ERC — An environmental robust Camshift face tracking algorithm

The classical Camshift face tracking algorithm requires a higher environmental demand and is susceptible to the skin color interference. To solve the above problems, an improved Camshift tracking algorithm - ERC (Environmental Robust Camshift) is presented. Firstly, the RGB histogram equalization is applied in ERC to extend the hue differentiation between pixels; secondly, the statistical and spatial information are combined by using the adaptive kernel function based on the spatiogram to obtain the target tone model; finally, the tracking module in the classical Camshift algorithm is employed to realize the target tracking. The experiment results show that the ERC can achieve an effective face tracking in the case of intense illumination changes, background clutter and rapid movement.

[1]  Rynson W. H. Lau,et al.  Visual Tracking via Locality Sensitive Histograms , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Rustam Stolkin,et al.  Efficient visual servoing with the ABCshift tracking algorithm , 2008, 2008 IEEE International Conference on Robotics and Automation.

[3]  Sebastien Ambellouis,et al.  Vehicle detection and tracking using Mean Shift segmentation on semi-dense disparity maps , 2012, 2012 IEEE Intelligent Vehicles Symposium.

[4]  Alex Zelinsky,et al.  Learning OpenCV---Computer Vision with the OpenCV Library (Bradski, G.R. et al.; 2008)[On the Shelf] , 2009, IEEE Robotics & Automation Magazine.

[5]  尹传历 Yin Chuan-li,et al.  Design and Realization of Airborne Embedded Image Enhancement System , 2013 .

[6]  Barry G. Haskell,et al.  Color balance for video conferencing , 1997, Proceedings of International Conference on Image Processing.

[7]  Dajie Cong,et al.  An improved camshift algorithm based on RGB histogram equalization , 2014, 2014 7th International Congress on Image and Signal Processing.

[8]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  WEN Zhi-Qiang,et al.  Convergence Analysis of Mean Shift Algorithm , 2007 .

[10]  Andrew Calway,et al.  Proceedings of the IEEE International Conference on Image Processing , 1996 .

[11]  Wang Xua.  Multilayer locality sensitive histograms based real-time target tracking under occlusion , 2015 .

[12]  Huicheng Zheng,et al.  Robust visual tracking using local salient coding and PCA subspace modeling , 2013, 2013 IEEE International Workshop on Information Forensics and Security (WIFS).

[13]  L. Darrell Whitley,et al.  Adaptive Appearance Model and Condensation Algorithm for Robust Face Tracking , 2010, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[14]  Wen Zhi.  Convergence Analysis of Mean Shift Algorithm , 2007 .

[15]  No Value,et al.  IEEE International Conference on Image Processing , 2003 .

[16]  D. Zhang,et al.  Scale and orientation adaptive mean shift tracking , 2012 .

[17]  Nan Sang,et al.  Eye Tracking Based on Improved CamShift Algorithm , 2013, 2013 Sixth International Symposium on Computational Intelligence and Design.

[18]  Gary R. Bradski,et al.  Real time face and object tracking as a component of a perceptual user interface , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[19]  Li Ji,et al.  Novel algorithm for image enhancement with histogram equalization and MSRCR , 2014 .

[20]  Zdenek Kalal,et al.  Tracking-Learning-Detection , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Zhang Wei-wei.  Vehicle Detection and Tracking Based on the Local Binary Pattern Texture and Improved Camshift Operator , 2013 .