Granted Patent B2

US 12,314,889 · App. 17/958,893 · Granted May 27, 2025

Inventors: Hongcheng Wang (Arlington, VA); Luke Deluccia (Philadelphia, PA); Sara Cuesta Gonzalez (Philadelphia, PA); Zhe Wu (Great Falls, VA); Toufiq Parag (Ashburn, VA)

Assignee: Comcast Cable Communications, LLC

G06Q10/0833G06Q10/083G06T7/215G06V20/41G06V20/52G06T2207/20081

Abstract

Claims (95)

1. A method comprising:

receiving, by a computing device based on detected motion in a field of view of a camera associated with a premises, video of a first object;

determining, by the computing device and based on tracking a position of the first object in the video, a time period between the first object disappearing from the field of view and the first object reappearing in the field of view;

determining, by the computing device and based on the time period satisfying a threshold, that a delivery of a second object occurs at the premises; and

sending, by the computing device to a user device, a notification of the delivery.

2. The method of claim 1 , wherein the second object is delivered at a location that is outside the field of view of the camera.

3. The method of claim 1 , wherein the determining that the delivery of the second object occurs is further based on:

determining that the first object moves, during a first time period and together with the second object, in a first direction; and

determining that the first object moves, during a second time period and without the second object, in a second direction.

4. The method of claim 1 , further comprising:

selecting, from the video of the first object, a frame and a region of the frame indicating the first object; and

generating a flipped version of the selected frame; and

wherein the determining the time period is based on the selected frame and the flipped version of the selected frame.

5. The method of claim 1 , further comprising:

selecting, from the video of the first object, a plurality of frames comprising regions indicating movement of the first object; and

comparing the regions of the plurality of frames; and

wherein the determining the time period is based on the comparing.

6. The method of claim 1 , further comprising:

causing, based on determining the first object as an object of interest, movement of the camera to track the movement of the first object.

7. The method of claim 1 , further comprising:

receiving, from a second camera, second video that indicates delivery of a third object at a second premises located within a geographical area proximate to the premises; and

wherein the determining that the delivery of the second object occurs is further based on the second video.

8. The method of claim 1 , further comprising:

determining contextual information associated with the first object; and

wherein the sending the notification is further based on the contextual information.

9. The method of claim 1 , wherein the determining that the delivery of the second object occurs is futher based on:

determining that a pattern of movement of the first object indicates placement of the second object at or near the premises.

10. A method comprising:

selecting, by a computing device and from video recorded by a camera associated with a premises, a frame and a region of the frame indicating a first object;

generating, by the computing device, a flipped version of the selected frame;

determining, by the computing device based on tracking a position of the first object in the selected frame and the flipped version of the selected frame, that a pattern of movement of the first object; indicates a delivery, of a second object, occurs at the premises; and

sending, by the computing device, to a user device, and based on the determination that the delivery occurs, a notification of the delivery.

11. The method of claim 10 , wherein the second object is delivered at a location that is outside a field of view of the camera.

12. The method of claim 10 , wherein the determining that the delivery occurs is further based on:

determining that the first object moves, during a first time period and together with the second object, in a first direction; and

determining that the first object moves, during a second time period and without the second object, in a second direction.

13. The method of claim 10 , wherein the determining that the delivery occurs is further based on contextual information comprising at least one of:

sounds accompanying appearance of the first object;

appearance of a delivery vehicle;

a logo associated with a delivery service; or

second video, received from a second camera, that indicates delivery of a third object at a second premises located within a geographical area proximate to the premises.

14. The method of claim 10 , wherein the determining that the delivery occurs is further based on a time period, between the first object disappearing from a field of view and the first object reappearing in the field of view, satisfying a threshold.

15. The method of claim 10 , wherein the notification comprises a priority value, associated with the delivery, that is based on a user profile that lists a plurality of scheduled deliveries, and wherein at least two of the plurality of scheduled deliveries are assigned different priority values.

16. An apparatus comprising:

one or more processors; and

memory storing instructions, when executed by the one or more processors, configure the apparatus to:

receive, based on detected motion in a field of view of a camera associated with a premises, video of a first object;

determine, based on tracking a position of the first object in the video, a time period between the first object disappearing from the field of view and the first object reappearing in the field of view;

determine, based on the time period satisfying a threshold, that a delivery of a second object occurs at the premises; and

send, to a user device, a notification of the delivery.

17. The apparatus of claim 16 , wherein the second object is delivered at a location that is outside the field of view of the camera.

