IP Library › Granted Patent US 12,261,996
Granted Patent B2
US 12,261,996 · App. 18/748,115 · Granted Mar 25, 2025

Method and system for preprocessing optimization of streaming video data

Inventor: Amol Ajgaonkar (Chandler, AZ)
Assignee: Insight Direct USA, Inc.
H04N17/00G11B27/031
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 12,261,996
App. No.
18/748,115
Granted
Mar 25, 2025
Kind
B2
Abstract

A method of improving a main output of a main processing application processing first video data includes analyzing incoming video data via a first processing pipeline and analyzing incoming video data via a second processing pipeline. The second processing pipeline includes identifying, by a parameter optimization module, first test preprocessing parameters; preprocessing the incoming video data according to the first test preprocessing parameters, wherein the first test preprocessing includes formatting the incoming video data to create first test video data; processing the first test video data by a test processing application to determine a first test output that is indicative of a first test inference dependent upon the first test video data; and comparing the first test output and the main output to a baseline criterion. In response to the first test output satisfying the baseline criterion, the parameter optimization module can alter the first preprocessing parameters to be similar to the first test preprocessing parameters.

Claims (43)

1. A method of improving a main output of a main processing application for processing first video data, the method comprising:

analyzing incoming video data via a first processing pipeline, the first processing pipeline comprising:

preprocessing the incoming video data according to first preprocessing parameters, wherein the preprocessing includes formatting the incoming video data to create the first video data; and

processing the first video data by the main processing application to determine the main output that is dependent upon the first video data;

analyzing incoming video data via a second processing pipeline, the second processing pipeline comprising:

identifying first test preprocessing parameters;

preprocessing the incoming video data according to the first test preprocessing parameters, wherein the first test preprocessing includes formatting the incoming video data to create first test video data; and

processing the first test video data by a test processing application to determine a first test output dependent upon the first test video data;

comparing the first test output to a value representative of an accuracy of the main output; and

in response to the first test output being more accurate than the value representative of the accuracy of the main output, altering the first preprocessing parameters.

2. The method of claim 1 , wherein the step of identifying the first test preprocessing parameters is performed by a parameter optimization module.

3. The method of claim 1 , wherein the value representative of the accuracy of the main output is a baseline criterion dependent upon the main output.

4. The method of claim 1 , wherein the first preprocessing parameters are altered to be at least substantially similar to the first test preprocessing parameters in response to the first test output being more accurate than the value representative of the accuracy of the main output.

5. The method of claim 1 , wherein the main output is indicative of a first inference dependent upon the first video data.

6. The method of claim 1 , wherein the first test output is a value representative of an accuracy of the first test output.

7. The method of claim 6 , wherein the first test output is more accurate than the value representative of the accuracy of the main output when the value representative of the accuracy of the first test output is greater than the value representative of the accuracy of the main output.

8. The method of claim 1 , wherein the main processing application at least partially includes an AI model.

9. The method of claim 1 , wherein the value representative of the accuracy of the main output is dependent upon an amount of correctly identified inferences by the main processing application.

10. The method of claim 1 , wherein the value representative of the accuracy of the main output is dependent upon a latency of the processing of the first video data by the main processing application.

11. The method of claim 1 , wherein the step of altering the first preprocessing parameters further includes updating the first preprocessing parameters with the first test preprocessing parameters.

12. The method of claim 1 , further comprising:

in response to the first test output being less accurate that the value representative of the accuracy of the main output, replacing the first test preprocessing parameters with second test preprocessing parameters that are different from the first test preprocessing parameters and repeating the steps of analyzing the incoming video data via the second preprocessing pipeline.

13. The method of claim 1 , wherein the step of preprocessing the incoming video data according to the first preprocessing parameters is performed by a first computer processor.

14. The method of claim 1 , wherein the main processing application and the test processing application are the same processing application such that processing the first video data to determine the main output and processing the test video data to determine the test output are performed by one processing application.

15. A system for improving a main output of a main processing application that is configured to analyze video data, the system comprising:

a first processing pipeline for analyzing incoming video data, the first processing pipeline comprising:

first preprocessing parameters for formatting the incoming video data;

a first gateway that is configured to receive the incoming video data and preprocess the incoming video data according to the first preprocessing parameters,

wherein the preprocessing of the incoming video data by the first gateway creates first video data;

the main processing application configured to access the first video data and process the first video data to determine a main output that is dependent upon the first video data; and

a second processing pipeline for analyzing the incoming video data, the second processing pipeline comprising:

first test preprocessing parameters for formatting the incoming video data;

a parameter optimization module that is configured to receive the incoming video data and preprocess the incoming video data according to the first test preprocessing parameters, wherein the test preprocessing includes formatting the incoming video data to create first test video data;

a test processing application configured to access the first test video data and process the first test video data to determine a test output,

wherein the parameter optimization module is configured to:

compare the test output to a value representative of an accuracy of the main output; and

in response to the test output being more accurate than the value representative of the accuracy of the main output, alter the first preprocessing parameters.

