Crane tracking and monitoring system based on TLD algorithm

Aiming at tracking performance of real-time and robustness of crane monitoring system, current target tracking methods are contrasted in this paper, such as Tracking-Learning-Detection (TLD) algorithm, MeanShift and particle filter. Experimental results show that MeanShift and particle filter algorithm have the advantage over TLD in real-time performance. However, TLD can adapt to the crane transformation with preferable self-learning capability. And TLD enables to re-track the object even if the object is sheltered or missed momently. Therefore, the crane monitoring system based on TLD algorithm can not only detect and track the target accurately but also be superior to another two algorithms in performance of robustness.

[1]  M. Gossa,et al.  Robust fault and state estimation for linear discrete-time systems with unknown disturbances using PI Three-Stage Kalman Filter , 2011, 2011 International Conference on Communications, Computing and Control Applications (CCCA).

[2]  Zhang Hai-yuan.  Target tracking using particle filters based on spatiograms , 2011 .

[3]  Shen Lan-sun.  Intelligent Visual Surveillance Technology:A Survey , 2007 .

[4]  Vincent Lepetit,et al.  Fast Keypoint Recognition Using Random Ferns , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

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

[7]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Jiri Matas,et al.  Online learning of robust object detectors during unstable tracking , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

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

[10]  Hu Shiqiang,et al.  Overview of particle filter algorithm , 2005 .

[11]  Jiri Matas,et al.  P-N learning: Bootstrapping binary classifiers by structural constraints , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

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

[14]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.