A multi-layer technology stack includes a sensor layer including image sensors, a device layer, and a cloud layer, with interfaces between the layers. Each layer contains multiple nodes. A method to develop contextual understanding of related events detected by the nodes includes the following. Sensor nodes capture sensor data, including multiple image sensors capturing images. Various nodes receive sensor data and/or metadata packages from other nodes, analyze the received data for events, and generate and/or augment metadata packages describing the detected events. The analysis includes image understanding. Events that are related are identified, based on the metadata packages describing the events. A contextual understanding of the related events is developed, based on analysis of the metadata packages describing the events.