IP Library › Granted Patent US 12,620,203
Granted Patent B2
US 12,620,203 · App. 17/719,049 · Granted May 5, 2026

Data collection and classifier training in edge video devices

Inventors: Damien Kah (San Jose, CA); Qian Zhong (Fremont, CA); Shaomin Xiong (Fremont, CA); Toshiki Hirano (San Jose, CA)
Assignee: Western Digital Technologies, Inc.
G06V10/774G06V10/7715G06V10/776G06V10/778G06V20/46G06N3/08G06T2207/20084G06V10/454G06V10/82G06V2201/07
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 12,620,203
App. No.
17/719,049
Filed
Apr 12, 2022
Granted
May 5, 2026
Kind
B2
Examiner
TRAN, QUOC A
Art Unit
2145
USPC
706/12
Abstract

A digital video camera architecture for updating an object identification and tracking model deployed with the camera is disclosed. The invention comprises optics, a processor, a memory, and an artificial intelligence logic which may further comprise artificial neural networks. The architecture may identify objects according to the confidence threshold of a model. The confidence threshold may be monitored over time, and the model may be updated if the confidence threshold drops below an acceptable level. The data for retraining is ideally generated substantially internal to the camera. A classifier is generated to process the entire field data set stored on the camera to create a field data subset also stored on the camera. The field data subset may be run through the model to generate cases that may be used in further monitoring, training, and updating of the model. Classifiers may also be generated for images in different domains (e.g., lighting, weather, surveillance area, indoor, outdoor, urban, rural, etc.). These classifiers can be used to train the model to accurately identify objects and features independent of the domain of origin of the image being evaluated.

Claims (100)

1 . A device, comprising:

an artificial intelligence logic configured to:

evaluate a source domain validation data set with a first detector,

use annotations of an output of the first detector to generate a source domain surrogate data set,

train a source domain classifier with the source domain surrogate data set,

evaluate a source domain entire field data set with the source domain classifier to generate a source domain field data subset,

evaluate the source domain field data subset with the first detector to generate a source domain final field data subset,

update the source domain validation data set from the source domain final field data subset, and

train, using the source domain classifier, a target domain classifier to:

minimize an error function at an output of a label classification head of the target domain classifier, and

maximize the error function at an output of a domain classification head of the target domain classifier to filter features that are unique to the source domain classifier.

2 . The device of claim 1 , wherein:

the target domain classifier comprises a feature extractor derived from a first portion of the source domain classifier;

the label classification head is derived from a second portion of the source domain classifier; and

the domain classification head is coupled in parallel to the label classification head.

3 . The device of claim 2 , wherein:

the artificial intelligence logic is further configured to:

extract first features from the source domain validation data set using the feature extractor,

extract second features from a target domain validation data set using the feature extractor,

run the first features through both the label classification head and the domain classification head, and

run the second features only through the domain classification head.

4 . The device of claim 3 , wherein:

the artificial intelligence logic is further configured to:

apply positive feedback to the output of the label classification head, and

apply negative feedback to the output of the domain classification head.

5 . The device of claim 4 , wherein the negative feedback is adversarial training.

6 . The device of claim 4 , wherein the positive feedback is backpropagation to reinforce features similar to the source domain classifier.

7 . The device of claim 4 , wherein:

the artificial intelligence logic is further configured to:

train the target domain classifier to:

label objects in images with substantially the same accuracy at the output of the label classification head with images from either the source domain validation data set or the target domain validation data set,

update a main validation data set from the source domain validation data set,

update the main validation data set from the target domain validation data set, and

train a second detector using the updated main validation data set.

8 . The device of claim 1 , further comprising:

an optics module.

9 . A system, comprising:

a computational system configured to:

evaluate a source domain validation data set with a first detector,

use annotation of an output of the first detector to generate a source domain surrogate data set, and

train a source domain classifier with the source domain surrogate data set; and

a device, comprising:

an artificial intelligence logic configured to:

run a source domain entire field data set through the source domain classifier to generate a source domain field data subset,

evaluate the source domain field data subset with the first detector to generate a source domain final field data subset,

update the source domain validation data set from the source domain final field data subset, and

train, using the source domain classifier, a target domain classifier to:

minimize an error function at an output of a label classification head of the target domain classifier, and

maximize the error function at an output of a domain classification head of the target domain classifier to filter features that are unique to the source domain classifier.

10 . The system of claim 9 , further comprising:

an optics module.

11 . The system of claim 9 , wherein:

the target domain classifier comprises a feature extractor derived from a first portion of the source domain classifier;

the label classification head is derived from a second portion of the source domain classifier; and

the domain classification head is coupled in parallel to the label classification head.

12 . The system of claim 11 , wherein:

the artificial intelligence logic is further configured to:

extract first features from the source domain validation data set using the feature extractor,

extract second features from a target domain validation data set using the feature extractor,

run the first features through both the label classification head and the domain classification head, and

run the second features only through the domain classification head.

13 . The system of claim 12 , wherein:

the artificial intelligence logic is further configured to:

train the target domain classifier to:

label objects in images with substantially the same accuracy at the output of the label classification head with images from either the source domain validation data set or the target domain validation data set,

update a main validation data set from the source domain validation data set,

update the main validation data set from the target domain validation data set, and

train a second detector using the updated main validation data set.

