Connected camera network with shared camera system video streams
Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for sharing video streams in a camera system network. The video streams may be modified and/or masked to obscure private video stream features from being shared. An example embodiment operates by linking a first camera system to a first user device. The first camera system detects a second camera system in its field of view, wherein the second camera system is linked to a second user device. Upon exchanging requests to share video streams, the first and second user devices may view the video streams from both camera systems. The video streams may be modified to mask and/or obscure private property and/or known persons to preserve privacy despite sharing video streams. For example, the first camera system may modify and stream a masked video stream to the second user device.
1 . A computer-implemented method for sharing a camera feed in a network of camera systems, comprising:
linking, by at least one computer processor, a first camera system to a first user device;
detecting a presence of a camera of a second camera system that is in a field of view of the first camera system based on one of an infrared-based strobing signal transmitted by the second camera system or a radio frequency-based strobing signal transmitted by the second camera system;
transmitting a command to the second camera system in response to detecting the presence of the camera, wherein the command requests permission to share a video stream from the camera with the first user device;
receiving a request message to share the video stream from the first camera system to a second user device linked to the second camera system;
determining, based at least on a pose of the camera of the second camera system, that the field of view of the first camera system comprises a private property associated with the first user device, public property, and property associated with the second user device;
generating a masked video stream that obscures the private property but not the property associated with the second user device; and
streaming the masked video stream from the first camera system to the second user device.
2 . The computer-implemented method of claim 1 , further comprising:
determining that the field of view of the first camera system further comprises a property associated with a third user device,
wherein generating the masked video stream comprises obscuring the third property associated with the third user device.
3 . The computer-implemented method of claim 1 , further comprising:
identifying a portion of the video stream from the first camera system corresponding to a detected person; and
applying a machine learning model to the video stream from the first camera system to determine that the detected person corresponds to a known person identified from training data,
wherein generating the masked video stream comprises obscuring the detected person.
4 . The computer-implemented method of claim 1 , further comprising:
monitoring the video stream from the first camera system to detect a predefined trigger event identified by a machine learning model trained to detect the predefined trigger event;
transmitting a notification message to one or more user devices corresponding to user accounts subscribed to receive trigger event notifications from the first camera system;
receiving a request from a user device of the one or more user devices to view the video stream from the first camera system via an interaction with the notification message; and
streaming the masked video stream from the first camera system to the user device providing the request.
5 . The computer-implemented method of claim 4 , wherein the predefined trigger event includes identification of a moving vehicle.
6 . The computer-implemented method of claim 4 , wherein the predefined trigger event includes an emergency condition, and wherein the computer-implemented method further comprises:
streaming the masked video stream from the first camera system to an emergency response system.
7 . The computer-implemented method of claim 1 , further comprising:
classifying portions of the masked video stream with labels identifying contents of the portions.
8 . A first camera system, comprising:
one or more cameras;
one or more memories; and
at least one processor each coupled to the one or more cameras and at least one of the memories and configured to perform operations comprising:
linking the first camera system to a first user device;
detecting a presence of a camera of a second camera system that is in a field of view of the first camera system based on one of an infrared-based strobing signal transmitted by the second camera system or a radio frequency-based strobing signal transmitted by the second camera system;
transmitting a command to the second camera system in response to detecting the presence of the camera, wherein the command requests permission to share a video stream from the camera with the first user device;
receiving a request message to share the video stream from the first camera system to a second user device linked to the second camera system;
determining, based at least on a pose of the camera of the second camera system, that the field of view of the first camera system comprises a private property associated with the first user device, public property, and property associated with the second user device;
generating a masked video stream that obscures the private property but not the property associated with the second user device; and
streaming the masked video stream from the first camera system to the second user device.
9 . The first camera system of claim 8 , the operations further comprising:
determining that the field of view of the first camera system further comprises a property associated with a third user device,
wherein generating the masked video stream comprises obscuring the property associated with the third user device.
10 . The first camera system of claim 8 , the operations further comprising:
identifying a portion of the video stream from the first camera system corresponding to a detected person; and
applying a machine learning model to the video stream from the first camera system to determine that the detected person corresponds to a known person identified from training data,
wherein generating the masked video stream comprises obscuring the detected person.
11 . The first camera system of claim 8 , the operations further comprising:
monitoring the video stream from the first camera system to detect a predefined trigger event identified by a machine learning model trained to detect the predefined trigger event;
transmitting a notification message to one or more user devices corresponding to user accounts subscribed to receive trigger event notifications from the first camera system;
receiving a request from a user device of the one or more user devices to view the video stream from the first camera system via an interaction with the notification message; and
streaming the masked video stream from the first camera system to the user device providing the request.
12 . The first camera system of claim 11 , wherein the predefined trigger event includes identification of a moving vehicle.
13 . The first camera system of claim 11 , wherein the predefined trigger event includes an emergency condition, and wherein the operations further comprise:
streaming the masked video stream from the first camera system to an emergency response system.
14 . The first camera system of claim 8 , the operations further comprising:
classifying portions of the masked video stream with labels identifying contents of the portions.
15 . A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
linking a first camera system to a first user device;
detecting a presence of a camera of a second camera system that is in a field of view of the first camera system based on one of an infrared-based strobing signal transmitted by the second camera system or a radio frequency-based strobing signal transmitted by the second camera system;
transmitting a command to the second camera system in response to detecting the presence of the camera, wherein the command requests permission to share a video stream from the camera with the first user device;
receiving a request message to share the video stream from the first camera system to a second user device linked to the second camera system;
determining, based at least on a pose of the camera of the second camera system, that the field of view of the first camera system comprises a private property associated with the first user device, public property, and property associated with the second user device;
generating a masked video stream that obscures the private property but not the property associated with the second user device; and
streaming the masked video stream from the first camera system to the second user device.
16 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:
determining that the field of view of the first camera system further comprises a property associated with a third user device,
wherein generating the masked video stream comprises obscuring the property associated with the third user device.
17 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:
identifying a portion of the video stream from the first camera system corresponding to a detected person; and
applying a machine learning model to the video stream from the first camera system to determine that the detected person corresponds to a known person identified from training data
wherein generating the masked video stream comprises obscuring the detected person.
18 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:
monitoring the video stream from the first camera system to detect a predefined trigger event identified by a machine learning model trained to detect the predefined trigger event;
transmitting a notification message to one or more user devices corresponding to user accounts subscribed to receive trigger event notifications from the first camera system;
receiving a request from a user device of the one or more user devices to view the video stream from the first camera system via an interaction with the notification message; and
streaming the masked video stream from the first camera system to the user device providing the request.
19 . The non-transitory computer-readable medium of claim 18 , wherein the predefined trigger event includes an emergency condition, and wherein the operations further comprise:
streaming the masked video stream from the first camera system to an emergency response system.
20 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:
classifying portions of the masked video stream with labels identifying contents of the portions.