Technologies for analyzing behaviors of objects or with respect to objects based on stereo imageries thereof
This disclosure enables various technologies for analyzing behaviors of objects or with respect to objects based on stereo imageries thereof. For example, such analysis may be useful in enforcement of certain actions by objects or with respect to objects, surveillance of objects or with respect to objects, or other situations involving analyzing behaviors of objects or with respect to objects.
1 . A device, comprising:
a processor programmed to:
access, in real-time, a stereo imagery of an area including a first object and a second object engaging with the first object;
form, in real-time, a reconstruction of the second object in the area based on the stereo imagery, wherein the reconstruction including a 3D area model and a 3D skeletal model within the 3D area model, wherein the 3D area model simulating the area, wherein the 3D skeletal model simulating the second object in the area;
identify, in real-time, a set of virtual movements of the 3D skeletal model in the 3D area model, wherein the set of virtual movements simulating the second object engaging with the first object;
identify, in real-time, a set of atomic movements of the 3D skeletal model corresponding to the set of virtual movements;
identify, in real-time, an event semantically defined by an expert system as a combination of at least two atomic movements of the set of atomic movements; and
take, in real-time, an action responsive to the event being identified.
2 . The device of claim 1 , wherein the second object including a real limb, wherein the 3D skeletal model including a virtual limb simulating the real limb, wherein the set of virtual movements including a virtual movement of the virtual limb, wherein the set of atomic movements including an atomic movement of the virtual limb, wherein the processor is further programmed to identify, in real-time, the set of atomic movements based on the atomic movement of the virtual limb corresponding the virtual movement of the virtual limb.
3 . The device of claim 2 , wherein the atomic movement of the virtual limb including a bending of the virtual limb according to a preset rule.
4 . The device of claim 3 , wherein the real limb is a real hand, wherein the first object is a sanitizing station, wherein the second object engaging with the first object includes the second object sanitizing the real hand at the sanitizing station, wherein the event is a hand sanitizing event.
5 . The device of claim 3 , wherein the first object is a first person having a first real hand, wherein the second object is a second person having a second real hand corresponding to the real limb, wherein the second object engaging with the first object including the second real hand shaking the first real hand, wherein the event is a hand shaking event.
6 . The device of claim 1 , wherein the set of atomic movements is a first set of atomic movements, wherein the event is further defined by a second set of atomic movements of the 3D skeletal model corresponding to the set of virtual movements, wherein the processor is further programmed to identify, in real-time, the event based on the first set of atomic movements and the second set of atomic movements.
7 . The device of claim 1 , wherein the second object having a pose in the area, wherein the second object including a real limb in the area, wherein the processor is further programmed to form, in real-time, the 3D skeletal model from the pose based on the stereo imagery and from how the real limb is positioned in the area based on the stereo imagery.
8 . The device of claim 7 , wherein the processor is further programmed to identify, in real-time, the set of atomic movements based on the 3D skeletal model simulating the pose and how the real limb is positioned in the area.
9 . The device of claim 1 , wherein the second object has a real face, wherein the stereo imagery depicts the real face, wherein the processor is further programmed to perform, in real-time, a recognition of the real face based on at least an image of the stereo imagery, wherein the action is based on the recognition, wherein the image depicts the real face.
10 . The device of claim 9 , wherein the action is a first action, wherein the processor is further programmed to take a second action responsive to the event not being identified, wherein the second action is based on the recognition.
11 . The device of claim 10 , wherein the second action includes adding an identifier of the second object associated with the real face to a list of identifiers not associated with the event.
12 . The device of claim 1 , wherein the processor is further programmed to modify, in real-time, a log for each occurrence of the event being identified and the event not being identified, wherein each of the occurrences includes an identifier of the second object.
13 . The device of claim 1 , wherein the processor is further programmed to retrieve a record with a set of information for the event not being identified responsive to a request from a user input device.
14 . The device of claim 13 , wherein the set of information includes at least a user interface element programmed to retrieve or play a portion of the stereo imagery.
15 . The device of claim 1 , wherein the processor is further programmed to access a log containing a set of information for the event being identified and the event not being identified responsive to a request from a user input device, and export a subset of the set of information for a preset time period responsive to the request from the user input device.
16 . The device of claim 1 , wherein the processor is further programmed to generate a dashboard based on a set of information for the event being identified and the event not being identified responsive a request from a user input device, and instruct a display to output the dashboard responsive to the request from the user input device.
17 . The device of claim 1 , further comprising:
a next unit of computing (NUC) apparatus including the processor; and
a housing including a pair of video cameras forming a stereo pair sourcing the stereo imagery.
18 . The device of claim 1 , wherein the action is a first action, wherein the processor is programmed to take a second action responsive to the event not being identified.
19 . The device of claim 18 , wherein the processor is further programmed to access an identifier for the second object, wherein each of the first action and the second action involves the identifier.
20 . The device of claim 18 , wherein the second action includes requesting an output device to output an alert, an alarm, or a notice indicative of the event not being identified.
21 . The device of claim 20 , wherein the output device is a display.
22 . The device of claim 20 , wherein the output device is a speaker.
23 . The device of claim 20 , wherein the stereo imagery is sourced from a source, wherein the output device is remote from the source.
24 . The device of claim 20 , wherein the stereo imagery is sourced from a source, wherein the output device is local to the source.
25 . The device of claim 20 , wherein the first object is a static object and the second object is a dynamic object.
26 . The device of claim 20 , wherein the first object is a dynamic object and the second object is a dynamic object.
27 . The device of claim 1 , wherein the stereo imagery is markerless motion capture.
28 . The device of claim 1 , wherein the expert system is programmed to employ a natural language to define the event as the combination of the at least two atomic movements of the set of atomic movements.
29 . The device of claim 1 , wherein the stereo imagery includes a set of depth metadata, wherein the expert system is programmed to process the set of depth metadata to define the event.
30 . A method, comprising:
accessing, via a processor, in real-time, a stereo imagery of an area including a first object and a second object engaging with the first object;
forming, via the processor, in real-time, a reconstruction of the second object in the area based on the stereo imagery, wherein the reconstruction including a 3D area model and a 3D skeletal model within the 3D area model, wherein the 3D area model simulating the area, wherein the 3D skeletal model simulating the second object in the area;
identifying, via the processor, in real-time, a set of virtual movements of the 3D skeletal model in the 3D area model, wherein the set of virtual movements simulating the second object engaging with the first object;
identifying, via the processor, in real-time, a set of atomic movements of the 3D skeletal model corresponding to the set of virtual movements;
identifying, via the processor, in real-time, an event semantically defined by an expert system as a combination of at least two atomic movements of the set of atomic movements; and
taking, via the processor, in real-time, an action responsive to the event being identified.
31 . The method of claim 30 , wherein the expert system is programmed to employ a natural language to define the event as the combination of the at least two atomic movements of the set of atomic movements.
32 . The method of claim 30 , wherein the stereo imagery includes a set of depth metadata, wherein the expert system is programmed to process the set of depth metadata to define the event.