IP Library › Granted Patent US 12,610,061
Granted Patent B2
US 12,610,061 · App. 18/235,561 · Granted Apr 21, 2026

Method and apparatus for the region of interest encryption in hevc/h.265 video based on the coding unit

Inventors: Young-Gab Kim (Seoul, KR); Jin-Yong Yu (Seoul, KR)
Assignee: Industry-Academia Cooperation Group Of Sejong University
H04N19/167G06F21/602G06V20/49G06V40/161H04N19/119H04N19/13H04N19/159H04N19/172H04N19/70
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 12,610,061
App. No.
18/235,561
Granted
Apr 21, 2026
Kind
B2
Abstract

A method and apparatus for encrypting an ROI in a HEVC/H.265 video based on a coding unit are disclosed. The method, which is performed by an encryption apparatus, may include identifying a coding unit related to an ROI that is generated for each frame as the frames that constitute a video are partitioned as a tile, and performing selective encryption on the identified coding unit.

Claims (24)

1 . A method of encrypting a region of interest (ROI) in a video encoded with a codec corresponding to HEVC (H.265), the method being performed by an encryption apparatus and comprising:

detecting the ROI in the video by using an object detection model and obtaining coordinate data of the detected ROI;

separately identifying a tile related to the ROI and a tile not related to the ROI, based on the obtained coordinate data;

separately identifying a coding unit related to the ROI and a coding unit not related to the ROI, based on the obtained coordinate data and the identified tile related to the ROI, the identified coding unit representing a processing unit for selective encryption which is distinct from the identified tile;

restricting encryption propagation by preventing prediction processes from referencing pixel data outside of a boundary of a coding tree unit (CTU) containing the identified coding unit related to the ROI; and

performing selective encryption on one or more syntax elements corresponding to the identified coding unit related to the ROI,

wherein performing the selective encryption comprises performing the selective encryption on the identified coding unit related to the ROI based on context-adaptive binary arithmetic coding (CABAC) for parameters of the codec corresponding to HEVC (H.265);

wherein the syntax elements are selected from a group consisting of a motion vector (MV), an MV sign, a transform coefficient (TC), a TC sign, and an intra prediction mode (IPM), and

wherein the selective encryption is performed on a suffix part of a binarized representation of the syntax elements by applying an AES-CFB algorithm to perform an XOR operation between the suffix part and a generated key stream.

2 . The method of claim 1 , wherein the object detection model is trained to detect a face as an object by using learning data for object detection based on a YOLOv4 object detection algorithm.

3 . The method of claim 1 , wherein the step of separately identifying the coding unit comprises partitioning the identified coding unit into at least one prediction unit through intra prediction or inter prediction for the identified coding unit.

4 . The method of claim 3 , wherein the step of separately identifying the coding unit further comprises performing entropy encoding on the identified coding unit via a discrete coefficient transform (DCT) and quantization.

5 . The method of claim 1 , wherein performing the selective encryption comprises performing the selective encryption based on the CABAC during an entropy encoding process for the identified coding unit related to the ROI.

6 . A non-transitory computer-readable recording medium storing instructions for executing the method of claim 1 on the encryption apparatus.

7 . An encryption apparatus for encrypting a region of interest (ROI) in a video encoded with a codec corresponding to HEVC (H.265) comprising:

at least one processor configured to

detect the ROI in the video by using an object detection model and obtaining coordinate data of the detected ROI,

separately identify a tile related to the ROI and a tile not related to the ROI, based on the obtained coordinate data,

separately identify a coding unit related to the ROI and a coding unit not related to the ROI, based on the obtained coordinate data and the identified tile related to the ROI, the identified coding unit representing a processing unit for selective encryption which is distinct from the identified tile,

restrict encryption propagation by preventing prediction processes from referencing pixel data outside of a boundary of a coding tree unit (CTU) containing the identified coding unit related to the ROI, and

perform selective encryption on one or more syntax elements corresponding to the identified coding unit related to the ROI,

wherein the processor is configured to perform the selective encryption by performing the selective encryption on the identified coding unit related to the ROI based on context-adaptive binary arithmetic coding (CABAC) for parameters of the codec corresponding to HEVC (H.265);

wherein the syntax elements are selected from a group consisting of a motion vector (MV), an MV sign, a transform coefficient (TC), a TC sign, and an intra prediction mode (IPM), and

wherein the selective encryption is performed on a suffix part of a binarized representation of the syntax elements by applying an AES-CFB algorithm to perform an XOR operation between the suffix part and a generated key stream.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 18, 2023
From: KIM, YOUNG-GAB; YU, JIN-YONG
To: INDUSTRY-ACADEMIA COOPERATION GROUP OF SEJONG UNIVERSITY
Reel/Frame 064636/0380 →
Priority Claims (1)
KR 10-2022-0104051 · Aug 19, 2022 · national
Continuity (2)
Related Publication 20240163458A1 · May 16, 2024
Related Publication 20250240434A9 · Jul 24, 2025
References Cited (22)
US 11546141B1 · Guest · 2023 [cited by examiner]
US 20070296817A1 · Ebrahimi · 2007 [cited by examiner]
US 20080117295A1 · Ebrahimi · 2008 [cited by examiner]
US 20090067626A1 · Dufaux · 2009 [cited by examiner]
US 20110158470A1 · Martin · 2011 [cited by examiner]
US 20130035979A1 · Tenbrock · 2013 [cited by examiner]
US 20150125042A1 · Haden · 2015 [cited by examiner]
US 20150350659A1 · Auyeung · 2015 [cited by examiner]
US 20160050341A1 · Erdler · 2016 [cited by examiner]
US 20160165248A1 · Lainema · 2016 [cited by examiner]
US 20170076572A1 · Rao · 2017 [cited by examiner]
US 20170359596A1 · Kim · 2017 [cited by examiner]
US 20190377901A1 · Balzer · 2019 [cited by examiner]
US 20200267392A1 · Lu · 2020 [cited by examiner]
US 20230028426A1 · Nadeem · 2023 [cited by examiner]
US 20230067541A1 · Boyce · 2023 [cited by examiner]
Z. Shahid and W. Puech, “Visual Protection of HEVC Video by Selective Encryption of CABAC Binstrings,” in IEEE Transactions on Multimedia, vol. 16, No. 1, pp. 24-36, Jan. 2014 (Year: 2014). [cited by examiner]
Bochkovskiy, Alexey; Wang, Chien-Yao; Mark Liao, Hong Yuan; “YOLOv4: Optimal Speed and Accuracy of Object Detection” ; Apr. 23, 2020; available at https://arxiv.org/abs/2004.10934 (Year: 2020). [cited by examiner]
“YOLOv4—Ultralytics YOLO Docs”, retrived Oct. 19, 2024; available at https://docs.ultralytics.com/models/yolov4/ (Year: 2024). [cited by examiner]
Mousa Farajallah, “ROI Encryption for the HEVC Coded Video Contents”, Article, 2015, 1-5, 2015 IEEE International Conference on Image Processing (ICIP). [cited by applicant]
Yiqi Tew, “Region-of-Interest Encryption in HEVC Compressed Video”, Article, 2016, 1-2, 2016 International Conference on Consumer Electronics-Taiwan. [cited by applicant]
Jimin Yu, “Face Mask Wearing Detection Algorithm Based on Improved YOLO-v4”, Article, 2021, 1-21, vol. 21, Sensors. [cited by applicant]