[1]齐永锋,王梦媛,卢晨鸣.一种在复杂光照条件下的人脸跟踪算法[J].红外技术,2018,40(12):1188-1192.[doi:10.11846/j.issn.1001_8891.201812012]
 QI Yongfeng,WANG Mengyuan,LU Chenming.Face Tracking Algorithm under Complicated Illumination Conditions[J].Infrared Technology,2018,40(12):1188-1192.[doi:10.11846/j.issn.1001_8891.201812012]
点击复制

一种在复杂光照条件下的人脸跟踪算法
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
40
期数:
2018年第12期
页码:
1188-1192
栏目:
出版日期:
2018-12-21

文章信息/Info

Title:
Face Tracking Algorithm under Complicated Illumination Conditions
文章编号:
1001-8891(20)12-1188-05
作者:
齐永锋王梦媛卢晨鸣
西北师范大学 计算机科学与工程学院, 甘肃 兰州 730070
Author(s):
QI YongfengWANG MengyuanLU Chenming
 College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China
关键词:
人脸跟踪多尺度技术韦伯脸预处理方法实时压缩复杂光照人脸遮挡
Keywords:
face trackingmulti-scale techniquesWeberfacepreprocessing methodsreal-time compressioncomplex illuminationface occlusion
分类号:
TP181
DOI:
10.11846/j.issn.1001_8891.201812012
文献标志码:
A
摘要:
针对光照以及人脸的尺度变换、遮挡等问题,提出一种基于多尺度韦伯脸与实时压缩在复杂光照情况下的跟踪算法。对实时压缩跟踪方法的理论模型的认真分析与研究,提出采用光照预处理方法来提高复杂光照情况下跟踪过程中目标信息的采集精准度。在目标检测跟踪过程中,与经典的实时压缩跟踪算法相比,基于多尺度韦伯脸与实时压缩的人脸跟踪算法在复杂光照情况下跟踪性能得到明显提升,能较好应对人脸尺度变换及局部遮挡的情况。
Abstract:
Aiming at the resolution of problems of illumination and face scale conversion and occlusion, a tracking algorithm based on multi-scale Weberface and real-time compression under complex lighting conditions is proposed. After a careful analysis and research on the theoretical model of the real-time compression tracking method, the illumination preprocessing method is proposed to improve the acquisition accuracy of the target information in the tracking process under complex lighting conditions. In the process of target detection and tracking, compared with the classical real-time compression tracking algorithm, the tracking performance based on multi-scale Weberface and real-time compression can clearly improve tracking performance under complex lighting conditions and better cope with face scale transformation and local occlusion cases.

参考文献/References:

[1] Robust face recognition via occlusion dictionary learning[J]. Pattern Recognition, 2014, 47(4): 1559-1572.
[2] Fukunaga K, Hostetler L D. The estimation of the gradient of a density function, with applications in pattern recognition[J]. IEEE Transactions on Information Theory, 1975, 32(1): 32-34.
[3] Kalal Z, Mikolajczyk K, Matas J. Tracking- Learning-Detection[M]. IEEE Computer Society, 2012.
[4] Hare S, Saffari A, Torr P H S. Struck: Structured output tracking with kernels[C]//IEEE International Conference on Computer Vision, 2012.
[5] Babenko B, Yang M H, Belongie S. Visual tracking with online multiple instance learning[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2009: DOI: 10.1109/CVPRW.2009.5206737.
[6] Zhang Kaihua, Song H H. Real-time visual tracking via online weighted multiple instance learning[J]. Pattern Recognition, 2013, 46(1): 397-411.
[7] ZHANG Kaihua, ZHANG Lei, YANG Ming-Hsuan. Real-time com- pressive tracking[C]//Proceedings of the 12th European Conference on Computer Vision, 2012, 7574: 866-879.
[8] Candes E J, Tao T. Decoding by linear programming[J]. IEEE Transactions on Information Theory, 2005, 51(12): 4203-4215.
[9] Basri R, Jacobs D W. Lambertian reflectance and linear subspaces[C]// Eighth IEEE International Conference, 2003: 383-390 .
[10] WANG B, LI W, YANG W, et al. Illumination normalization based on Weber’s law with application to face recognition[J]. IEEE Signal Processing Letters, 2011, 18(8): 462-465.
[11] CHENG S. Face recognition under complex illumination based on multi- scale Weberface and local binary pattern[J]. Journal of Information & Computational Science, 2015, 12(12): 4585-4593.

备注/Memo

备注/Memo:
收稿日期:2018-01-20;修订日期:2018-03-07.
作者简介:齐永锋(1971-),男,教授,主要研究方向:模式识别与数字图像,E-mail:qiyf@nwnu.edu.cn。
基金项目:甘肃省高等学校科研项目(2016A-004)。
更新日期/Last Update: 2018-12-19