Real-time face blurring method based on head skeleton point detection

doi:10.11772/j.issn.1001-9081.2025020246

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (2): 596-603.DOI: 10.11772/j.issn.1001-9081.2025020246

• Multimedia computing and computer simulation • Previous Articles

Real-time face blurring method based on head skeleton point detection

Ping HUANG¹(), Qing LI¹, Haifeng QIU¹, Chengsi WANG¹, Anzi HUANG¹, Xiang ZHANG²

^1.Shenzhen Power Supply Bureau Company Limited，Shenzhen Guangdong 518001，China
^2.School of Computer Science，Nanjing University，Nanjing Jiangsu 210023，China

Received:2025-03-12 Revised:2025-06-05 Accepted:2025-06-09 Online:2025-06-10 Published:2026-02-10
Contact: Ping HUANG
About author:HUANG Ping， born in 1993， engineer. Her research interests include power system construction and integration. Email:1021328790@qq.com
LI Qing， born in 1988， M. S.， senior engineer. Her research interests include power information system development.
QIU Haifeng， born in 1981， M. S.， senior engineer. His research interests include transmission and transformation engineering design.
WANG Chengsi， born in 1986， M. S.， senior engineer. His research interests include power civil engineering management.
HUANG Anzi， born in 1980， M. S.， senior engineer. His research interests include power project management.
ZHANG Xiang， born in 1999， M. S. His research interests include computer vision.

基于头部骨骼点检测的实时人脸打码方法

黄萍¹(), 李清¹, 邱海枫¹, 王程斯¹, 黄安子¹, 张翔²

^1.深圳供电局有限公司，广东深圳 518001
^2.南京大学计算机学院，南京 210023

通讯作者: 黄萍
作者简介:黄萍（1993—），女，广东韶关人，工程师，主要研究方向：电力系统建设与集成 Email:1021328790@qq.com
李清（1988—），女，湖南衡阳人，高级工程师，硕士，主要研究方向：电力信息系统开发
邱海枫（1981—），男，广东湛江，高级工程师，硕士，主要研究方向：输变电工程设计
王程斯（1986—），男，广东梅州人，高级工程师，硕士，主要研究方向：电力土建工程管理
黄安子（1980—），男，广东深圳人，高级工程师，硕士，主要研究方向：电力工程项目管理
张翔（1999—），男，江苏常熟人，硕士，主要研究方向：计算机视觉。

Abstract

Abstract:

In power monitoring scenarios， real-time monitoring and analysis of personnel behavior are crucial for ensuring the safe and stable operation of power systems. However， directly exposing facial information in monitoring videos without proper processing poses serious privacy risks. Traditional face detection-based blurring methods face challenges such as insufficient robustness and high computational costs in complex power environments， making them hard to meet both accuracy and real-time requirements. To address these issues， a real-time face blurring method based on head skeleton point detection was proposed. Firstly， a lightweight head skeleton point detection framework based on a hierarchical processing strategy was designed to locate personnel regions in compressed videos rapidly and stitch the cropped areas at original resolution to batch-detect head skeleton points of all the people， thus improving detection efficiency and accuracy. Secondly， an adaptive inter-frame optimization strategy was introduced， to use frame differencing to detect changes in the number of personnel quickly and adjust detection frequency dynamically by incorporating a tracking mechanism for personnel detection boxes， thereby reducing redundant computational overhead effectively. Finally， a prototype system for real-time face blurring was constructed on edge nodes， and its performance was validated through experiments. Experimental results indicate that taking the KAPAO-S model as an example， the proposed method improves the face blurring accuracy in monitoring videos by 3.6 percentage points and reduces the processing time per frame by 2.5 ms approximately compared to the original model， thereby ensuring accuracy and real-time performance at the same time.

Key words: face blurring, skeleton point detection, lightweighting, real-time, video monitoring

摘要：

在电力监控场景中，人员行为的实时监控与分析对保障电力系统的安全稳定运行具有重要意义。然而，监控视频中的人脸信息若未经处理直接暴露将带来严重的隐私泄露风险。传统基于人脸检测的打码方法在复杂的电力环境下存在鲁棒性不足以及计算开销大等问题，难以满足人脸打码的精确性和实时性需求。针对上述问题，提出一种基于头部骨骼点检测的实时人脸打码方法。首先，设计一种基于分层处理策略的头部骨骼点轻量化检测框架，在压缩视频中快速定位人员区域，并在原始分辨率下拼接裁剪区域以批量检测所有人员的头部骨骼点，从而提升检测的效率与精度；其次，提出一种自适应帧间优化策略以利用帧差法快速检测人员数量的变化，并结合人员检测框追踪机制动态调整检测频率，有效减少冗余的计算开销；最后，在边缘节点搭建一套实时人脸打码的原型系统，并通过实验验证性能。实验结果表明，以KAPAO-S模型为例，所提方法相较于原始模型，对监控视频中人脸的打码准确率提高了3.6个百分点，每帧处理时间减少了约2.5 ms，兼顾精确性和实时性。

关键词: 人脸打码, 骨骼点检测, 轻量化, 实时, 视频监控

CLC Number:

TP391.4

Ping HUANG, Qing LI, Haifeng QIU, Chengsi WANG, Anzi HUANG, Xiang ZHANG. Real-time face blurring method based on head skeleton point detection[J]. Journal of Computer Applications, 2026, 46(2): 596-603.

