光流估计下的移动端实时人脸检测

doi:10.11772/j.issn.1001-9081.2017092154

计算机应用 ›› 2018, Vol. 38 ›› Issue (4): 1146-1150.DOI: 10.11772/j.issn.1001-9081.2017092154

• 虚拟现实与多媒体计算 • 上一篇下一篇

光流估计下的移动端实时人脸检测

魏震宇¹, 文畅¹, 谢凯², 贺建飚³

1. 长江大学计算机科学学院, 湖北荆州 434023;
2. 长江大学电子信息学院, 湖北荆州 434023;
3. 中南大学信息科学与工程学院, 长沙 410083

收稿日期:2017-09-05 修回日期:2017-11-13 出版日期:2018-04-10 发布日期:2018-04-09
通讯作者: 文畅
作者简介:魏震宇(1997-),男,江苏泰兴人,硕士研究生,CCF会员,主要研究方向:人脸识别、图像与视频处理;文畅(1979-),女,湖北荆州人,讲师,硕士,主要研究方向:信号与信息处理、模式识别、三维建模;谢凯(1974-),男,湖北潜江人,教授,博士,主要研究方向:信号与信息处理;贺建飚(1964-),男,湖南长沙人,副教授,博士,主要研究方向:信号处理。
基金资助:
国家自然科学基金资助项目（61272147）；长江大学大学生创新创业训练计划项目（2017008）。

Real-time face detection for mobile devices with optical flow estimation

WEI Zhenyu¹, WEN Chang¹, XIE Kai², HE Jianbiao³

1. College of Computer Science, Yangtze River University, Jingzhou Hubei 434023, China;
2. College of Electronic Information, Yangtze River University, Jingzhou Hubei 434023, China;
3. College of Information Science and Engineering, Central South University, Changsha Hunan 410083, China

Received:2017-09-05 Revised:2017-11-13 Online:2018-04-10 Published:2018-04-09
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61272147), the Innovation and Entrepreneurship Training Program for Yangtze University Students (2017008)

摘要/Abstract

摘要： 为了提高移动设备人脸检测准确率，提出一种应用于移动设备的实时人脸检测算法。通过改进Viola-Jones方法进行人脸区域快速分割，在不损失速度的情况下提高分割精度；同时应用了光流估计方法将卷积神经网络子网络在离散关键帧上的特征提取结果传播至非关键帧，提高神经网络实际检测运行效率。实验使用YouTube视频人脸数据库、自建20人各1 min正位人脸视频数据库和实际检测项目在不同分辨率下进行，实验结果表明运行速度在2.35帧/秒~22.25帧/秒，达到了一般人脸检测水平；人脸检测在10%误检率下召回率由Viola-Jones的65.93%提高到82.5%~90.8%，接近卷积神经网络检测精度，满足了移动设备实时人脸检测的速度和精度要求。

关键词: 人脸检测, 快速区域分割, 瀑布型分类器, 卷积神经网络, 光流估计

Abstract: To improve the face detection accuracy of mobile devices, a new real-time face detection algorithm for mobile devices was proposed. The improved Viola-Jones was used for a quick region segmentation to improve segmentation precision without decreasing segmentation speed. At the same time, the optical flow estimation method was used to propagate the features of discrete keyframes extracted by the sub-network of a convolution neural network to other non-keyframes, which increased the efficiency of convolution neural network. Experiments were conducted on YouTube video face database, a self-built one-minute face video database of 20 people and the real test items at different resolutions. The results show that the running speed is between 2.35 frames per second and 22.25 frames per second, reaching the average face detection level; the recall rate of face detection is increased from 65.93% to 82.5%-90.8% at rate of 10% false alarm, approaching the detection accuracy of convolution neural network, which satisfies the speed and accuracy requirements for real-time face detection of mobile devices.

Key words: face detection, quick region segmentation, cascade classifier, Convolution Neural Network (CNN), optical flow estimation

中图分类号:

TP3941

魏震宇, 文畅, 谢凯, 贺建飚. 光流估计下的移动端实时人脸检测[J]. 计算机应用, 2018, 38(4): 1146-1150.

WEI Zhenyu, WEN Chang, XIE Kai, HE Jianbiao. Real-time face detection for mobile devices with optical flow estimation[J]. Journal of Computer Applications, 2018, 38(4): 1146-1150.

