IP Library › Granted Patent US 12,464,239
Granted Patent B2
US 12,464,239 · App. 18/434,056 · Granted Nov 4, 2025

Full frame media stabilization in electronic devices

Inventors: Raj Narayana Gadde (Bengaluru, IN); Sarvesh (Bengaluru, IN); Yathish Reddy (Bengaluru, IN); Addanki Sankara Rao (Bengaluru, IN); Pravin Ramachandran Nair (Bengaluru, IN)
Assignee: SAMSUNG ELECTRONICS CO., LTD.
H04N23/683H04N5/2628H04N23/65H04N23/6811H04N23/6812H04N23/81
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 12,464,239
App. No.
18/434,056
Granted
Nov 4, 2025
Kind
B2
Abstract

A method may comprise detecting at least one motion of the electronic device while capturing a plurality of media frames, determining a type of the at least one motion of the electronic device while capturing the plurality of media frames, determining a variation in the type of the at least one motion of the electronic device over a pre-determined period of time, selecting at least one stabilization procedure from a plurality of stabilization procedures and a frame fusion procedure from a plurality of frame fusion procedures based on the type of the at least one motion of the electronic device and the variation in the type of the at least one motion of the electronic device, and stabilizing, after the capturing of the plurality of media frames, the plurality of media frames based on the at least one selected stabilization procedure and the selected frame fusion procedure.

Claims (71)

1 . A method for full frame media stabilization, the method performed by an electronic device, the method comprising:

detecting at least one motion of the electronic device while capturing a plurality of media frames;

determining a type of the at least one motion of the electronic device while capturing the plurality of media frames;

determining a variation in the type of the at least one motion of the electronic device over a pre-determined period of time;

selecting at least one stabilization procedure from a plurality of stabilization procedures and a frame fusion procedure from a plurality of frame fusion procedures based on the type of the at least one motion of the electronic device and the variation in the type of the at least one motion of the electronic device; and

stabilizing, after the capturing of the plurality of media frames, the plurality of media frames based on the at least one selected stabilization procedure from the plurality of stabilization procedures and the selected frame fusion procedure from the plurality of frame fusion procedures.

2 . The method of claim 1 , wherein the selecting the at least one stabilization procedure and the frame fusion procedure based on the type of the at least one motion and the variation in the type of the at least one motion comprises:

determining a complexity level of the at least one motion based on at least one stabilization parameter, the type of the at least one motion, and the variation in the type of the at least one motion; and

selecting the at least one stabilization procedure based on the complexity level of the at least one motion.

3 . The method of claim 1 , wherein the stabilizing the plurality of media frames based on the at least one selected stabilization procedure and the selected frame fusion procedure, comprises:

stabilizing at least one media frame of the plurality of media frames based on the at least one selected stabilization procedure; and

determining the full frame media stabilization using the selected frame fusion procedure for the at least one stabilized media frame.

4 . The method of claim 2 , wherein the at least one stabilization parameter comprises at least one of a power consumed for stabilization of the plurality of media frames by each of the plurality of stabilization procedures, a time taken for stabilization of the plurality of media frames by each of the plurality of stabilization procedures, and a correlation between each of the plurality of media frames and each of the plurality of stabilization procedures.

5 . The method of claim 1 , wherein the type of the at least one motion is determined based on an analysis of one or more objects included in the plurality of media frames and a motion sensor.

6 . The method of claim 2 , wherein the stabilizing the plurality of media frames based on the at least one selected stabilization procedure and the selected frame fusion procedure comprises:

determining one or more crop parameters for the stabilizing the plurality of media frames based on the complexity level of the at least one motion of the electronic device; and

cropping a pre-determined size of at least one media frame of the plurality of media frames based on the determined one or more crop parameters.

7 . The method of claim 2 , wherein the frame fusion procedure comprises:

receiving the type of the at least one motion of the electronic device;

selecting at least one fusion procedure from the plurality of fusion procedure based on the type of the at least one motion, wherein selecting the fusion procedure comprises selecting the plurality of media frames;

receiving stabilized frame from a path smoothing component;

restoring the at least one media frame of the plurality of media frames based on the at least one fusion procedure selected using the plurality of media frames; and

fusing the plurality of media frames based on the type of the at least one motion and variation dynamically.

8 . The method of claim 1 , wherein the determining the type of the at least one motion comprises:

receiving, from a motion sensor, a plurality of motions of the electronic device;

determining the type of the at least one motion using at least one motion estimation method and the received plurality of motions of the electronic device; and

classifying the type of the at least one motion based on an output of the at least one motion estimation method.

9 . An electronic device for full frame media stabilization, the electronic device comprising:

a memory;

at least one processor;

a motion sensor configured to detect at least one motion of the electronic device while capturing a plurality of media frames; and

at least one image sensor configured to capture the plurality of media frames,

wherein the at least one processor is configured to;

determine a type of the at least one motion of the electronic device while capturing the plurality of media frames;

determine a variation in the type of the at least one motion of the electronic device over a pre-determined period of time;

select at least one stabilization procedure from a plurality of stabilization procedures and a frame fusion procedure from a plurality of frame fusion procedures based on the type of the at least one motion of the electronic device and the variation in the type of the at least one motion of the electronic device; and

stabilize, after the capture of the plurality of media frames, the plurality of media frames based on the at least one selected stabilization procedure from the plurality of stabilization procedures and the selected frame fusion procedure from the plurality of frame fusion procedures.

10 . The electronic device of claim 9 , wherein, to select the at least one stabilization procedure and the frame fusion procedure based on the type of the at least one motion and the variation in the type of the at least one motion, the at least one processor is configured to:

determine a complexity level of the at least one motion based on at least one stabilization parameter, the type of the at least one motion, and the variation in the type of the at least one motion; and

select the at least one stabilization procedure based on the complexity level of the at least one motion.

