Real-time video event detection using edge and cloud ai

A non-transitory computer-readable storage medium including instructions which, when executed by a processor, cause the processor to perform operations comprising:

• receiving, by an event monitoring system, live video data from one or more video capture devices at a surveillance location;
• identifying, by a first machine learning model, a first portion of the live video data as depicting an event;
• providing the first portion of the live video data to a second machine learning model;
• identifying, by the second machine learning model, the first portion of the live video data as depicting the event;
• and
• sending an event notification corresponding to the event to a user device.

A system, comprising:

• one or more video capture devices positioned at a surveillance location;
• and
• an event monitoring system coupled to the one or more video capture devices at the surveillance location, wherein the event monitoring system includes at least one processor which performs operations comprising:
• receiving live video data from one or more video capture devices at the surveillance location;
• identifying, by a first machine learning model, a first portion of the live video data as depicting an event;
• providing the first portion of the live video data to a second machine learning model;
• identifying, by the second machine learning model, the first portion of the live video data as depicting the event;
• and
• sending an event notification corresponding to the event to a user device.