一种复杂场景下的视频流人脸隐私保护技术

doi:10.11959/j.issn.1000-0801.2021015

Abstract

Abstract:

During the process of monitoring video surveillance, potential risks of leaking personal privacy information may occur due to the exposure of facial information to the surveillance video.It is necessary to mosaic the pedestrian privacy information in the real-time video stream.At present, the commonly used coding method based on face detection is heavily affected by pedestrian appearances and illumination, which often leads to weak real-time performance and undetected errors.To solve the problems above, a multi-detection model was proposed, combining face detection algorithm, target object detection algorithm and pre-frame association detection method, and compared with the traditional face detection model.Experimental results show that the recall rate of the proposed model is 532% higher than that of the traditional face detection algorithm.

Key words: face privacy protection, face mosaic, object detection

CLC Number:

TP311

Chi ZHANG, Ye LU, Yuping LUO, Xiaokai SUN, Hanke ZHU. A novel approach for face privacy protection based on surveillance video in complex scene[J]. Telecommunications Science, 2021, 37(1): 94-101.

Figures/Tables 7

References 13

[1]	毕玉谦, 洪霄 . 民事诉讼生成权利规制探析——以“人脸识别第一案”为切入点[J]. 法学杂志, 2020,41(3): 53-62.
	BI Y Q , HONG X . Research on regulations of generating rRights in civil litigation:based on the first case of facial recognition[J]. Law Science Magazine, 2020,41(3): 53-62.
[2]	BRADSKI G , KAEHLER A . Learning openCV:computer vision with the openCV library[J]. IEEE Robotics ＆ Automation Magazine, 2008(9): 100.
[3]	陈玲 . 人脸检测技术综述[J]. 科学与信息化, 2018(16): 1-.
	CHEN L . Overview of face detection technology[J]. Technology and Information, 2018(16): 1.
[4]	侯小毛, 徐仁伯 . 云环境中考虑隐私保护的人脸图像识别[J]. 沈阳工业大学学报, 2018(2): 203-207.
	HOU X M , XU R B . Face image recognition based on privacy protection in cloud environment[J]. Journal of Shenyang University of Technology, 2018(2): 203-207.
[5]	张啸剑, 付聪聪, 孟小峰 . 面向人脸图像发布的差分隐私保护[J]. 中国图像图形学报, 2018,23(9): 1305-1315.
	ZHANG X J , FU C C , MENG X F . Facial image publication with differential privacy[J]. Journal of Image and Graphics, 2018,23(9): 1305-1315.
[6]	PAPAGEORGIOU C P , OREN M , POGGIO T . A general framework for object detection[C]// Proceedings of the International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 1998: 555-562.
[7]	崔鹏, 燕天天 . 融合YCbCr肤色模型与改进的Adaboost算法的人脸检测[J]. 哈尔滨理工大学学报, 2018(2): 91-96.
	CUI P , YAN T T . Face detection combining the YCbCr skin color model with improved adaboost algorithm[J]. Journal of Harbin University of Science and Technology, 2018(2): 91-96.
[8]	CHEN P H , LIN C J , SCHLKOPF B . A tutorial on ν-support vector machines[J]. Applied Stochastic Models in Business and Industry, 2005,21(2): 111-136.
[9]	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.
[10]	陈正斌, 叶东毅, 朱彩霞 ,等. 基于改进 YOLOv3 的目标识别方法[J]. 计算机系统应用, 2020,29(1): 49-58.
	CHEN Z B , YE D Y , ZHU C X ,et al. Object recognition method based on improved YOLOv3[J]. Computer Systems Applications, 2020,29(1): 49-58.
[11]	LIN T Y , MAIRE M S , BELONGIE J ,et al. Microsoft COCO:common objects in context[C]// Proceedings of European Conference on Computer Vision.[S.l:s.n.], 2014: 740-755.
[12]	刘卫华, 吴丹 . 基于 OpenCV 的人脸检测[J]. 科技创新与应用, 2019(31): 18-19.
	LIU W H , WU D . Face detection based on OpenCV[J]. Technology Innovation and Application, 2019(31): 18-19.
[13]	金翠, 王洪元, 陈首兵 . 基于随机擦除行人对齐网络的行人重识别方法[J]. 山东大学学报:工学版, 2018,48(6): 71-77.
	JIN C , WANG H Y , CHEN S B . Person re-identification based on random erasing pedestrian alignment network method[J]. Journal of Shandong University (Engineering Science), 2018,48(6): 71-77.

Metrics

Recommended 0

No Suggested Reading articles found!

对比项		特征图
对比项	13×13	26×26	52×52
感受野	大	中	小
先验框	（116×90）（156×198）（373×326）	（30×61）（62×45）（59×119）	（10×13）（16×30）（33×23）

	模型检测人脸数总数	检测正确人脸数	真实人脸数	准确率	召回率
Haar-like	16	16	337	100.00%	4.75%
MTCNN	52	52	337	100.00%	15.43%
多检测模型	334	329	337	98.50%	97.63%

A novel approach for face privacy protection based on surveillance video in complex scene

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 13

Related Articles 2

Metrics

Recommended 0

[1]	Tingting ZHANG,Jianwu ZHANG,Chunsheng GUO,Huahua CHEN,Di ZHOU,Yansong WANG,Aihua XU. A survey of image object detection algorithm based on deep learning [J]. Telecommunications Science, 2020, 36(7): 92-106.
[2]	Xiaohui Guan,Yaguan Qian,Zhimin Zhou. Object Detection and Tacking Algorithm in Intelligent Monitoring System [J]. Telecommunications Science, 2011, 27(12): 81-84.