18. The apparatus of claim 16 , wherein the instructions, when executed by the one or more processors, configure the apparatus to determine that the delivery of the second object occurs by:

determining that the first object moves, during a first time period and together with the second object, in a first direction; and

determining that the first object moves, during a second time period and without the second object, in a second direction.

19. The apparatus of claim 16 , wherein the instructions, when executed by the one or more processors, further configure the apparatus to:

select, from the video of the first object, a frame and a region of the frame indicating the first object; and

generate a flipped version of the selected frame; and

wherein the instructions, when executed by the one or more processors, configure the apparatus to determine the time period further based on the selected frame and the flipped version of the selected frame.

20. The apparatus of claim 16 , wherein the instructions, when executed by the one or more processors, further configure the apparatus to:

select, from the video of the first object, a plurality of frames comprising regions indicating movement of the first object; and

compare the regions of the plurality of frames; and

wherein the instructions, when executed by the one or more processors, configure the apparatus to determine the time period further based on the comparing.

21. The apparatus of claim 16 , wherein the instructions, when executed by the one or more processors, further configure the apparatus to:

cause, based on determining the first object as an object of interest, movement of the camera to track the movement of the first object.

22. The apparatus of claim 16 , wherein the instructions, when executed by the one or more processors, further configure the apparatus to:

receive, from a second camera, second video that indicates delivery of a third object at a second premises located within a geographical area proximate to the premises; and

wherein the instructions, when executed by the one or more processors, configure the apparatus to determine that the delivery of the second object occurs further based on the second video.

23. The apparatus of claim 16 , wherein the instructions, when executed by the one or more processors, further configure the apparatus to determine contextual information associated with the first object; and

wherein the instructions, when executed by the one or more processors, configure the apparatus to send the notification further based on the contextual information.

24. The apparatus of claim 16 , wherein the instructions, when executed by the one or more processors, further configure the apparatus to determine that the delivery of the second object occurs by:

determining that a pattern of movement of the first object indicates placement of the second object at or near the premises.

25. An apparatus comprising:

one or more processors; and

memory storing instructions, when executed by the one or more processors, configure the apparatus to:

select, from video recorded by a camera associated with a premises, a frame and a region of the frame indicating a first object;

generate a flipped version of the selected frame;

determine, based on tracking a position of the first object in the selected frame and the flipped version of the selected frame, that a pattern of movement of the first object indicates a delivery, of a second object, occurs at the premises; and

send, to a user device and based on the determination that the delivery occurs, a notification of the delivery.

26. The apparatus of claim 25 , wherein the second object is delivered at a location that is outside a field of view of the camera.

27. The apparatus of claim 25 , wherein the instructions, when executed by the one or more processors, configure the apparatus to determine that the delivery occurs by:

determining that the first object moves, during a first time period and together with the second object, in a first direction; and

determining that the first object moves, during a second time period and without the second object, in a second direction.

28. The apparatus of claim 25 , wherein the instructions, when executed by the one or more processors, configure the apparatus to determine that the delivery occurs futher based on contextual information comprising at least one of:

sounds accompanying appearance of the first object;

appearance of a delivery vehicle;

a logo associated with a delivery service; or

second video, received from a second camera, that indicates delivery of a third object at a second premises located within a geographical area proximate to the premises.

29. The apparatus of claim 25 , wherein the instructions, when executed by the one or more processors, configure the apparatus to determine that the delivery occurs further based on a time period, between the first object disappearing from a field of view and the first object reappearing in the field of view, satisfying a threshold.

30. The apparatus of claim 25 , wherein the notification comprises a priority value, associated with the delivery, that is based on a user profile that lists a plurality of scheduled deliveries, and wherein at least two of the plurality of scheduled deliveries are assigned different priority values.

31. The method of claim 1 , wherein the tracking the position of the first object in the video comprises:

receiving, from a machine learning model, a prediction indicating that the first object comprises an object of interest, wherein the machine learning model is trained, by a plurality of training data sets each identifying a respective object of interest, to recognize an object of interest from an input video.

32. The method of claim 1 , wherein the tracking the position of the first object in the video comprises:

recognizing, using a machine learning model, a moving blob in the video;

cropping, from one or more image frames of the video, one or more regions associated with the moving blob; and

determining, by applying an image recognition algorithm, that the moving blob is associated with the first object.

Assignments (1)

Continuity (1)

References Cited (17)