计算机科学 ›› 2017, Vol. 44 ›› Issue (4): 306-311.doi: 10.11896/j.issn.1002-137X.2017.04.062

• 图形图像与模式识别 • 上一篇    下一篇

基于改进型LTP的均值漂移目标跟踪算法

邹青志,黄山   

  1. 四川大学电气信息学院 成都610065,四川大学计算机学院 成都610065
  • 出版日期:2018-11-13 发布日期:2018-11-13

Mean Shift Tracking Algorithm Based on Improved LTP Feature Extraction

ZOU Qing-zhi and HUANG Shan   

  • Online:2018-11-13 Published:2018-11-13

摘要: 提出一种使用改进型LTP特征与颜色特征融合的均值漂移(Mean Shift)目标跟踪算法,该算法解决了均值漂移目标跟踪算法在变化的光强场景下跟踪难的问题。首先针对LTP模式过多的问题引入旋转不变的LTP模式,然后提出动态计算LTP算子阈值的方法,之后将改进的LTP特征与颜色特征通过自适应函数融合起来并嵌入均值漂移算法中。在变光强场景下与传统目标跟踪算法相比较,此算法跟踪结果明显优于其他算法,且鲁棒性较好。

关键词: Mean Shift算法,LTP,自适应,光照,鲁棒性

Abstract: A mean shift target tracking algorithm based on improved LTP feature and color feature fusion was proposed,which can solve the problem of tracking difficult of algorithm under varying light intensity scene.The rotation invariant is introduced aiming at the problem of LTP model,then the dynamic threshold method is put forward, and then the improved LIP feature and color feature are fused to embed into mean shift algorithm throught adaptive function. Compared with traditional target tracking algorithm in changing light intensity scenario,tracking result of this algorithm is superior to other algorithms,and has good robustness.

Key words: Mean shift algorithm,LTP,Adaptive,Light intensity,Robustness

[1] Ning J F,ZHANG L,ZHANG D,et al.Scale and Orientation Adaptive Mean Shift Tracking [J].IET Computer Vision,2012,6(1):52-61.
[2] KHAN Z H,GU Y H,BACKHOUSE A.Robust Visual Object Tracking Using Multi-Mode Anisotropic Mean Shift and Particle Filters [J].IEEE Transactions on Circuits and Systems for Vi-deo Technology,2011,21(1):74-87.
[3] CHEN F,HUANG Y J,LI S Y,et al.Meanshift Target Trac-king Algorithm based on Adaptive Window [J].Electronic Technology,2016,45(5):1-4.(in Chinese) 陈菲,黄勇坚,李淑彦,等.自适应窗口的Meanshift目标跟踪算法[J].电子技术,2016,5(5):1-4.
[4] MEHMOOD R,NAWAZ R,RAO N I.Occlusion handling in meanshift tracking using adaptive window Normalized Cross Correlation[C]∥International Bhurban Conference on Applied Sciences & Technology.2014:126-129.
[5] HE J,YANG Y.Multi-iterative tracking method using mean-shift based on kalman filter[C]∥IEEE International Conference on Signal Processing,Communications & Computing.2014:22-27.
[6] WANG X,HU Z,FENG J,et al.Mean-Shift tracking algorithm based on Kalman filter using adaptive window and sub-blocking [C]∥World Congress on Intelligent Control & Automation.2015:5438-5443.
[7] TAN X,TRIGGS B.Enhanced local texture feature sets for face recognition under difficult lighting conditions[C]∥Analysis and Modeling of Faces and Gestures.2007:168-182.
[8] TOPI M,MATTI P,TIMO O.Texture Classification by Multi-Predicate Local Binary Pattern Operators[J].International Conference on Pattern Recognition,2000,3(3):3951.
[9] ROSIN P L.Thresholding for change detection [J].Computer Vision and Image Understanding,2002,6(2):79-85.
[10] TAN X,TRIGGS B.Fusing Gabor and LBP features sets for kernel based face recognition[J].International Conference on Analysis & Modeling of Fce & Gestures,2007,8(9):235-249.
[11] FERNNDEZ-CABALLERO A,CASTILLO J C,MARTNEZ-CANTOS J,et al.Optical flow or image subtraction in human detection from infrared camera on mobile robot[J].Robotics and Autonomous Systems,2010,58(12):1273-1281.
[12] JIAO B,YAN L L,LI W .Fast convergent Gaussian Mixture Model in moving objects detection[C]∥IEEE International Conference on Computer Science and Automation Engineering (CSAE),2011.2011:422-425.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!