基于MS-KCF模型的图像序列中人脸快速稳定检测

doi:10.11772/j.issn.1001-9081.2018020363

计算机应用 ›› 2018, Vol. 38 ›› Issue (8): 2192-2197.DOI: 10.11772/j.issn.1001-9081.2018020363

基于MS-KCF模型的图像序列中人脸快速稳定检测

叶远征¹, 李小霞^1,2, 李旻择¹

1. 西南科技大学信息工程学院, 四川绵阳 621010;
2. 特殊环境机器人技术四川省重点实验室(西南科技大学), 四川绵阳 621010

收稿日期:2018-02-09 修回日期:2018-03-15 出版日期:2018-08-10 发布日期:2018-08-11
通讯作者: 李小霞
作者简介:叶远征(1992-),男,安徽阜阳人,硕士研究生,主要研究方向:机器学习、模式识别;李小霞(1976-),女,四川安岳人,教授,博士,主要研究方向:模式识别、机器视觉;李旻择(1992-),男,四川南充人,硕士研究生,主要研究方向:机器学习、模式识别。
基金资助:
国家自然科学基金资助项目（61771411）。

Rapid stable detection of human faces in image sequence based on MS-KCF model

YE Yuanzheng¹, LI Xiaoxia^1,2, LI Minze¹

1. School of Information Engineering, Southwest University of Science and Technology, Mianyang Sichuan 621010, China;
2. Key Laboratory of Robot Technology Used for Special Environment of Sichuan Province(Southwest University of Science and Technology), Mianyang Sichuan 621010, China

Received:2018-02-09 Revised:2018-03-15 Online:2018-08-10 Published:2018-08-11
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61771411).

摘要/Abstract

摘要： 为快速稳定地检测图像序列中角度变化较大、遮挡较为严重的人脸，结合快速精确的目标检测模型MobileNet-SSD （MS）和快速跟踪模型核相关滤波（KCF），提出一种新的自动检测-跟踪-检测（DTD）模式，即MS-KCF人脸检测模型。首先，利用MS模型快速精确地对人脸进行检测，并且更新跟踪模型；其次，将检测到的人脸坐标信息输入到KCF跟踪模型中进行稳定的跟踪，并加快整体的检测速度；最后，为了防止跟踪丢失，跟踪数帧后再次更新检测模型，重新对人脸进行检测。实验显示，在FDDB人脸检测基准中，MS-KCF模型的召回率为93.60%；在WIDER FACE人脸检测基准的Easy、Medium和Hard数据集中，MS-KCF模型的召回率分别为93.11%、92.18%和82.97%，平均速度为193帧/s。实验结果表明，MS-KCF模型具有稳定性和快速性，在图像序列中对严重遮挡和角度变化大的人脸具有很好的检测效果。

关键词: 人脸检测, 图像序列, 卷积神经网络, 核相关滤波

Abstract: In order to quickly and stably detect the faces with large change of angle and serious occlusion in image sequence, a new automatic Detection-Tracking-Detection (DTD) model was proposed by combining the fast and accurate target detection model MobileNet-SSD (MS) and the fast tracking model Kernel Correlation Filtering (KCF), namely MS-KCF face detection model. Firstly, the face was detected quickly and accurately by using MS model, and the tracking model was updated. Secondly, the detected face coordinate information was input into the KCF tracking model to track steadily, and the overall detection speed was accelerated. Finally, to prevent tracking loss, the detection model was updated again after tracking several frames, then the face was detected again. The recall of MS-KCF model in the FDDB face detection benchmark was 93.60%; the recall in Easy, Medium and Hard data sets of WIDER FACE benchmark were 93.11%, 92.18% and 82.97%, respectively; the average speed was 193 frames per second. Experimental results show that the MS-KCF model is stable and fast, which has a good detection effect on the faces with serious shadows and large angle changes.

Key words: face detection, image sequence, Convolutional Neural Network (CNN), Kernel Correlation Filtering (KCF)

中图分类号:

TP391.4

叶远征, 李小霞, 李旻择. 基于MS-KCF模型的图像序列中人脸快速稳定检测[J]. 计算机应用, 2018, 38(8): 2192-2197.

YE Yuanzheng, LI Xiaoxia, LI Minze. Rapid stable detection of human faces in image sequence based on MS-KCF model[J]. Journal of Computer Applications, 2018, 38(8): 2192-2197.