11 . The electronic device of claim 9 , wherein, to stabilize the plurality of media frames based on the at least one selected stabilization procedure and the selected frame fusion procedure, the at least one processor is configured to:

stabilize at least one media frame of the plurality of media frames based on the at least one selected stabilization procedure; and

determine the full frame media stabilization using the selected frame fusion procedure for the at least one stabilized media frame.

12 . The electronic device of claim 10 , wherein the at least one stabilization parameter comprises at least one of a power consumed for stabilization of the plurality of media frames by each of the plurality of stabilization procedures, a time taken for stabilization of the plurality of media frames by each of the plurality of stabilization procedures, and a correlation between each of the plurality of media frames and each of the plurality of stabilization procedures.

13 . The electronic device of claim 9 , wherein the type of the at least one motion is determined based on an analysis of one or more objects included in the plurality of media frames and a motion sensor.

14 . The electronic device of claim 10 , wherein, to stabilize the plurality of media frames based on the at least one selected stabilization procedure and the selected frame fusion procedure, the at least one processor is configured to:

determine one or more crop parameters for the stabilizing the plurality of media frames based on the complexity level of the at least one motion of the electronic device; and

crop a pre-determined size of at least one media frame of the plurality of media frames based on the determined one or more crop parameters.

15 . The electronic device of claim 10 , wherein the frame fusion procedure comprises:

receiving the type of the least one motion of the at least one motion of the electronic device;

selecting at least one fusion procedure from the plurality of fusion procedure based on the type of the at least one motion, wherein selecting the fusion procedure comprises selecting the plurality of media frames;

receiving stabilized frame from a path smoothing component;

restoring the at least one media frame of the plurality of media frames based on the at least one fusion procedure selected using the plurality of media frames; and

fusing the plurality of media frames based on the type of the at least one motion and variation dynamically.

16 . The electronic device of claim 9 , wherein, to determine the type of the at least one motion, the at least one processor is configured to:

receive a plurality of motions of the electronic device;

determine the type of the at least one motion using at least one motion estimation method and the received plurality of motions of the electronic device; and

classify the type of the at least one motion based on an output of the at least one motion estimation method.

17 . A computer-readable storage media storing a program that, when executed by at least one processor of an electronic device, causes the electronic device to perform a method comprising:

detecting at least one motion of the electronic device while capturing a plurality of media frames;

determining a type of the at least one motion of the electronic device while capturing the plurality of media frames;

determining a variation in the type of the at least one motion of the electronic device over a pre-determined period of time;

selecting at least one stabilization procedure from a plurality of stabilization procedures and a frame fusion procedure from a plurality of frame fusion procedures based on the type of the at least one motion of the electronic device and the variation in the type of the at least one motion of the electronic device; and

stabilizing, after the capturing of the plurality of media frames, the plurality of media frames based on the at least one selected stabilization procedure from the plurality of stabilization procedures and the selected frame fusion procedure from the plurality of frame fusion procedures.

18 . The computer-readable storage media of claim 17 , wherein the selecting the at least one stabilization procedure and the frame fusion procedure based on the type of the at least one motion and the variation in the type of the at least one motion comprises:

determining a complexity level of the at least one motion based on at least one stabilization parameter, the type of the at least one motion, and the variation in the type of the at least one motion; and

selecting the at least one stabilization procedure based on the complexity level of the at least one motion.

19 . The computer-readable storage media of claim 17 , wherein the stabilizing the plurality of media frames based on the at least one selected stabilization procedure and the selected frame fusion procedure, comprises:

stabilizing at least one media frame of the plurality of media frames based on the at least one selected stabilization procedure; and

determining the full frame media stabilization using the selected frame fusion procedure for the at least one stabilized media frame.

20 . The computer-readable storage media of claim 18 , wherein the at least one stabilization parameter comprises at least one of a power consumed for stabilization of the plurality of media frames by each of the plurality of stabilization procedures, a time taken for stabilization of the plurality of media frames by each of the plurality of stabilization procedures, and a correlation between each of the plurality of media frames and each of the plurality of stabilization procedures.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 6, 2024
From: GADDE, RAJ NARAYANA; ., SARVESH; REDDY, YATHISH; RAO, ADDANKI SANKARA; NAIR, PRAVIN RAMACHANDRAN
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 066395/0896 →
Priority Claims (2)
IN 202341007888 · Feb 7, 2023 · national
IN 202341007888 · Jul 27, 2023 · national
Continuity (2)
Continuation PCTKR2024001073 · Jan 23, 2024
Related Publication 20240267624A1 · Aug 8, 2024
References Cited (13)
US 9674440B2 · Karpenko · 2017 [cited by applicant]
US 11258999B2 · Rao Padebettu · 2022 [cited by examiner]
US 12335146B2 · Sivakumar · 2025 [cited by examiner]
US 20030076408A1 · Dutta · 2003 [cited by applicant]
US 20130044228A1 · Corey et al. · 2013 [cited by applicant]
US 20170041545A1 · Murgia et al. · 2017 [cited by applicant]
US 20180070015A1 · Hubel et al. · 2018 [cited by applicant]
US 20180338132A1 · Rao Padebettu · 2018 [cited by examiner]
KR 100677913B1 · 2007 [cited by applicant]
KR 100964951B1 · 2010 [cited by applicant]
KR 1020210115185A · 2021 [cited by applicant]
Translation of International Search Report dated Apr. 25, 2024, issued by the International Searching Authority in International Application No. PCT/KR2024/001073. [cited by applicant]
Translation of Written Opinion dated Apr. 25, 2024, issued by the International Searching Authority in International Application No. PCT/KR2024/001073. [cited by applicant]