Methods and systems for person detection in a video feed

• US 10,657,382 B2
• Filed: 07/02/2019
• Issued: 05/19/2020
• Est. Priority Date: 07/11/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Chaudhry, Rizwan Ahmed, Dalal, Navneet, Ben-Meshulam, Jonathan Z., Heitz, III, George Alban
• Primary Examiner(s): Bella, Matthew C
• Assistant Examiner(s): Shin, Brian D
• Application Number:
  US16/460,706
• Publication Number:
  US 20190325228A1
• Time in Patent Office: 322 Days
• Field of Search: None
• CPC Class Codes: G06F 18/231 Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06V 10/40 Extraction of image or video features
• CPC Class Codes: G06V 10/62 relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
• CPC Class Codes: G06V 10/7625 Hierarchical techniques, i.e. dividing or merging patterns to obtain a tree-like representation; Dendograms
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/49 Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

The various embodiments described herein include methods, devices, and systems for providing event alerts. In one aspect, a method includes obtaining a video feed. A frame of the video feed is analyzed at a first resolution to determine whether the frame includes a potential instance of a person. In accordance with the determination that the image includes the potential instance, a region is denoted around the potential instance. The region is analyzed at a second resolution, greater than the first resolution. In accordance with a determination that the region includes the instance of the person. a determination that the frame includes the person is made. An indication of the determination is stored for use in subsequent alert notification processing.

Claims

1. A method, comprising:

at a computing system having one or more processors and memory;

obtaining a video feed; and

for a frame of the video feed, analyzing the frame at a first resolution to determine whether the frame includes a potential instance of a person;

in accordance with a determination that the frame includes the potential instance, denoting a region around the potential instance;

analyzing the region at a second resolution, greater than the first resolution; and

in accordance with a determination that the region includes the instance of the person;

determining that the frame includes the person; and

storing an indication of the determination for use in subsequent alert notification processing.

2. The method of claim 1, wherein the video feed comprises a plurality of frames, the method further comprising, for each frame of the plurality of frames, assigning a confidence score to the frame.

3. The method of claim 2, wherein the confidence score is based on the analysis of the frame at the first resolution.

4. The method of claim 2, wherein the confidence score is based on the analysis of the region at the second resolution.

5. The method of claim 2, wherein the video feed includes a motion event, and the method further comprises, in accordance with a determination that the confidence score for at least one frame of the plurality of frames exceeds a predetermined threshold, denoting the motion event as involving a person.

6. The method of claim 1, wherein determining that the frame includes the potential instance of the person comprises:

detecting the potential instance of the person;

assigning a confidence score to the potential instance of the person; and

in accordance with a determination that the confidence score meets one or more predetermined criteria, determining that the frame includes the potential instance of the person.

7. The method of claim 1, further comprising:

determining whether the region includes one or more persons other than the potential person; and

in accordance with a determination that the region includes the one or more other persons, denoting the frame as containing a person.

8. The method of claim 1, wherein the video feed comprises a plurality of frames, the method further comprising:

determining that one or more frames of the plurality of images includes a person;

obtaining a second plurality of frames, the second plurality of frames preceding the motion event;

for each frame in the second plurality of frames, analyzing the frame to determine whether the image includes the person;

in accordance with a determination that one or more frames of the second plurality of frames do not include the person, denoting the motion event as involving the person; and

in accordance with a determination that one or more frames of the second plurality of frames include the person, forgoing denoting the motion event as involving the person.

9. The method of claim 1, further comprising:

in accordance with a determination that the frame includes multiple potential instances of a person, denoting a region encompassing each potential instance; and

determining whether the region includes one or more instances of a person by analyzing the region at the second resolution, greater than the first resolution.

10. The method of claim 1, further comprising:

for each frame in the plurality of frames, analyzing the frame to determine whether the frame includes a particular object, the analyzing including;

determining whether the frame includes a potential instance of the particular object by analyzing the frame at a first resolution;

in accordance with a determination that the frame includes a potential instance, denoting a region around the potential instance, wherein the area of the region is less than the area of the frame;

determining whether the region includes an instance of the particular object by analyzing the region at a second resolution, greater than the first resolution; and

in accordance with a determination that the region includes an instance of the particular object, determining that the frame includes the particular object.

11. The method of claim 1, further comprising determining whether the motion event involves a person by analyzing one or more relationships between frames including persons of the plurality of frames.

12. A computing system comprising:

one or more processors; and

memory coupled to the one or more processors, the memory storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions for;

obtaining a video feed; and

for a frame of the video feed, analyzing the frame at a first resolution to determine whether the frame includes a potential instance of a person;

in accordance with the determination that the frame includes the potential instance, denoting a region around the potential instance;

analyzing the region at a second resolution, greater than the first resolution; and

in accordance with a determination that the region includes the instance of the person;

determining that the frame includes the person; and

storing an indication of the determination for use in subsequent alert notification processing.

13. The computing system of claim 12, wherein the video feed includes a plurality of frames, the one or more programs further include instructions for assigning a confidence score to each frame of the plurality of frames.

14. The computing system of claim 13, wherein the video feed includes a motion event, and the one or more programs further include instructions for, in accordance with a determination that the confidence score for at least one frame of the plurality of frames exceeds a predetermined threshold, denoting the motion event as involving a person.

15. The computing system of claim 12, wherein the instructions for determining that the frame includes the potential instance of the person comprises instructions for:

detecting the potential instance of the person;

assigning a confidence score to the potential instance of the person; and

in accordance with a determination that the confidence score meets one or more predetermined criteria, determining that the frame includes the potential instance of the person.

16. The computing system of claim 12, wherein the video feed comprises a plurality of frames, the one or more programs further include instructions for:

determining that one or more frames of the plurality of images includes a person;

obtaining a second plurality of frames, the second plurality of frames preceding the motion event;

for each frame in the second plurality of frames, analyzing the frame to determine whether the frame includes the person;

in accordance with a determination that one or more frames of the second plurality of frames do not include the person, denoting the motion event as involving the person; and

in accordance with a determination that one or more frames of the second plurality of images include the person, forgoing denoting the motion event as involving the person.

17. A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing system, cause the system to:

obtain a video feed; and

for a frame of the video feed, analyze the frame at a first resolution to determine whether the frame includes a potential instance of a person;

in accordance with the determination that the frame includes the potential instance, denote a region around the potential instance;

analyze the region at a second resolution, greater than the first resolution; and

in accordance with a determination that the region includes the instance of the person;

determine that the frame includes the person; and

store an indication of the determination for use in subsequent alert notification processing.

18. The non-transitory computer-readable storage medium of claim 17, wherein the one or more programs comprising instructions, which when executed by the computing system, cause the system to assign a confidence score to each frame of the plurality of frames.

19. The non-transitory computer-readable storage medium of claim 17, wherein the determination that the frame includes the potential instance of the person comprises:

detecting the potential instance of the person;

assigning a confidence score to the potential instance of the person; and

in accordance with a determination that the confidence score meets one or more predetermined criteria, determining that frame includes the potential instance of the person.

20. The non-transitory computer-readable storage medium of claim 17, wherein the video feed includes a plurality of frames, and the one or more programs comprising instructions, which when executed by the computing system, cause the system to:

determine that one or more frames of the plurality of frames include a person;

obtain a second plurality of frames, the second plurality of frames preceding the motion event;

for each frame in the second plurality of frames, analyze the frame to determine whether the image includes the person;

in accordance with a determination that one or more frames of the second plurality of frames do not include the person, denote the motion event as involving the person; and

in accordance with a determination that one or more frames of the second plurality of images include the person, forgo denoting the motion event as involving the person.