16. The system of claim 15 , wherein the parameter optimization module is further configured to access the main output, the test output, and the first preprocessing parameters before comparing the test output to the value representative of the accuracy of the main output.

17. The system of claim 15 , further comprising:

a first computer processor that at least partially includes at least one of the first gateway, the main processing application, the parameter optimization module, and the test processing application.

18. The system of claim 15 , wherein the value representative of the accuracy of the main output is a baseline criterion dependent upon the main output.

19. The system of claim 15 , wherein the first preprocessing parameters are altered to be at least substantially similar to the first test preprocessing parameters in response to the first test output being more accurate than the value representative of the accuracy of the main output.

20. The system of claim 15 , wherein the parameter optimization module is configured to, in response to the test output being less accurate that the value representative of the accuracy of the main output, replace the first test preprocessing parameters with second test preprocessing parameters that are different from the first test preprocessing parameters and repeating the preprocessing of the incoming video data to create second test video data and the processing of the second test video data by the test processing application.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 20, 2024
From: AJGAONKAR, AMOL
To: INSIGHT DIRECT USA, INC.
Reel/Frame 067776/0984 →
Continuity (3)
Continuation 18221561 · Jul 13, 2023
Continuation 17873789 · Jul 26, 2022
Related Publication 20240340405A1 · Oct 10, 2024
References Cited (107)
US 5857109A · Taylor · 1999 [cited by applicant]
US 6757434B2 · Miled et al. · 2004 [cited by applicant]
US 7334249B1 · Byers · 2008 [cited by applicant]
US 8031956B2 · Ali · 2011 [cited by applicant]
US 8229587B2 · Shieh et al. · 2012 [cited by applicant]
US 8358319B2 · Côtéet al. · 2013 [cited by applicant]
US 8493482B2 · Côtéet al. · 2013 [cited by applicant]
US 8539355B2 · Compagnat et al. · 2013 [cited by applicant]
US 8577279B2 · Baker et al. · 2013 [cited by applicant]
US 8593483B2 · Côtéet al. · 2013 [cited by applicant]
US 8786625B2 · Côtéet al. · 2014 [cited by applicant]
US 9100588B1 · Seymour · 2015 [cited by applicant]
US 9741098B2 · Cox · 2017 [cited by applicant]
US 9871998B1 · Curlander et al. · 2018 [cited by applicant]
US 10057636B1 · Nijim et al. · 2018 [cited by applicant]
US 10114980B2 · Barinov et al. · 2018 [cited by applicant]
US 10122906B2 · Yang et al. · 2018 [cited by applicant]
US 10176309B2 · Tormasov et al. · 2019 [cited by applicant]
US 10380431B2 · Winter et al. · 2019 [cited by applicant]
US 10424087B2 · Risser · 2019 [cited by applicant]
US 10497136B2 · Tamaazousti et al. · 2019 [cited by applicant]
US 10529106B2 · Eckert · 2020 [cited by applicant]
US 10674185B2 · Thomas et al. · 2020 [cited by applicant]
US 10687022B2 · Rasheed et al. · 2020 [cited by applicant]
US 10701321B2 · Westmacott et al. · 2020 [cited by applicant]
US 10756912B2 · Balasaygun et al. · 2020 [cited by applicant]
US 10776941B2 · Hollander et al. · 2020 [cited by applicant]
US 10860860B1 · Huynh et al. · 2020 [cited by applicant]
US 10922105B1 · Verma et al. · 2021 [cited by applicant]
US 10958854B2 · Elboher · 2021 [cited by applicant]
US 10972519B2 · Bar-Mashiah et al. · 2021 [cited by applicant]
US 10979663B2 · Amengual Galdon et al. · 2021 [cited by applicant]
US 10979718B2 · Chou et al. · 2021 [cited by applicant]
US 11038884B2 · Li · 2021 [cited by applicant]
US 11044525B2 · Armaly · 2021 [cited by applicant]
US 11050551B2 · Maggu et al. · 2021 [cited by applicant]
