Future works

In our system, the moving human can be detected and tracked smoothly and continuously but if the moving human in the complex environment that will result

tracking lose. For example, the background has very bright light that will result moving human changes it character.

We use temporal difference, x-axis and y-axis to redefined target object ROI size.

The experiment result has shown in chap5. There is a problem in this method. When the active camera move and use temporal difference, in the general situation we get blur and unclear image. This problem will influence our ROI resizing. There are some methods to solve this problem. For example [37], use different kernel function scale to adjust height and width avoid temporal difference used.

The active camera is driven by pelco P protocol and use position based control pan or tilt. Although, drive active camera to control direction successfully. But the speed of pan or tilt is fixed. Maybe the moving human motion can be considered and use motion to drive active camera speed and direction. That will result active camera moves more reliable.

References

[1] Wei Guo, Dong-Liang Bi, Lu Liu "Human motion tracking based on shape analysis" in proc. of the 2007 international conference on wavelet analysis and pattern recognition, Beijing , china, 2-4 nov. 2007.

[2] W. J. Gillner, “Motion based vehicle detection on motorways,” in Proc. of the Intelligent Vehicles '95 Symposium, pp.483-487, Sept. 1995.

[3] R.C. Gonzalez, R.E. Woods, Digital Image Processing, Addison-Wesley, New York, 1992.

[4] D. Marr, E. Hildreth, Theory of edge detection, Proc. R. Soc. London 207 (1980) 197–217.

[5] T. Law, H. Itoh, H. Seki, Image filtering, edge detection, and edge tracing using fuzzy reasoning, IEEE Trans. Pattern Analysis Mach. Intell. 18 (1996) 481–491.

[6] P. H. Batavia, D. E. Pomerleau, and C. E. Thorpe, “Overtaking vehicle detection using implicit optical flow,” IEEE Conference on Intelligent Transportation System, Nov.1997, pp. 729-734.

[7] Dalal N, T riggs B, “Histograms of oriented gradients for human detection”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol 1,pp. 886-893, 2005

[8] L. Zhao and C. E. Thorpe, “Stereo- and neural network-based pedestrian detection,” IEEE Transactions on Intelligent Transportation Systems, Vol. 1, No.3, pp. 148-154, Sept. 2000.

[9] K. Fukunaga, L.D. Hostetler, “The estimation of the gradient of a density function, with applications in pattern recognition,” IEEE Trans. Inform. Theo. 21 (1) (1975) 32–40.

[10] Montabone S, Soto A, “Human detection using a mobile platform and novel features derived from a visual saliency mechanism”, Image and Vision Computing Volume. 28, Issue.3, pp. 391-402, 2010

[11] M.S. Bartlett, J.R. Movellan and T.J. Sejnowski, “Face recognition by independent component analysis.“ IEEE Transaction on Neural Networks, Vol.13, No. 6 , pp. 1450–1464, 2002.

[12] Y. Ou, X. Wu,H. Qian and Y. Xu, “A Real Time Race Classification System,”

IEEE International Conference on Information Acquisition, pp. 378-383, 2005.

[13] P. Viola, M. Jones, and D. Snow, “Detecting Pedestrians Using Patterns of Motion and Appearance,” Int’l J. Computer Vision, vol. 63, no. 2, pp. 153-161,

2005.

[14] Dimitrijevic M, Lepetit V, Fua P, "Human body pose detection using Bayesian spatio-temporal templates", Computer Vision and Image Understanding, Vol.104, issue.2-3, pp.127-139,2006 .

[15] Plamen P, Ognian B and Krasimir M, “Face Detection and Tracking with an Active Camera”, International IEEE Conference Intelligent Systems, 2008 4th.

[16] Smith, A. R., ”Color Gamut Transform Pairs,” Computer Graphics, Vol. 12(3), pp. 12-19, 1978

[17] http://en.wikipedia.org/wiki/HSV_color_space#Conversion_from_RGB_to_HSL _or_HSV

[18] http://www.mathworks.com/access/helpdesk/help/toolbox/images/f8-20792.html [19] Comaniciu, D., Ramesh, V., and Meer, P. “Kernel-based object tracking.” IEEE

Transactions on Pattern Analysis and Machine Intelligence, 25, 5 (2003), 564—577.