参考文献

[1] 魏玮,马瑞,王小芳. 视频中人脸位置的定量检测[J]. 计算机应用, 2017, 37(3):801-805.(WEI W, MA R, WANG X F. Quantitative detection of face location in videos[J]. Journal of Computer Applications, 2017, 37(3):801-805.)
[2] LI Q, NIAZ U, MERIALDO B. An improved algorithm on Viola-Jones object detector[C]//Proceedings of the 201210th International Workshop on Content-Based Multimedia Indexing. Piscataway, NJ:IEEE, 2012:55-60.
[3] ELMAGHRABY A, ABDALLA M, ENANY O, et al. Detect and analyze face parts information using Viola-Jones and geometric approaches[J]. International Journal of Computer Applications, 2014, 101(3):23-28.
[4] 朱承志.基于OpenCV的人脸检测与跟踪[J]. 计算机工程与应用, 2012, 48(26):157-161.(ZHU C Z. Face detection and tracking based on OpenCV[J]. Computer Engineering and Applications, 2012, 48(26):157-161.)
[5] BRUCE B R, AITKEN J M, PETKE J. Deep parameter optimisation for face detection using the Viola-Jones algorithm in OpenCV[C]//SSBSE 2016:Proceedings of 8th International Symposium, LNCS 9962. Berlin:Springer, 2016:238-243.
[6] 孔英会,王之涵, 车辚辚. 基于卷积神经网络(CNN)和CUDA加速的实时视频人脸识别[J]. 科学技术与工程, 2016, 16(35):96-100.(KONG Y H, WANG Z H, CHE L L. Real-time face recognition in videos based on Convolutional Neural Networks(CNN) and CUDA[J]. Science Technology & Engineering, 2016, 16(35):96-100.)
[7] JIANG H, LEARNEDMILLER E. Face detection with the faster R-CNN[C]//Proceedings of the 201712th IEEE International Conference on Automatic Face & Gesture Recognition. Washington, DC:IEEE Computer Society, 2017:650-657.
[8] QIN H, YAN J, LI X, et al. Joint training of cascaded CNN for face detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:3456-3465.
[9] 卢宏涛, 张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述[J]. 数据采集与处理, 2016, 31(1):1-17.(LU H T, ZHANG Q C. Applications of deep convolutional neural network in computer vision[J]. Journal of Data Acquisition and Processing, 2016, 31(1):1-17.)
[10] KONG K H, KANG D S. A study of face detection algorithm using CNN based on symmetry-LGP & uniform-LGP and the skin color[EB/OL].[2017-05-10]. http://onlinepresent.org/proceedings/vol139_2016/30.pdf.
[11] ZHU X, XIONG Y, DAI J, et al. Deep feature flow for video recognition[EB/OL].[2017-05-10]. https://arxiv.org/abs/1611.07715.
[12] Google. Camera.PreviewCallback[EB/OL].[2017-08-22]. https://developer.android.com/reference/android/hardware/Camera.PreviewCallback.html.
[13] Google. Camera.Parameters[EB/OL].[2017-08-22]. https://developer.android.com/reference/android/hardware/Camera.Parameters.html#setPreviewFormat(int).
[14] YANG S, LUO P, LOY C C, et al. From facial parts responses to face detection:a deep learning approach[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2015:3676-3684.
[15] WEDEL A, CREMERS D. Stereo Scene Flow for 3D Motion Analysis[M]. Berlin:Springer, 2011:5-30.
[16] WOLF L, HASSNER T, MAOZ I. Face recognition in unconstrained videos with matched background similarity[C]//Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2011:529-534.

光流估计下的移动端实时人脸检测

Real-time face detection for mobile devices with optical flow estimation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[2]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[3]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[4]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[5]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[6]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[7]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[8]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[9]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[10]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[11]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[12]	谭道强, 曾诚, 乔金霞, 张俊. 基于混合注意力模型的阴影检测方法[J]. 计算机应用, 2021, 41(7): 2076-2081.
[13]	武光利, 李雷霆, 郭振洲, 王成祥. 基于改进的双向长短期记忆网络的视频摘要生成模型[J]. 计算机应用, 2021, 41(7): 1908-1914.
[14]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[15]	吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1939-1946.