应用姿态估计的人脸特征点定位算法

doi:10.11772/j.issn.1001-9081.2017.11.3256

计算机应用 ›› 0, Vol. ›› Issue (): 3256-3260.DOI: 10.11772/j.issn.1001-9081.2017.11.3256

• 2017年中国计算机学会人工智能会议(CCFAI 2017) • 上一篇下一篇

应用姿态估计的人脸特征点定位算法

张海艳¹, 高尚兵^1,2, 姜明新¹

1. 淮阴工学院计算机与软件工程学院, 江苏淮安 223003;
2. 南京市可信云计算与大数据分析重点实验室(南京晓庄学院), 南京 211171

收稿日期:2017-05-11 修回日期:2017-07-10 发布日期:2019-01-01 出版日期:2017-11-10
通讯作者: 张海艳
作者简介:张海艳(1980-),女,吉林长春人,讲师,硕士,主要研究方向:图像处理;高尚兵(1981-),男,江苏淮安人,副教授,博士研究生,主要研究方向:图像处理;姜明新(1979-),女,黑龙江哈尔滨人,副教授,博士研究生,主要研究方向:计算机视觉。
基金资助:
国家自然科学基金资助项目（61402192，61403060）；江苏省"六大人才高峰"计划资助项目（XYDXXJS-011）；江苏省333工程项目（BRA2016454）。

Facial feature points localization algorithm using pose estimation

ZHANG Haiyan¹, GAO Shangbing^1,2, JIANG Mingxin¹

1. Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an Jiangsu 223003, China;
2. Nanjing Key Laboratory of Trusted Cloud Computing and Big Data Analysis(Nanjing Xiaozhuang University), Nanjing Jiangsu 211171, China

Received:2017-05-11 Revised:2017-07-10 Online:2019-01-01 Published:2017-11-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61402192, 61403060), the Six Talent Peaks Project in Jiangsu Province (XYDXXJS-011), the 333 Project in Jiangsu Province (BRA2016454).

摘要/Abstract

摘要： 针对已有鲁棒级联姿势回归算法缺少形状约束条件的现状，同时在复杂人脸及遮挡情况中定位精度较低、成功率不高等问题，提出应用姿态估计人脸特征点的新型定位算法来提高定位精度和成功率。对人脸特征点执行区域分块操作来实现形状约束条件；为提高算法性能，对部分特征点位置执行回归操作从而降低回归器规模，并引入形状索引特征进行采样先验操作。实验结果表明，所提算法针对复杂人脸及遮挡情况具备较高定位精度与鲁棒性，同时算法速度可达实时要求。

关键词: 核回归, 姿态估计, 特征点定位, 采样先验, 形状约束

Abstract: Aiming at the problem that the existing robust cascade postural regression algorithm lacks shape constraint, and has low localization accuracy and unsatisfactory success rate in complex face and occlusion situations, a novel positioning algorithm for pose estimation of facial feature points was proposed to improve the accuracy and success rate. A regional block operation was performed on face feature points to implement shape constraint. To improve the algorithm performance, a regression operation was performed on partial feature point positions to reduce the scale of regression, and the shape index feature was introduced to sampling prior operation. The experimental results show that the proposed algorithm has higher localization accuracy and robustness for complex face and occlusion, and meets the realtime requirement.

Key words: kernel regression, pose estimation, feature points localization, sampling prior, shape constraint

中图分类号:

TP391.413

张海艳, 高尚兵, 姜明新. 应用姿态估计的人脸特征点定位算法[J]. 计算机应用, 0, (): 3256-3260.

ZHANG Haiyan, GAO Shangbing, JIANG Mingxin. Facial feature points localization algorithm using pose estimation[J]. Journal of Computer Applications, 0, (): 3256-3260.