黄萍, 李清, 邱海枫, 王程斯, 黄安子, 张翔. 基于头部骨骼点检测的实时人脸打码方法[J]. 《计算机应用》唯一官方网站, 2026, 46(2): 596-603.

Figures/Tables 13

Fig. 1 System framework

Fig. 2 Performance comparison of different pose estimation models at various image resolutions

Fig. 3 Performance comparison of different pose estimation models

Fig. 4 Skeleton point detection based on hierarchical processing

Fig. 5 Generation of local detection boxes

Fig. 6 Image stitching after cropping

Fig. 7 Detection of change in number of people

Fig. 8 Optimized flow for head skeleton point detection

Fig. 9 Schematic diagram of pixel blurring method

Fig. 10 Overall performance comparison

Fig. 11 Impact of dynamic frame-skipping strategy

Fig. 12 Impact of time of re-generating local detection boxes

Fig. 13 Impact of detection model input size

References 24

[1]	VIOLA P， JONES M J. Robust real-time face detection［J］. International Journal of Computer Vision， 2004， 57（2）： 137-154.
[2]	DHIVAKAR B， SRIDEVI C， SELVAKUMAR S， et al. Face detection and recognition using skin color［C］// Proceedings of the 3rd International Conference on Signal Processing， Communication and Networking. Piscataway： IEEE， 2015： 1-7.
[3]	ZHANG K， ZHANG Z， LI Z， et al. Joint face detection and alignment using multitask cascaded convolutional networks［J］. IEEE Signal Processing Letters， 2016， 23（10）： 1499-1503.
[4]	DENG J， GUO J， VERVERAS E， et al. RetinaFace： single-shot multi-level face localisation in the wild［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 5202-5211.
[5]	谢金衡，张炎生. 基于深度残差和特征金字塔网络的实时多人脸关键点定位算法［J］. 计算机应用， 2019， 39（12）： 3659-3664.
	XIE J H， ZHANG Y S. Real-time multi-face landmark localization algorithm based on deep residual and feature pyramid neural network［J］. Journal of Computer Applications， 2019， 39（12）： 3659-3664.
[6]	任海培，李腾. 面向移动平台人脸检测的FaceYoLo算法［J］. 计算机应用， 2020， 40（4）： 1002-1008.
	REN H P， LI T. FaceYoLo algorithm for face detection on mobile platform［J］. Journal of Computer Applications， 2020， 40（4）： 1002-1008.
[7]	YU Z， HUANG H， CHEN W， et al. YOLO-FaceV2： a scale and occlusion aware face detector［J］. Pattern Recognition， 2024， 155： No.110714.
[8]	GIRSHICK R. Fast R-CNN［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2015： 1440-1448.
[9]	龚锐，丁胜，章超华，等. 基于深度学习的轻量级和多姿态人脸识别方法［J］. 计算机应用， 2020， 40（3）： 704-709.
	GONG R， DING S， ZHANG C H， et al. Lightweight and multi-pose face recognition method based on deep learning［J］. Journal of Computer Applications， 2020， 40（3）： 704-709.
[10]	SUN K， XIAO B， LIU D， et al. Deep high-resolution representation learning for human pose estimation［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 5686-5696.
[11]	FANG H S， LI J， TANG H， et al. AlphaPose： whole-body regional multi-person pose estimation and tracking in real-time［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2023， 45（6）： 7157-7173.
[12]	DUAN H， ZHAO Y， CHEN K， et al. Revisiting skeleton-based action recognition［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 2959-2968.
[13]	DUAN H， WANG J， CHEN K， et al. PYSKL： towards good practices for skeleton action recognition［C］// Proceedings of the 30th ACM International Conference on Multimedia. New York： ACM， 2022： 7351-7354.
[14]	CAO Z， SIMON T， WEI S E， et al. Realtime multi-person 2D pose estimation using part affinity fields［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 1302-1310.
[15]	JIN S， XU L， XU J， et al. Whole-body human pose estimation in the wild［C］// Proceedings of the 2020 European Conference on Computer Vision， LNCS 12354. Cham： Springer， 2020： 196-214.
[16]	NGUYEN V N， GROUEIX T， SALZMANN M， et al. GigaPose： fast and robust novel object pose estimation via one correspondence［C］// Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2024： 9903-9913.
[17]	WEN B， YANG W， KAUTZ J， et al. FoundationPose： unified 6D pose estimation and tracking of novel objects［C］// Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2024： 17868-17879.
[18]	南京大学. 基于两阶段人体骨骼点检测的人脸视频打码系统及方法： 202410536206.X［P］. 2024-08-06.
	Nanjing University. Face video blurring system and method based on two-stage human skeleton point detection： 202410536206.X［P］. 2024-08-06.
[19]	McNALLY W， VATS K， WONG A， et al. Rethinking keypoint representations： modeling keypoints and poses as objects for multi-person human pose estimation［C］// Proceedings of the 2022 European Conference on Computer Vision， LNCS 13666. Cham： Springer， 2022： 37-54.
[20]	LIN T Y， MAIRE M， BELONGIE S， et al. Microsoft COCO： common objects in context［C］// Proceedings of the 2014 European Conference on Computer Vision， LNCS 8693. Cham： Springer， 2014： 740-755.
[21]	LIU H， CHEN Q， TAN Z， et al. Group Pose： a simple baseline for end-to-end multi-person pose estimation［C］// Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2023： 14983-14992.
[22]	YANG J， ZENG A， LIU S， et al. Explicit box detection unifies end-to-end multi-person pose estimation［EB/OL］. ［2024-11-13］..
[23]	ANDRILUKA M， IQBAL U， INSAFUTDINOV E， et al. PoseTrack： A benchmark for human pose estimation and tracking［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 5167-5176.
[24]	MAJI D， NAGORI S， MATHEW M， et al. YOLO-Pose： enhancing YOLO for multi person pose estimation using object keypoint similarity loss［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2022： 2636-2645.