US 11075744B2 · Tormasov et al. · 2021 [cited by applicant]
US 11120013B2 · Bates et al. · 2021 [cited by applicant]
US 11138345B2 · Zou et al. · 2021 [cited by applicant]
US 11153069B2 · Kurian · 2021 [cited by applicant]
US 11196978B2 · Presler · 2021 [cited by applicant]
US 11509836B1 · Ajgaonkar · 2022 [cited by applicant]
US 11594032B1 · Raman · 2023 [cited by applicant]
US 11704891B1 · Ajgaonkar · 2023 [cited by applicant]
US 12118916B2 · Yang et al. · 2024 [cited by applicant]
US 20060277256A1 · Tiruthani et al. · 2006 [cited by applicant]
US 20060287081A1 · Osawa · 2006 [cited by applicant]
US 20070013801A1 · Sezan et al. · 2007 [cited by applicant]
US 20070189708A1 · Lerman et al. · 2007 [cited by applicant]
US 20090033745A1 · Yeredor et al. · 2009 [cited by applicant]
US 20100104027A1 · Youn et al. · 2010 [cited by applicant]
US 20100131554A1 · Cooper · 2010 [cited by applicant]
US 20100198947A1 · Daughtery et al. · 2010 [cited by applicant]
US 20110041080A1 · Fleischman et al. · 2011 [cited by applicant]
US 20120044945A1 · Bhayani · 2012 [cited by applicant]
US 20120075435A1 · Hovanky et al. · 2012 [cited by applicant]
US 20130038737A1 · Yehezkel et al. · 2013 [cited by applicant]
US 20130216207A1 · Berry et al. · 2013 [cited by applicant]
US 20150026718A1 · Seyller · 2015 [cited by applicant]
US 20160127749A1 · Chowdhury et al. · 2016 [cited by applicant]
US 20160205341A1 · Hollander et al. · 2016 [cited by applicant]
US 20170085892A1 · Liu et al. · 2017 [cited by applicant]
US 20170134162A1 · Code et al. · 2017 [cited by applicant]
US 20170308403A1 · Turull et al. · 2017 [cited by applicant]
US 20180167698A1 · Mercer et al. · 2018 [cited by applicant]
US 20180268864A1 · Bovik et al. · 2018 [cited by applicant]
US 20180330169A1 · Van Hoof et al. · 2018 [cited by applicant]
US 20180342045A1 · Lutz et al. · 2018 [cited by applicant]
US 20200007958A1 · Wondra et al. · 2020 [cited by applicant]
US 20200195693A1 · Price et al. · 2020 [cited by applicant]
US 20200336710A1 · Zhang · 2020 [cited by applicant]
US 20200380261A1 · Chandran et al. · 2020 [cited by applicant]
US 20210124760A1 · Klein et al. · 2021 [cited by applicant]
US 20210165966A1 · Swamypillai et al. · 2021 [cited by applicant]
US 20210195268A1 · Jiang et al. · 2021 [cited by applicant]
US 20210227126A1 · Se et al. · 2021 [cited by applicant]
US 20210233204A1 · Alattar et al. · 2021 [cited by applicant]
US 20210314396A1 · Basu et al. · 2021 [cited by applicant]
US 20210321064A1 · Broaddus · 2021 [cited by applicant]
US 20210337217A1 · Reddiar et al. · 2021 [cited by applicant]
US 20220044334A1 · Blaikie et al. · 2022 [cited by applicant]
US 20220276940A1 · Wald · 2022 [cited by applicant]
US 20220329539A1 · Kim et al. · 2022 [cited by applicant]
US 20220368972A1 · Cheraghi et al. · 2022 [cited by applicant]
US 20230056885A1 · Mamadapur et al. · 2023 [cited by applicant]
AU 499889B2 · 1979 [cited by applicant]
AU 2001296636A1 · 2002 [cited by applicant]
CA 2260932A1 · 1998 [cited by applicant]
CA 3057924A1 · 2021 [cited by applicant]
CN 105430429B · 2019 [cited by applicant]
DE 2945615A1 · 1981 [cited by applicant]
EP 0824824A1 · 1998 [cited by applicant]
EP 2200000B1 · 2011 [cited by applicant]
EP 3374926A1 · 2018 [cited by applicant]
EP 3275175A4 · 2018 [cited by applicant]
EP 3559868A1 · 2019 [cited by applicant]
EP 3719687A1 · 2020 [cited by applicant]
EP 3644277A4 · 2021 [cited by applicant]
GB 201406814 · 2014 [cited by applicant]
WO 2001011862A9 · 2001 [cited by applicant]
WO 2004061729A2 · 2004 [cited by applicant]
WO 2016078490A1 · 2016 [cited by applicant]
WO 2020022956A1 · 2020 [cited by applicant]
WO 2021053604A1 · 2021 [cited by applicant]
WO 2021135641A1 · 2021 [cited by applicant]
WO 2021208952A1 · 2021 [cited by applicant]
WO 2021226601A1 · 2021 [cited by applicant]