Systems and methods for performing object detection and motion detection on video information

Patent metadata

Field	Value
Publication number	US-11494596-B2
Application number	US-202117194207-A
Country	US
Kind code	B2
Filing date	Mar 5, 2021
Priority date	Oct 8, 2019
Publication date	Nov 8, 2022
Grant date	Nov 8, 2022

Abstract

Systems and methods for converting video information into electronic output files are disclosed. Exemplary implementations may: obtain video information defining one or more videos; select a subset of the visual content included in the video content of the particular video; perform object detection to detect objects in the selected subset; perform motion detection to detect a movement for one or more of the detected objects in the selected subset, responsive to the object detection detecting one or more detected objects; and generate and store an electronic output file, responsive to the detection of the movement.

First claim

What is claimed is:

1. A system configured for converting video information into electronic output files, the system comprising:
one or more hardware processors configured by machine-readable instructions to:
obtain video information defining one or more videos, the one or more videos including a particular video, the particular video including video content having a progress length, the video content including visual content viewable as a function of progress through the progress length, wherein the visual content has a first electronic format, wherein the progress length is less than 1 minute when viewed at a frame rate between 20 frames per second and 60 frames per second, wherein the video content has been captured by one or more capture devices;
select a subset of the visual content included in the video content of the particular video, wherein the subset is at least 20 times smaller than the visual content;
perform object detection to detect one or more objects in the selected subset, wherein the object detection includes multiclass classification of a set of classes, wherein the set of classes includes a first class that represents living entities;
perform motion detection to detect a movement for at least one of the one or more objects in the selected subset, responsive to the object detection detecting one or more detected objects; and
generate and store an electronic output file, responsive to the motion detection detecting the movement, wherein the electronic output file is in a second electronic format, and wherein the electronic output file includes one or more representations of the detected movement.

2. The system of claim 1 , wherein the one or more hardware processors are further configured by machine-readable instructions to:
create a batch of other subsets of other visual content included in other video content of the one or more videos, wherein performing the object detection and the motion detection are performed for the batch.

3. The system of claim 1 , wherein the object detection further includes generating bounding boxes around the one or more objects.

4. The system of claim 1 , wherein the set of classes includes a second class that represents animals and a third class that represents vehicles.

5. The system of claim 1 , wherein the set of classes includes a class that represents people,
wherein the one or more hardware processors are further configured by machine-readable instructions to perform face detection to detect faces in the selected subset, responsive to the object detection detecting a person.

6. The system of claim 5 , wherein the one or more hardware processors are further configured by machine-readable instructions to:
perform face recognition on a face, responsive to the face detection detecting the face.

7. The system of claim 1 , wherein the motion detection is performed on the one or more objects.

8. The system of claim 1 , wherein the motion detection includes blurring part or all of the selected subset, setting contour levels for the blurred part of the selected subset, quantifying one or more differences between the blurred part of at least two objects in the selected subset, and comparing the one or more differences with a motion threshold level to determine whether the movement is detected for individual ones of the one or more objects in the selected subset.

9. The system of claim 1 , wherein the one or more hardware processors are further configured by machine-readable instructions to:
transfer and/or present the electronic output file to a user.

10. The system of claim 1 , wherein the subset is at least 100 times smaller than the visual content.

11. A method for converting video information into electronic output files, the method comprising:
obtaining video information defining one or more videos, the one or more videos including a particular video, the particular video including video content having a progress length, the video content including visual content viewable as a function of progress through the progress length, wherein the visual content has a first electronic format, wherein the progress length is less than 1 minute when viewed at a frame rate between 20 frames per second and 60 frames per second, wherein the video content has been captured by one or more capture devices;
selecting a subset of the visual content included in the video content of the particular video, wherein the subset is at least 20 times smaller than the visual content;
performing object detection to detect one or more objects in the selected subset, wherein the object detection includes multiclass classification of a set of classes, wherein the set of classes includes a first class that represents living entities;
performing motion detection to detect a movement for at least one of the one or more objects in the selected subset, responsive to the object detection detecting one or more detected objects; and
generating and storing an electronic output file, responsive to the motion detection detecting the movement, wherein the electronic output file is in a second electronic format, and wherein the electronic output file includes one or more representations of the detected movement.

12. The method of claim 11 , further comprising:
creating a batch of other subsets of other visual content included in other video content of the one or more videos, wherein performing the object detection and the motion detection are performed for the batch.

13. The method of claim 11 , wherein the object detection further includes generating bounding boxes around the one or more objects.

14. The method of claim 11 , wherein the set of classes includes a second class that represents animals and a third class that represents vehicles.

15. The method of claim 11 , wherein the set of classes includes a class that represents people; the method further comprising:
performing face detection to detect faces in the selected subset, responsive to the object detection detecting a person.

16. The method of claim 15 , further comprising:
performing face recognition on a face, responsive to the face detection detecting the face.

17. The method of claim 11 , wherein the motion detection is performed on the one or more objects.

18. The method of claim 11 , wherein the motion detection includes blurring part or all of the selected subset, setting contour levels for the blurred part of the selected subset, quantifying one or more differences between the blurred part of at least two objects in the selected subset, and comparing the one or more differences with a motion threshold level to determine whether the movement is detected for individual ones of the one or more objects in the selected subset.

19. The method of claim 11 , further comprising:
transferring and/or presenting the electronic output file to a user.

20. The method of claim 11 , wherein the subset is at least 100 times smaller than the visual content.

Assignees

• Mythical Inc

Inventors

• Cunningham Stephan
• Thacker Cameron
• Downs Chris
• Linden John

Classifications

• G06T7/215 Primary

  Motion-based segmentation · CPC title

• G06V40/20

  Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) · CPC title

• G06V20/40

  in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44) · CPC title

• G06F18/2431

  Multiple classes · CPC title

• G06T7/246

  using feature-based methods, e.g. the tracking of corners or segments · CPC title