Image zone processing
View Patent ↗Cameras capture time-stamped images of predefined areas. The predefined areas are assigned to one or more zones. The images are processed to recognize items and persons within the zones. Custom metrics with respect to each zone relative to at least time durations, items, and persons are logged in a data store. An interface is provided to custom define queries that are processed against the data store. In an embodiment, the data store is mined to discover relationships between the metrics for each zone, and real-time actions are processed when predefined conditions are discovered from the metrics.
1. A method, comprising:
obtaining images from cameras captured of different areas of an enterprise;
mapping area identifiers representing the different areas to zones;
identifying metrics based on custom conditions detected in the images for each zone;
logging the metrics in a data store;
providing an interface for defining custom queries to process against the metrics in the data store;
receiving an instruction through the interface to save a particular one of the queries as a first query;
receiving an interval of time through the interface with the instruction; and
repeatedly processing the first query against the metrics in the data store at a frequency that conforms to the interval of time.
2. The method of claim 1 , wherein identifying further includes receiving item identifiers for items detected in the images from an item tracker as first metrics.
3. The method of claim 2 , wherein identifying further includes receiving person identifiers for persons detected in the images from a person tracker as second metrics.
4. The method of claim 3 , wherein identifying further includes obtaining time stamps provided in the images by the cameras as third metrics.
5. The method of claim 4 , wherein identifying further includes recognizing attributes from the images that conform to the custom conditions as fourth metrics.
6. The method of claim 1 , wherein logging further includes logging the first metrics, the second metrics, the third metrics, and the fourth metrics as the metrics for each image in the data store.
7. The method of claim 1 further comprising, receiving real-time conditions and actions through the interface.
8. The method of claim 7 , wherein receiving further includes identifying the real-time conditions in some of the images and processing the actions responsive to identifying the real-time conditions.
9. The method of claim 1 further comprising:
mining the metrics in the data store for patterns present in a particular zone; and
reporting particular metrics identified in the patterns for the particular zone.
10. A method, comprising:
receiving through an interface conditions to detect in images;
associating the images to zones that are being monitored;
logging metrics for each image when the conditions are detected in the images by each zone;
reporting through the interface the metrics by each zone; and
sending a real-time notification to a predefined device when a particular condition is detected in a particular zone, wherein sending further includes sending the real-time notification as one or more of: a text message sent to the predefined device, a first instruction to a second device to play a sound over a speaker, and, a second instruction to a third device to illuminate one or more light sources in one or more predefined colors.
11. A method further comprising:
receiving through an interface conditions to detect in images;
associating the images to zones that are being monitored;
logging metrics for each image when the conditions are detected in the images by each zone;
reporting through the interface the metrics by each zone; and
processing one of:
(1) receiving a zone-specific query through the interface, processing the zone-specific query against the metrics that are associated with a particular zone identified by the zone-specific query, and returning zone-specific results through the interface;
(2) receiving an individual-specific query through the interface, processing the individual specific query against the metrics that are associated with a particular individual, and returning individual-specific results through the interface;
(3) receiving an item-specific query through the interface, processing the item-specific query against the metrics that are associated with a particular item, and returning item-specific results through the interface; and
(4) receiving a query associated with a combination of item-specific criteria, person-specific criteria, and zone-specific criteria, processing the query against the metrics that are associated with given items defined by the item-specific criteria, given individuals defined by the person-specific criteria, and given zones defined by the zone-specific criteria, and returning results through the interface.
12. The method of claim 11 , wherein receiving the conditions further includes identifying the conditions as: item conditions for the given items present in the images, person conditions for the given individuals present in the images, and time conditions for durations of the given items and the given individuals being detected within the given zones in the images.