Moving object tracking based on geogram

We introduce the concept of a geogram that captures richer features to represent the objects. The spatiogram contains some moments upon the coordinates of the pixels corresponding to each bin while the geogram contains information about the perimeter of grouped regions in addition to features in the spatiogram. The perimeter of the given region has capability to represent the geometrical compactness on the distribution of the given feature. The geogram-based feature descriptor increases the accuracy of tracking because it can capture the features in lower levels. Also, we consider that a convergence of the mean shift algorithm for the spatiogram is divided into obvious dynamic and steady states as well as in automatic control, and introduce a hybrid technique of the geogram and the histogram to control convergence process. Moreover, we derive a mean shift procedure for the proposed geogram. We test our feature descriptor and measure in object tracking scenario. Experimental results demonstrate that the geogram has promising discriminative capability in comparison with other ones.

[1]  Takahiro Ishikawa,et al.  The template update problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Fernando Diaz,et al.  Improving recency ranking using twitter data , 2013, TIST.

[3]  Guijin Wang,et al.  An incremental Bhattacharyya dissimilarity measure for particle filtering , 2010, Pattern Recognit..

[4]  Gang Chen,et al.  A Lie group based spatiogram similarity measure , 2009, 2009 IEEE International Conference on Multimedia and Expo.

[5]  Stanley T. Birchfield,et al.  Spatiograms versus histograms for region-based tracking , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  Ingvar Claesson,et al.  On histograms and spatiograms - introduction of the mapogram , 2008, 2008 15th IEEE International Conference on Image Processing.

[7]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Monson H. Hayes,et al.  Maximum likelihood training of the embedded HMM for face detection and recognition , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[9]  Ingvar Claesson,et al.  The successive mean quantization transform , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[10]  Liyu Gong,et al.  Shape of Gaussians as feature descriptors , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Alan F. Smeaton,et al.  An Improved Spatiogram Similarity Measure for Robust Object Localisation , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[12]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[13]  Zhongfei Zhang,et al.  A survey of appearance models in visual object tracking , 2013, ACM Trans. Intell. Syst. Technol..

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

[15]  John Conley,et al.  Technical Report 2 , 2014 .

[16]  Christoph H. Lampert,et al.  Spatiogram-Based Shot Distances for Video Retrieval , 2006, TRECVID.

[17]  Guijin Wang,et al.  A compact association of particle filtering and kernel based object tracking , 2012, Pattern Recognit..

[18]  Yan Yu,et al.  A Lie group based Gaussian Mixture Model distance measure for multimedia comparison , 2009, ICIMCS '09.

[19]  Dima Damen,et al.  Proceedings of the British Machine Vision Conference , 2014, BMVC 2014.