IP Library › Granted Patent US 11,611,719
Granted Patent B2
US 11,611,719 · App. 17/112,108 · Granted Mar 21, 2023

Management of video playback speed based on objects of interest in the video data

Inventor: Amit Kumar (Menlo Park, CA)
Assignee: DRAGONFRUIT AI, INC.
H04N7/013G06K9/6253G06T7/20G06V20/46G06V40/10G11B27/005G11B27/031H04N5/23229H04N5/91H04N7/183G06T2207/10016G06T2207/30242G06V2201/08
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,611,719
App. No.
17/112,108
Granted
Mar 21, 2023
Kind
B2
Abstract

Systems, methods, and software described herein manage the playback speed of video data based on processing objects in the video data. In one example, a video processing service obtains video data from a video source and identifies objects of interest in the video data. The video processing service further determines complexity in frames of the video data related to the objects of interest and updates playback speeds for segments of the video data based on the complexity of the frames.

Claims (38)

1. A method comprising:

obtaining video data from a video source;

identifying objects of interest in the video data, wherein the objects of interest comprise vehicles or people;

determining complexity in frames of the video data for the objects of interest, wherein the complexity comprises at least a quantity of the objects of interest in the frames, an amount of movement by the objects of interest in the frames, and a physical proximity between at least two of the objects of interest in the frames; and

updating playback speeds of the video data based on the complexity, wherein different segments of the video data are allocated a different playback speed, and wherein one or more frames of the frames are skipped when no objects of interest are detected in the one or more frames.

2. The method of claim 1 , wherein the video source comprises video storage or a video camera.

3. The method of claim 1 , wherein updating the playback speeds of the video data based on the complexity comprises updating a first one or more segments with a first complexity with a first playback speed and a second one or more segments with a second complexity.

4. The method of claim 1 , wherein identifying the objects of interest in the video data comprises:

receiving a selection of one or more attributes associated with the objects of interest; and

identifying the objects of interest in the video data with the one or more attributes.

5. The method of claim 4 , wherein the one or more attributes comprise one or more object types, one or more object colors, or one or more object shapes.

6. The method of claim 1 further comprising:

identifying one or more objects that are not the objects of interest to be removed from the video data; and

removing the one or more objects from the video data.

7. A computing apparatus comprising:

a storage system;

a processing system operatively coupled to the storage system; and

program instructions stored on the storage system that, when executed by the processing system, direct the computing apparatus to:

obtain video data from a video source;

identify objects of interest in the video data;

determine complexity in frames of the video data for the objects of interest, wherein the complexity comprises at least a quantity of the objects of interest in the frames and an amount of movement by the objects of interest in the frames, and a physical proximity between at least two of the objects of interest in the frames; and

update playback speeds of the video data based on the complexity, wherein different segments of the video data are allocated a different playback speed, and wherein one or more frames of the frames are skipped when no objects of interest are detected in the one or more frames.

8. The computing apparatus of claim 7 , wherein the video source comprises video storage or a video camera.

9. The computing apparatus of claim 7 , wherein the updating playback speeds of the video data based on the complexity comprises updating a first one or more segments with a first complexity with a first playback speed and a second one or more segments with a second complexity.

10. The computing apparatus of claim 7 , wherein identifying the objects of interest in the video data comprises:

receiving a selection of one or more attributes associated with the objects of interest; and

identifying the objects of interest in the video data with the one or more attributes.

11. The computing apparatus of claim 10 , wherein the one or more attributes comprise one or more object types, one or more object colors, or one or more object shapes.

12. The computing apparatus of claim 7 , wherein the program instructions further direct the computing apparatus to:

identify one or more objects that are not the objects of interest to be removed from the video data; and

remove the one or more objects from the video data.

13. A method comprising:

obtaining video data from a video storage device;

receiving a selection of one or more attributes for objects of interest in the video data;

identifying the objects of interest in the video data;

determining complexity in frames of the video data for the objects of interest, wherein the complexity is determined at least in part on a quantity of the objects of interest in the frames and an amount of movement of the objects of interest in the frame, and a physical proximity between at least two of the objects of interest in the frames; and

updating playback speeds of the video data based on the complexity, wherein different segments of the video data are allocated a different playback speed, and wherein one or more frames of the frames are skipped when no objects of interest are detected in the one or more frames.

14. The method of claim 13 , wherein the one or more attributes comprise one or more object types, one or more object colors, or one or more object shapes.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 4, 2020
From: KUMAR, AMIT
To: DRAGONFRUIT AI, INC.
Reel/Frame 054549/0011 →
Continuity (1)
Related Publication 20220182577A1 · Jun 9, 2022
Cited By (1)
US 12,200,397