基于改进YOLO-v4的室内人脸快速检测方法

doi:10.3778/j.issn.1002-8331.2201-0309

摘要/Abstract

摘要： 针对室内安防工程应用中检测人脸角度不同、光照变化、部分遮挡、模糊等复杂工况，提出一种基于改进YOLO-v4的室内人脸快速检测方法。基于深度可分离残差网络结构改进YOLO-v4主干网络，提升模型检测效率；在构建特征金字塔过程中引入注意力机制，自适应调整通道特征与空间特征权重，提升模型特征提取能力。实验结果表明，该方法对室内人脸图像的检测精度与速度分别为92.53%与35?frame/s，相比原YOLO-v4算法及其他主流人脸检测算法，具有更好的检测精度与效率，因此可应用于移动机器人的室内人脸实时检测。

关键词: 深度学习, 特征融合, 人脸检测, 注意力机制

Abstract: A fast indoor face detection method based on improved YOLO-v4 is proposed in this paper, under the complex working conditions of human faces with different angles, varying illumination, partial occlusion, and blurring in indoor security engineering applications. The YOLO-v4 backbone network is improved based on the deep separable residual network structure to increase the detection efficiency of the model. The attention mechanism is introduced during the process of constructing the feature pyramid, which can adaptively adjust the weights of the channel features and spatial features, to improve the feature extraction capability of the model. The experimental results show that the accuracy and speed of the proposed method are 92.53% and 35 frame/s, respectively, for indoor face images, which has relatively better detection precision and efficiency, compared with the original YOLO-v4 algorithm, and other mainstream face detection algorithms. The proposed method therefore can be applied to indoor face detection of mobile robots in real time.

Key words: deep learning, feature fusion, face detection, attention mechanism

巢渊, 刘文汇, 唐寒冰, 马成霞, 王雅倩. 基于改进YOLO-v4的室内人脸快速检测方法[J]. 计算机工程与应用, 2022, 58(14): 105-113.

CHAO Yuan, LIU Wenhui, TANG Hanbing, MA Chengxia, WANG Yaqian. Fast Indoor Face Detection Method Based on Improved YOLO-v4[J]. Computer Engineering and Applications, 2022, 58(14): 105-113.