14 . The system of claim 12 , wherein:

the artificial intelligence logic is further configured to:

apply positive feedback to the output of the label classification head, and

apply negative feedback to the output of the domain classification head.

15 . The system of claim 14 , wherein the positive feedback is backpropagation to reinforce features similar to the source domain classifier.

16 . The system of claim 14 , wherein the negative feedback is adversarial training.

17 . A system, comprising:

means for evaluating a source domain validation data set with a first detector;

means for using annotations of an output of the first detector to generate a source domain surrogate data set;

means for training a source domain classifier with the source domain surrogate data set;

means for running a source domain entire field data set through the source domain classifier to generate a source domain field data subset;

means for evaluating the source domain field data subset with the first detector to generate a source domain final field data subset;

means for updating the source domain validation data set from the source domain final field data subset; and

means for training, using the source domain classifier, a target domain classifier to:

minimize an error function at an output of a label classification head of the target domain classifier, and

maximize the error function at an output of a domain classification head of the target domain classifier to filter features that are unique to the source domain classifier, wherein;

the target domain classifier comprises a feature extractor derived from a first portion of the source domain classifier,

the label classification head is derived from a second portion of the source domain classifier, and

the domain classification head is coupled in parallel to the label classification head.

18 . The system of claim 17 , further comprising:

means for extracting first features from the source domain validation data set using the feature extractor;

means for extracting second features from a target domain validation data set using the feature extractor;

means for running the first features through both the label classification head and the domain classification head;

means for running the second features only through the domain classification head;

means for applying positive feedback to the output of the label classification head; and

means for applying negative feedback to the output of the domain classification head.

19 . The system of claim 18 , further comprising:

means for updating a main validation data set from the source domain validation data set;

means for updating the main validation data set from the target domain validation data set; and

means for training a second detector using the updated main validation data set.

20 . The system of claim 18 , further comprising:

a digital video camera.

Assignments (3)
PATENT COLLATERAL AGREEMENT - A&R LOAN AGREEMENT Recorded Aug 21, 2023
From: WESTERN DIGITAL TECHNOLOGIES, INC.
To: JPMORGAN CHASE BANK, N.A.
Reel/Frame 064715/0001 →
PATENT COLLATERAL AGREEMENT - DDTL LOAN AGREEMENT Recorded Aug 21, 2023
From: WESTERN DIGITAL TECHNOLOGIES, INC.
To: JPMORGAN CHASE BANK, N.A.
Reel/Frame 067045/0156 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 3, 2022
From: KAH, DAMIEN; ZHONG, QIAN; XIONG, SHAOMIN; HIRANO, TOSHIKI
To: WESTERN DIGITAL TECHNOLOGIES, INC.
Reel/Frame 060712/0351 →
Continuity (1)
Related Publication 20230326183A1 · Oct 12, 2023
References Cited (15)
US 8385632B2 · Porikli · 2013 [cited by applicant]
US 20160078359A1 · Csurka et al. · 2016 [cited by applicant]
US 20160253597A1 · Bhatt et al. · 2016 [cited by applicant]
US 20170140253A1 · Wshah et al. · 2017 [cited by applicant]
US 20210406560A1 · Park · 2021 [cited by examiner]
US 20230119634A1 · Kabkab · 2023 [cited by examiner]
WO 2015192239A1 · 2015 [cited by applicant]
Brady et al.,(“Deep learning for camera data acquisition, control, and image estimation” Published Nov. 24, 2020 By “Advances in Optics and Photonics” Total 60 Pages (Year: 2020). [cited by examiner]
“Domain Adaptation and Retraining”, Modzy, Nov. 20, 2020, https://www.modzy.com/blog/domain-adaptation-and-retraining/. [cited by applicant]
Patel, V. M., et al., “Visual Domain Adaptation: A Survey of Recent Advances”, Oct. 1, 2014, <https://engineering.jhu.edu/vpatel36/wp-content/uploads/2018/08/SPM_DA_v9.pdf>. [cited by applicant]
IVmarcom, “Reducing False Alarms in Central Monitoring Stations”, Mar. 22, 2019, https://www.intelli-vision.com/2019/03/22/reducing-false-alarms-in-central-monitoring-stations/. [cited by applicant]
“Industrial AI Camera, Vision Cam AI.go”, screen capture Feb. 21, 2021, <https://imago-technologies.com/ai-camera/?gclid=EAlalQobChMlqffD5bzE9AIVQZImAh1wVATKEAMYASAAEgJqcfD_BwE>. [cited by applicant]
Zhang C., et al., “Improving Domain-Adaptive Person Re-Identification by Dual-Alignment Learning With Camera-Aware Image Generation”, IEEE Transactions on Circuits and Systems for VideoTechnology ( vol. 31, Issue: 11, N… [cited by applicant]
Wan, M. et al., “Deep Visual Domain Adaptation: A Survey”, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Apr. 25, 2018, <https://www.researchgate.net/publicatio… [cited by applicant]
Bermudez, D.V., “Domain Adaptation of virtual and real world for pedestrian detection”, Universitat Autonoma de Barcelona, Jun. 17, 2013, <https://www.tesisenred.net/bitstream/handle/10803/125977/dvb1de1.pdf?sequence=1&… [cited by applicant]