Real-time face blurring method based on head skeleton point detection

基于头部骨骼点检测的实时人脸打码方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 24

Related Articles 15

Recommended Articles

Metrics

[1]	Ning CAO, Xin WEN, Yanrong HAO, Rui CAO. Lightweight motor imagery electroencephalogram decoding neural network with multi-domain feature fusion [J]. Journal of Computer Applications, 2026, 46(1): 289-296.
[2]	Dehui ZHOU, Jun ZHAO, Jinfeng CHENG. Tiny defect detection algorithm for bearing surface based on RT-DETR [J]. Journal of Computer Applications, 2025, 45(6): 1987-1997.
[3]	Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263.
[4]	Yaping DENG, Yingjiang LI. Review of YOLO algorithm and its applications to object detection in autonomous driving scenes [J]. Journal of Computer Applications, 2024, 44(6): 1949-1958.
[5]	Xiaogang SONG, Dongdong ZHANG, Pengfei ZHANG, Li LIANG, Xinhong HEI. Real-time object detection algorithm for complex construction environments [J]. Journal of Computer Applications, 2024, 44(5): 1605-1612.
[6]	Yudong PANG, Zhixing LI, Weijie LIU, Tianhao LI, Ningning WANG. Small target detection model in overlooking scenes on tower cranes based on improved real-time detection Transformer [J]. Journal of Computer Applications, 2024, 44(12): 3922-3929.
[7]	Qiumei ZHENG, Weiwei NIU, Fenghua WANG, Dan ZHAO. Dual-branch real-time semantic segmentation network based on detail enhancement [J]. Journal of Computer Applications, 2024, 44(10): 3058-3066.
[8]	Dongying ZHU, Yong ZHONG, Guanci YANG, Yang LI. Research progress on motion segmentation of visual localization and mapping in dynamic environment [J]. Journal of Computer Applications, 2023, 43(8): 2537-2545.
[9]	Qingyu JIA, Liang CHANG, Xianyi YANG, Baohua QIANG, Shihao ZHANG, Wu XIE, Minghao YANG. Real-time reconstruction method of visual information for manipulator operation [J]. Journal of Computer Applications, 2023, 43(4): 1255-1260.
[10]	Yun ZHANG, Shuying WANG, Qing ZHENG, Haizhu ZHANG. Lightweight algorithm of 3D mesh model for preserving detailed geometric features [J]. Journal of Computer Applications, 2023, 43(4): 1226-1232.
[11]	Qiangqiang QIN, Junguo LIAO, Yixun ZHOU. Small object detection algorithm based on split mixed attention [J]. Journal of Computer Applications, 2023, 43(11): 3579-3586.
[12]	Zixing YU, Shaojun QU, Xin HE, Zhuo WANG. High-low dimensional feature guided real-time semantic segmentation network [J]. Journal of Computer Applications, 2023, 43(10): 3077-3085.
[13]	Jun MA, Zhen YAO, Cuifeng XU, Shouhong CHEN. Multi-UAV real-time tracking algorithm based on improved PP-YOLO and Deep-SORT [J]. Journal of Computer Applications, 2022, 42(9): 2885-2892.
[14]	Juan WANG, Xuliang YUAN, Minghu WU, Liquan GUO, Zishan LIU. Real-time semantic segmentation method based on squeezing and refining network [J]. Journal of Computer Applications, 2022, 42(7): 1993-2000.
[15]	Hanlun LI, Jianguo REN. Malware propagation model based on characteristic behavior detection in P2P networks [J]. Journal of Computer Applications, 2022, 42(7): 2125-2131.