参考文献

[1] VIOLA P，JONES M.Rapid object detection using aboosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2001：511-518.
[2] IENHART R，MAYDT J.An extended set of Haar-like features for rapid object detection[C]//Proceedings of International Conference on Image Processing.New York：IEEE，2002：900-903.
[3] 胡丽乔，仇润鹤.一种自适应加权HOG特征的人脸识别算法[J].计算机工程与应用，2017，53（3）：164-168.
HU L Q，QIU R H.Face recognition based on adaptively weighted HOG[J].Computer Engineering and Applications，2017，53（3）：164-168.
[4] JIANG H，LEARNED-MILLER E.Face detection with the Faster R-CNN[C]//IEEE International Conference on Automatic Face & Gesture Recognition，2017：650-657.
[5] 李泽琛，李恒超，胡文帅，等.多尺度注意力学习的Faster R-CNN口罩人脸检测模型[J].西南交通大学学报，2021，56（5）：1002-1010.
LI Z C，LI H C，HU W S，et al.Masked face detection model based on multi-scale attention-driven Faster RCNN[J].Journal of Southwest Jiaotong University，2021，56（5）：1002-1010．
[6] WU W，YIN Y，WANG X，et al.Face detection with different scales based on faster R-CNN[J].IEEE Transactions on Cybernetics，2019，49（11）：4017-4028.
[7] ZHANG K，ZHANG Z，LI Z，et al.Joint face detection and alignment using multi-task cascaded convolutional networks[J].arXiv：1604.02878，2016.
[8] DENG J，GUO J，ZHOU Y，et al.RetinaFace：single-stage dense face localisation in the wild[J].arXiv：1905.00641，2019.
[9] REDMON J，FARHADI A.YOLO9000 better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：7263-7271.
[10] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767，2018.
[11] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[12] 薛均晓，程君进，张其斌，等.改进轻量级卷积神经网络的复杂场景口罩佩戴检测方法[J].计算机辅助设计与图形学学报，2021，33（7）：1045-1054.
XUE J X，CHENG J J，ZHANG Q B，et al.Improved efficient convolutional neural networks for complex scene mask-wearing detection[J].Journal of Computer-Aided Design & Computer Graphics，2021，33（7）：1045-1054.
[13] 李亚，张雨楠，彭程，等.基于多任务学习的人脸属性识别方法[J].计算机工程，2020，46（3）：229-236.
LI Y，ZHANG Y N，PENG C，et al.Face attributes recognition method based on multi-task learning[J].Computer Engineering，2020，46（3）：229-236．
[14] NGUYEN Q H，TRUONG H V.Real-time human ear detection based on the joint of Yolo and RetinaFace[J].Complexity，2021：1-11.
[15] 李闻，李小春，闫昊雷.基于改进YOLO v3的PCB缺陷检测[J].电光与控制，2022，29（4）：106-111.
LI W，LI X C，YAN H L.PCB defect detection based on improved YOLO v3[J].Electronics Optics & Control，2022，29（4）：106-111.
[16] 华泽玺，施会斌，罗彦，等.基于轻量级YOLO-v4模型的变电站数字仪表检测识别[J/OL].西南交通大学学报：1-11[2021-11-28].http：//kns.cnki.net/kcms/detail/51.1277.U.20211027.
1050.003.html.
HUA Z X，SHI H B，LUO Y，et al.Detection and recognition of digital instruments based on lightweight YOLO-v4 model at substations[J/OL].Journal of Southwest Jiaotong University：1-11[2021-11-28].http：//kns.cnki.net/kcms/detail/51.1277.U.20211027.1050.003.html.
[17] 邹聪，梁永全.基于YOLO V3算法的输电线路鸟类检测[J].计算机应用与软件，2021，38（10）：164-167.
ZOU C，LIANG Y Q.Bird detection of transmission line based on YOLO V3 algorithm[J].Computer Applications and Software，2021，38（10）：164-167.
[18] 朱超平，杨艺.基于YOLO2和ResNet算法的监控视频中的人脸检测与识别[J].重庆理工大学学报（自然科学），2018，32（8）：170-175.
ZHU C P，YANG Y.Face detection and recognition in monitoring video based on YOLO2 and ResNet algorithm[J].Journal of Chongqing University of Technology（Natural Science），2018，32（8）：170-175.
[19] 房国志，孙康瞳.多尺度YOLO人脸年龄估计方法研究[J].计算机工程与应用，2019，55（21）：135-141.
FANG G Z，SUN K T.Research on face age estimation based on multi-scale YOLO model[J].Computer Engineering and Applications，2019，55（21）：135-141.
[20] 邓珍荣，白善今，马富欣，等.改进YOLO的密集小尺度人脸检测方法[J].计算机工程与设计，2020，41（3）：874-879.
DENG Z R，BAI S J，MA F X，et al.Improved YOLO dense small-scale face detection method[J].Computer Engineering and Design，2020，41（3）：874-879.
[21] 张路达，邓超.多尺度融合的YOLOv3人群口罩佩戴检测方法[J].计算机工程与应用，2021，57（16）：283-290.
ZHANG L D，DENG C.Multi-scale fusion of YOLOv3 crowd mask wearing detection method[J].Computer Engineering and Applications，2021，57（16）：283-290.
[22] 葛青青，张智杰，袁珑，等.融合环境特征与改进YOLOv4的安全帽佩戴检测[J].中国图象图形学报，2021，26（12）：2904-2917.
GE Q Q，ZHANG Z J，YUAN L，et al.Safety helmet wearing detection method of fusing environmental features and improved YOLOv4[J].Journal of Image and Graphics，2021，26（12）：2904-2917.
[23] YANG F，LU H，YANG M H.Robust superpixel tracking[J].IEEE Transactions on Image Processing，2014，23（4）：1639-1651.
[24] YU Q，DINH T B，MEDIONI G.Online tracking and reacquisition using co-trained generative and discriminative trackers[C]//European Conference on Computer Vision，2008：678-691.
[25] WU Y，CHENG J，WANG J，et al.Real-time probabilistic covariance tracking with efficient model update[J].IEEE Transactions on Image Processing，2012，21（5）：2824-2837.
[26] JEPSON A D，FLEET D J，EL-MARAGHI T F.Robust online appearance models for visual tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2003，25（10）：1296-1311.
[27] LIU Z，LUO P，WANG X，et al.Deep learning face attributes in the wild[C]//IEEE International Conference on Computer Vision（ICCV），2015：3730-3738.
[28] YANG S，LUO P，LOY C，et al.WIDER FACE：a face detection benchmark[C]//IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016：5525-5533.
[29] ARTHUR D，VASSILVITSKII S.K-Means++：the advantages of careful seeding[C]//Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms，2007：7-9.
[30] JIE H，LI S，GANG S，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（8）：2011-2023.
[31] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[C]//European Conference on Computer Vision.Cham：Springer，2018：3-19.
[32] PAN S J，QIANG Y.A survey on transfer learning[J].IEEE Transactions on Knowledge and Data Engineering，2010，22（10）：1345-1359.