause the logic circuit to perform computations of a first artificial neural network using the first data as an input and to generate an output of the first artificial neural network, the output having a classification of whether the images are relevant to an item of interest characterized by the item model;
• transmitting, by the central station, to the plurality of cameras via the communications network, second data representative of the item model to cause the item model to be stored in the random access memory of the respective camera;
• receiving, in the central station and responsive to the output having a first classification that the images are relevant to the item of interest, a report including the images from the respective camera via the communications network.