Threat detection and notification system for public safety vehicles
Abstract
The present invention is directed to a threat detection and notification system capable of capturing streaming video. The system preferably identifies a first object in a frame of streaming video and determines whether it is consistent with at least one predetermined object type, e.g., “person” or “weapon”. In a first embodiment, if the first object is consistent with a “person” object type, the system determines whether it is recognized as a known entity. If so, the system determines whether or not the first object is in a non-upright orientation. If so, the system generates a first alert notification to at least a first device. In another aspect, if the first object is not recognized as a known entity, the system can further determine whether the first object is recognized as a person-of-interest, and, if so, the system can generate a second alert notification to at least a second device.
Claims
exact text as granted — not AI-modifiedWhat we claim as our invention is:
1 . A method of processing captured streaming video on a frame-by-frame basis for threat detection and notification, said method comprising the steps of:
identifying a first object in a first frame of captured streaming video; determining whether the first object is consistent with at least one predetermined object type; upon determining that the first object is consistent with a “person” object type, determining whether or not the first object is recognized as a known entity; upon determining that the first object is recognized as a known entity, determining whether or not the first object is in a non-upright orientation; and upon determining that the first object is in a non-upright orientation, generating a first alert notification to at least a first device.
2 . The method of claim 1 , said method further comprising the step of:
upon determining that the first object is in a non-upright orientation, transmitting location data corresponding to a location at which the first frame of streaming video was captured to at least the first device.
3 . The method of claim 2 , said method further comprising the step of:
upon determining that the first object is in a non-upright orientation, generating a second alert notification to at least a second device.
4 . The method of claim 1 , said method further comprising the step of transmitting at least the first frame of captured streaming video to at least the first device.
5 . The method of claim 1 , said method further comprising the step of embedding within the first frame a graphic overlay around the first object upon determining that the first object is consistent with a “person” object type.
6 . The method of claim 1 , said method further comprising the steps of:
upon determining that the first object is not recognized as a known entity, determining whether or not the first object is recognized as a person-of-interest; and upon determining that the first object is recognized as a person-of-interest, generating a second alert notification to at least a second device.
7 . The method of claim 6 , said method further comprising the step of:
upon determining that the first object is recognized as a person-of-interest, transmitting location data corresponding to a location at which the first frame of streaming video was captured to at least the first device.
8 . The method of claim 7 , said method further comprising the step of:
upon determining that the first object is recognized as a person-of-interest, generating a third alert notification to at least a third device.
9 . The method of claim 6 , said method further comprising the step of transmitting at least the first frame of captured streaming video to at least the second device.
10 . The method of claim 6 , said method further comprising the step of enabling at least a first user to disable a broadcasting of the second alert notification on at least the second device.
11 . The method of claim 6 , said method further comprising the step of embedding within the first frame a graphic overlay around the first object upon determining that the first object is consistent with a “person” object type.
12 . A method of processing captured streaming video on a frame-by-frame basis for threat detection and notification, said method comprising the steps of:
identifying a first object in a first frame of captured streaming video; determining whether the first object is consistent with at least one predetermined object type; upon determining that the first object is consistent with a “weapon” object type, determining whether or not the first object is in the possession of a known entity; upon determining that the first object is not in the possession of a known entity, generating a first alert notification to at least a first device.
13 . The method of claim 12 , said method further comprising the step of:
upon determining that the first object is consistent with a “weapon” object type, determining whether the first object is consistent with predetermined weapon type.
14 . The method of claim 13 , wherein the predetermined weapon type is selected from a group consisting of “knife”, “handgun” and “rifle”.
15 . The method of claim 12 , said method further comprising the steps of:
upon determining that the first object is not in the possession of a known entity, determining whether or not the first object is recognized as being located in a gun rack attached to a vehicle; and upon determining that the first object is recognized as being located in a gun rack attached to a vehicle, disabling the generation of the first alert notification to at least the first device.
16 . The method of claim 12 , said method further comprising the steps of:
upon determining that the first object is not in the possession of a known entity, determining whether or not the first object is recognized as being secured; and upon determining that the first object is recognized as being secured, disabling the generation of the first alert notification to at least the first device.
17 . The method of claim 12 , said method further comprising the step of:
upon determining that the first object is not in the possession of a known entity, transmitting location data corresponding to a location at which the first frame of streaming video was captured to at least a second device.
18 . The method of claim 17 , said method further comprising the step of:
upon determining that the first object is not in the possession of a known entity, generating a second alert notification to at lease a third device.
19 . The method of claim 12 , said method further comprising the step of transmitting at least the first frame of captured streaming video to at least the first device.
20 . The method of claim 12 , said method further comprising the step of embedding within the first frame a graphic overlay around the first object upon determining that the first object is consistent with a “weapon” object type.Join the waitlist — get patent alerts
Track US2023024702A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.