[20] D. Freedman and P. Kisilev, " Fast mean shift by compact density representation." IEEE Conference on Computer Vision and Pattern Recognition Pages: 1818-1825 Published: 2009.

[21] Wang F.L., Yu S.Y. and Yang J., "Robust and efficient fragments-based tracking using mean shift." Aeu-International Journal of Electronics and Communications Volume: 64 Issue: 7 Pages: 614-623 Published: 2010

[22] F. Porikli, O. Tuzel, “Multi-kernel object tracking,” IEEE Int. Conf. Multimedia Expo (2005) 1234–1237.

[23] C. Yang, R. Duraiswami, L. Davis, “Efficient mean-shift tracking via a new Similarity measure.” in: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, 2005, pp. 176–183.

[24] P. Pe´rez, C. Hue, J. Vermaak, M. Gangnet, Color-based probabilistic tracking, in:

Proceedings of European Conference on Computer Vision, Copenhagen, Denmark, 2002.

[25] K. Nummiaro, E. Koller-Meier, L. Van Gool, An adaptive color based particle filter, Image Vis. Comput. 21 (1) (2003) 99–110.

[26] O. Williams, A. Blake, R. Cipolla, Sparse bayesian learning for efficient visual tracking, IEEE Trans. Pattern Anal. Mach. Intell. 27(8) (2005) 1292–1304.

[27] A. Agarwal and B. Triggs, “Recovering 3D human pose from monocular images,” IEEE Trans. Pattern Analysis Machine Intelligence, vol. 28, no. 1, pp.

44-58, Jan. 2006.

[28] Bohyung Han and Larry Davis, "Object tracking by adaptive feature extraction", International Conference on Image Processing, Singapore, 2004.

[29] Robert T. Collins, Yanxi Liu and Marius Leordeanu, "Online Selection of

Discriminative", IEEE Transactions on Pattern Analysis and Machine intelligence, VOL. 27, NO. 10, 2005.

[30] D. Murray and A. Basu, “Motion tracking with an active camera,” IEEE Trans.

Pattern Anal. Mach. Intell., vol. 19, no. 5, pp. 449–454, May 1994.

[31] Lin C., Wang C., Chang Y., Chen Y. “Real-time object extraction and tracking with an active camera using image mosaics”. Proceedings of the IEEE International Workshop on Multimedia Signal Processing, Dec. (2002)

[32] Collins, R., Amidi, O., Kanade, T.: An active camera system for acquiring multi-view video. In: Proceedings of the 2002 International Conference on Image Processing, Sept. (2002)

[33] L. Fiore, D. Fehr, R. Bodor, A. Drenner, G. Somasundaram and N.

Papanikolopoulos, "Multi-camera human activity monitoring", Springer Netherlands, Journal of Intelligent & Robotic Systems, pp.5-43, 2008.

[34] R. Venkatesh Babu a, Patrick Pe´rez b, Patrick Bouthemy, "Robust tracking with motion estimation and local Kernel-based color modeling", ,Image and Vision Computing, pp.1205–1216, 2007.

[35] Feng S., Guan Q., Xu s. and Tan F., "Human tracking based on mean shift and Kalman Filter", International Conference on Artificial Intelligence and Computational Intelligence,2009

[36] Yizong Cheng, "Mean shift, mode seeking, and Clustering", IEEE Transaction on pattern analysis and machine intelligence, VOL.17, NO.8, August 1995.

[37] Robert T. Collins, "Mean-shift Blob Tracking through Scale Space", IEEE computer society conference on computer vision and pattern recognition, Pages:

234-240, Published: 2003

[38] Tsia-Jung Chung and Chin-Teng Lin ,"Human Detection and Tracking Based on Modified Independent Component Analysis" National Chiao Tung University ,publish 2008