|Table of Contents|

Object Tracking Method Based on Gray Level Co-occurrence Matrix Texture Characteristic

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2010年04期
Page:
459-463
Research Field:
Publishing date:

Info

Title:
Object Tracking Method Based on Gray Level Co-occurrence Matrix Texture Characteristic
Author(s):
WU GangTANG Zhen-minCHENG YongZHU FengWEI Li-hua
School of Computer Science and Technology,NUST,Nanjing 210094,China
Keywords:
object tracking textures gray level co-occurrence matrix
PACS:
TP391.41
DOI:
-
Abstract:
Based on the texture characteristic,the object tracking method which integrates gray level co-occurrence matrix texture’s characteristic into system’s framework is proposed.By doing experiments on standard video under OpenCV,the functions about the gray level co-occurrence matrix texture,local binary model texture and gray color characteristic are tested in contrastive experimentations using a particle filter tracking algorithm.The capabilities about resisting analogous color’s disturbance and working time are embodied in experimentation using gray level co-occurrence matrix texture.The excellent quality of the gray level co-occurrence matrix texture is indicated by correlative testing data and contrastive results,which can boost up the holistic capability of the tracking system.

References:

[ 1] ?? 夏德深, 金盛, 王健. 基于分数维与灰度梯度共生 矩阵的气象云图识别( ?? ) ?? ?? ?? 灰度梯度共生矩阵 对纹理统计特征的描述[ J] . 南京理工大学报(自 然科学版), 1999, 23( 4): 289- 292.
[ 2] Jafar i??Khouzani K, Soltan ian??Zadeh H. Radon trans?? form or ientation estim ation fo r rota tion invar iant texture analysis[ J]. IEEE Transactions on Pa ttern Ana lys is and M ach ine Inte lligence, 2005, 27 ( 6 ): 1004 - 1008. [ 3 ] Oja la T, PietikainenM, M aenpaa T. Mu ltireso lution gray??scale and ro tation invar iant tex ture c lassifica tion w ith loca l b ina ry pa tterns[ J]. IEEE T ransactions on Patte rn Ana lysis and M achine Inte lligence, 2002, 24( 7): 971- 987.
[ 4] 宁纪锋, 吴成柯. 一种基于纹理模型的M ean Sh ift 目标跟踪算法[ J]. 模式识别与人工智能, 2007, 20( 5): 612- 618.
[ 5] H e ikk il??M, Pie tik??inen M. A tex ture??based m ethod form ode ling the background and de tecting m ov ing ob?? jects[ J] . IEEE T ransactions on Pattern Analysis and M achine Inte lligence, 2006, 28( 4): 657- 662.
[ 6] Go rdan N J, Salm ond D J, Sm ith A F M. A novel ap?? proach to non linear /non??Gaussian Bayesian state esti?? m ation[ J]. IEEE Proceed ings- F, 1993, 140 ( 2 ): 107- 113.
[ 7] Numm iaro K, M e ier E K, Goo lL J V. An adaptiv e co lor??based particle filter[ J]. Im ag e and V ision Com?? pu ting, 2003, 21( 1): 99- 110.
[ 8] DoucetA, Freitas N D, Go rdon N J. Sequen tia lM on te Car lo m ethods in practice[M ] . New York: Spr ing er?? V erlag Press, 2001.
[ 9] A ru lam palam M S, M aske ll S, Gordon N J, et a.l A tutor ia l on partic le filters fo r on??line non??linear / non?? Gaussian B ayes ian track ing [ J]. IEEE T ransactions on S ignal Processing, 2002, 50( 2): 174- 188.

Memo

Memo:
-
Last Update: 2012-11-02