参考文献

[1] CHARALABOPOULOS A. Face recognition approach based on rank correlation of Gabor-filtered images[J]. Pattern Recognition, 2002, 35(6):1275-1289.
[2] CAO C, HOU Q, ZHOU K. Displaced dynamic expression regression for real-time facial tracking and animation[J]. ACM Transactions on Graphics, 2014, 33(4):1-10.
[3] MARTINEZ A, DU S. A model of the perception of facial expressions of emotion by humans:research over-view and perspectives[J]. Journal of Machine Learning Research, 2012, 13(1):1589-1608.
[4] FELZENSZWALB P F, GIRSHICK R B, DAVID M A, et al. Object detection with discriminatively trained part based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9):1627-1645.
[5] CAO X, WEI Y, WEN F, et al. Face alignment by explicit shape regression[J]. International Journal of Computer Vision, 2014, 107(2):177-190.
[6] BURGOS-ARTIZZU X P, PERONA P, DOLLAR P. Robust face landmark estimation under occlusion[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2013:1513-1520.
[7] XIONG X, TORRE F D L. Supervised descent method and its applications to face alignment[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2013:532-539.
[8] REN S, CAO X, WEI Y, et al. Face alignment at 3000 fps via regressing local binary features[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2014:1685-1692.
[9] LEE D, PARK H, YOO C D. Face alignment using cascade Gaussian process regression trees[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2015:4204-4212.
[10] 仲柔在,熊磊,刘畅. 基于相对距离分布的人脸特征点定位算法[J]. 空军工程大学学报(自然科学版), 2016,17(1):60-64.(ZHONG R Z, XIONG L, LIU C. An algorithm of locating the feature points of human face landmarks based on relative distance distribution[J]. Journal of Air Force Engineering University (Nature Science Edition), 2016, 17(1):60-64.)
[11] MUSTAFA O, MICHAEL C, VINCENT L, et al.Fast keypoint recognition using random ferns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3):448-461.
[12] 钟森海,汪烈军,张莉. 小样本条件下的人脸特征提取算法[J]. 计算机工程与应用,2015,51(8):165-169.(ZHONG S H, WANG L J, ZHANG L. Face feature extraction algorithm for small training sets[J]. Computer Engineering and Applications, 2015, 51(8):165-169.)
[13] 黄飞,谭守标. 基于改进主动表观模型算法的人脸特征定位[J]. 计算机工程与应用,2015,51(16):204-209.(HUANG F, TAN S B. Facial feature points localization based on improved active appearance models algorithm[J]. Computer Engineering and Applications, 2015, 51(16):204-209.)

[1]	张广耀, 宋纯锋. 融合人体全身表观特征的行人头部跟踪模型[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1372-1377.
[2]	赵威, 李毅. 基于Kinect的人体姿态估计优化和动画生成[J]. 《计算机应用》唯一官方网站, 2022, 42(9): 2830-2837.
[3]	李坤, 侯庆. 基于注意力机制的轻量型人体姿态估计[J]. 《计算机应用》唯一官方网站, 2022, 42(8): 2407-2414.
[4]	杨飞宇, 宋展, 肖振中, 莫曜阳, 陈宇, 潘哲, 张敏, 张遥, 钱贝贝, 汤朝伟, 金武. 对人体姿态估计热图误差的再思考[J]. 《计算机应用》唯一官方网站, 2022, 42(8): 2548-2555.
[5]	孙琪翔, 何宁, 张敬尊, 宏晨. 基于非局部高分辨率网络的轻量化人体姿态估计方法[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1398-1406.
[6]	危德健, 王文明, 王全玉, 任好盼, 高彦彦, 王志. 改进的基于锚点的三维手部姿态估计网络[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 953-959.
[7]	马康哲, 皮家甜, 熊周兵, 吕佳. 融合注意力特征的遮挡物体6D姿态估计[J]. 《计算机应用》唯一官方网站, 2022, 42(12): 3715-3722.
[8]	马敬奇, 雷欢, 陈敏翼. 基于AlphaPose优化模型的老人跌倒行为检测算法[J]. 《计算机应用》唯一官方网站, 2022, 42(1): 294-301.
[9]	章惠, 张娜娜, 黄俊. 优化LeNet-5网络的多角度头部姿态估计方法[J]. 计算机应用, 2021, 41(6): 1667-1672.
[10]	郭天晓, 胡庆锐, 李建伟, 沈燕飞. 基于人体骨架特征编码的健身动作识别方法[J]. 计算机应用, 2021, 41(5): 1458-1464.
[11]	李伟强, 雷航, 张静玉, 王旭鹏. 基于标签分布学习的三维手部姿态估计[J]. 计算机应用, 2021, 41(2): 550-555.
[12]	黄俊, 张娜娜, 章惠. 融合头部姿态和面部表情的互动式活体检测[J]. 计算机应用, 2020, 40(7): 2089-2095.
[13]	强保华, 翟艺杰, 陈金龙, 谢武, 郑虹, 王学文, 张世豪. 基于改进CPMs和SqueezeNet的轻量级人体骨骼关键点检测模型[J]. 计算机应用, 2020, 40(6): 1806-1811.
[14]	肖仕华, 桑楠, 王旭鹏. 基于深度学习的三维点云头部姿态估计[J]. 计算机应用, 2020, 40(4): 996-1001.
[15]	魏嘉旺, 王肖, 袁玉波. 人脸特征点定位的自适应窗回归方法[J]. 计算机应用, 2019, 39(5): 1459-1465.

应用姿态估计的人脸特征点定位算法

Facial feature points localization algorithm using pose 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