参考文献

[1] 鲍可进,姚成.基于双核数字信号处理器的人脸识别门禁系统[J].计算机应用,2010,30(9):2553-2555. (BAO K J, YAO C. Access control system based on dual-core digital signal processor and face recognition[J]. Journal of Computer Applications, 2010, 30(9):2553-2555.)
[2] 黄凯奇,陈晓棠,康运锋,等.智能视频监控技术综述[J].计算机学报,2015,20(6):1093-1118. (HANG K Q, CHEN X T, KANG Y F, et al. Intelligent visual surveillence:a review[J]. Chinese Journal of Computers, 2015, 20(6):1093-1118.)
[3] 李俊,谢维信,李良群,等.基于模糊空时线索的多目标在线跟踪算法[J].电子学报,2017,45(3):513-519. (LI J, XIE W X, LI L Q, et al. Online multiple target tracking algorithm based on fuzzy spatio-temporal cues[J]. Acta Electronica Sinica, 2017, 45(3):513-519.)
[4] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]//CVPR 2001:Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2001:511-518.
[5] OJALA T, PIETIKÄINEN M, MÄENPÄÄ T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 24(7):971-987.
[6] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[7] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//CVPR 2005:Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2005:886-893.
[8] SCHAPIRE R E, FREUND Y, BARTLETT P, et al. Boosting the margin:a new explanation for the effectiveness of voting methods[J]. The Annals of Statististics, 1998, 26(5):1651-1686.
[9] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[10] FORSYTH D. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 47(2):6-7.
[11] EVERINGHAM M, ZISSERMAN A, WILLIAMS C K I, et al. The PASCAL visual object classes challenge 2007(VOC2007) results[EB/OL].[2017-06-16]. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.230.2543.
[12] HARIHARAN B, ARBELÁEZ P, GIRSHICK R, et al. Hypercolumns for object segmentation and fine-grained localization[C]//CVPR 2015:Proceedings of the 2015 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:447-456.
[13] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137-1149.
[14] DAI J, LI Y, HE K, et al. R-FCN:object detection via region-based fully convolutional networks[J/OL]//arXiv:1605.06409(2016-06-21)[2017-10-21]. https://arxiv.org/abs/1605.06409.
[15] HE K, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[J/OL]//arXiv:1703.06870[2018-01-24]. https://arxiv.org/abs/1703.06870.
[16] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real-time object detection[C]//CVPR 2016:Proceedings of the 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:779-788.
[17] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector [C]// ECCV 2016: Proceedings of the 2016 European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
[18] HUANG J, GUADARRAMA S, MURPHY K, et al. Speed/accuracy trade-offs for modern convolutional object detectors [C]// CVPR 2017: Proceedings of the 2017 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2017: 3296-3297.
[19] CHEN D, REN S, WEI Y, et al. Joint cascade face detection and alignment [C]// ECCV 2014: Proceedings of the 2014 European Conference on Computer Vision. Cham: Springer, 2014: 109-122.
[20] 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.
[21] YANG S, LUO P, LOY C-C, et al. From facial parts responses to face detection: a deep learning approach [C]// ICCV '15: Proceedings of the 2015 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2015: 3676-3684.
[22] HOWARD A G, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications [J/OL]. arXiv:1704.04861[2017-04-17]. https://arxiv.org/abs/1704.04861.
[23] HENRIQUES J F, RUI C, MARTINS P, et al. High-speed tracking with kernelized correlation filters [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 37(3): 583-596.
[24] IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift [C]// ICML 2015: International Conference on International Conference on Machine Learning. Lille: JMLR, 2015:448-456.
[25] JAIN V, LEARNED-MILLER E. FDDB: a benchmark for face detection in unconstrained settings, UM-CS-2010-009[R]. Amherst: University of Massachusetts, 2010.
[26] YANG S, LUO P, CHEN C L, et al. WIDER FACE: a face detection benchmark [C]// CVPR 2016: Proceedings of the 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016: 5525-5533.

基于MS-KCF模型的图像序列中人脸快速稳定检测

Rapid stable detection of human faces in image sequence based on MS-KCF model

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]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[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]	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.
[13]	杨粟, 欧阳智, 杜逆索. 基于相关度距离的无监督并行哈希图像检索[J]. 计算机应用, 2021, 41(7): 1902-1907.
[14]	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.
[15]	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.