Abstract  The  advancement  of  technology  allows  video  acquisit ion  devices  to  have  a  better  performance,  thereby  increasing  the  number  of  applications  that  can  effectively  uti lize  digital  video.  Compared  to  still  images,  video   sequences  provide  more  information  about  how  objects  and  scenarios  change  over  time.  Tracking  humans  is  of  interest  for  a  variety  of  applications  including surveillance, activity monitoring and gat e analysis. Many efficient object tracking algorithms have been proposed in  literature,  however  part  of  those  algorithms  are  se mi-automatic  requiring  human  interference.  As  for  t he  fully  automated  algorithms, most of them are not applicable to real-time applications. This paper presents a low cost automatic object tracking  algorithm  suitable  for  use  in  real-time  video  based   systems.  The  novelty  of  the  proposed  system  is  tha t  it  uses  a  simplified  version  of  the  Kanade-Lucas-Tomasi  (KLT)  technique  to  detect  features  of  both  continuous  and  discontinuous  nature.  As  discontinuous feature selection is subject to noise , and would result in non-optimal feature based obj ect tracking, the authors  propose the  use of  a  Kalman filter  for  the purpose  of  seeking optimal  estimates  in tracking.  The  integrated tracking  system  is  capable  of  handling  shadows  and  is  based  on  a  dynam ic  background  subtraction  strategy  that  minimises  errors  and  quickly  adapts  to  scene  changes.  Experimental  results  are  p rovided  to  demonstrate  the  system’s  capability  of  accurately  tracking  objects  in  real-time  applications  where  scenes  are  subject  to  noise  particularly  resulting  from  occlusions  and  sudden  illumination variations.   

References

[1] AlGarni S. and Abdennour A., Moving Vehicles Detection Using Automatic Background Extraction, in Proceedings of World Academy of Science, Engineering and Technology , Pennsylvania, pp. 1307-6884, 2006.

[2] AlNajdawi N., Bez H., and Edirisinghe E., A Novel Approach for Cast Shadow Modelling and Detection, in Proceedings of the IET International Conference on VIE , India, pp. 553- 558, 2006.

[3] Al-Najdawi N., Bez H., and Edirisinghe E., A Novel Hypothesis for Cast Shadow Modelling and Detection for Objects Tracking and Recognition, in Proceedings of the 6 th IASTED on Visualization, Imaging and Image Processing , Palma, Spain, pp. 377-382, 2006.

[4] AlNajdawi N., Edirisinghe E., and Bez H., Real- Time Object Tracking Based on a Limited, Discontinuous Feature Set, in Proceedings of the 5 th IASTED International Conference Visualization, Imaging and Image Processing , Benidorm, Spain, pp. 645-649, 2005.

[5] Amamoto N. and Fujii A., Detecting Obstructions and Tracking Moving Objects by Image Processing Technique, Computer Journal of Electronics and Communication , Japan, vol. 82, no. 11, pp. 28-37, 1999.

[6] Blake A. and Isard M., Condensation Conditional Density Propagation for Visual Tracking, International Journal of Computer Vision , vol. 29, no. 1, pp. 5-28, 1998.

[7] Boykov Y. and Huttenlocher D., Adaptive Bayesian Recognition in Tracking Rigid Objects, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition-CVPR , Canada, pp. 697-704, 2000.

[8] Brookner E., Tracking and Kalman Filtering Made Easy , John Wiley and Sons, 1999.

[9] Chen T., Lin Y., and Chen T., Intelligent Vehicle Counting Method Based on Blob Analysis in Traffic Surveillance, in Proceedings of the IEEE International Conference on Innovative Computing, Information and Control , USA, pp. 238-238, 2007.

[10] Chen Y., Rui Y., and Huang T., JPDAF Based HMM for Real-Time Contour Tracking, in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition , Kauai, pp. 543-550, 2001.

[11] Han C. and Zhang Q., Real-Time Detection of Vehicles for Advanced Traffic Signal Control, in Proceedings of the International Conference on Intelligent Transportation Systems , Phuket, pp. 245-249, 2008.

[12] Haritaoglu I., Harwood D., and Davis L., W4: Who? When? Where? What? A Real Time System for Detecting and Tracking People, in Proceedings of International Conference on Automatic Face and Gesture Recognition , Nara, Japan, pp. 222-227, 1998.

[13] Jinglei Z. and Zhengguang L., A Vision-Based Road Surveillance System Using Improved Background Subtraction and Region Growing Approach, in Proceedings of the International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing , Qingdao, pp. 819-822, 2007.

[14] MacCormick J. and Blake A., Probabilistic Exclusion and Partitioned Sampling for Multiple Object Tracking, International Journal on Computer Vision , vol. 39, no. 1, pp. 57-71, 2000.

[15] Ricquebourg Y. and Bouthemy P., Tracking of Articulated Structures Exploiting Spatio- Temporal Image Slices, in Proceedings of the 4th IEEE International Conference on Image Processing , California, pp. 480-483, 1997.

[16] Rosales R. and Sclaroff S., 3D Trajectory Recovery for Tracking Multiple Objects and Trajectory Guided Recognition of Actions, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , USA, pp. 1-7, 1999.

[17] Stauffer C. and Grimson E., Learning Patterns of Activity Using Real Time Tracking, Computer Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 22, no. 8, pp. 747-767, 2000. An Automated Real-Time People Tracking System Based on KLT Features Detection 107

[18] Shah M. and Javed O., Tracking and Object Classification for Automated Surveillance, in Proceedings of the 7 th European Conference on Computer Vision , Copenhagen, pp. 343-357, 2002.

[19] Tomasi C. and Kanade T., Factoring Image Sequences into Shape and Motion, in Proceedings of the IEEE Workshop on Visual Motion , Japan, pp. 21-28, 1991.

[20] Wren C., Azarbayejani A., Darrell T., and Pentland A., Pfinder: Real-Time Tracking of the Human Body, Computer Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 19, no. 7, pp. 780-785, 1997.

[21] Zhifang L. and Zhisheng Y., A Real-Time Vision-Based Vehicle Tracking and Traffic Surveillance, in Proceedings of the International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/ Distributed Computing , Qingdao, pp. 174-179, 2007. Nijad Al-Najdawi received his BSc degree in computer science from Mu tah University, Jordan in 1999. He obtained his MSc degree in multimedia and Internet computing, and a PhD degree in machine vision and autonomous systems from Loughborough University, UK in 2003 and 2006, respectively. After which he joined Loughborough University as a Research Associate (Post-Doc positi on) in the Electronic and Electrical Engineering Department. Currently, he is appointed as an assist ant professor at Al-Balqa Applied University, Jordan. H is research interests include: Image processing, video coding, objects tracking and recognition. Sara Tedmori received her BSc degree in computer science from the American University of Beirut, Lebanon. In 2003, she obtained her MSc degree in multimedia and Internet computing from Loughborough University, UK. In 2008, she received her PhD degree in computer scien ce from Loughborough University, UK. Currently, she is appointed as an assistant professor in the Computer Science Department at Princess Sumaya University of Technology, Jordan. Her research interests include: Object Tracking, image processing, expertise locato r, knowledge extraction, knowledge sharing, and privac y. Eran Edirisinghe received his PhD degree from the Department of Computer Science, Loughborough University, in September 1999. He was promoted to a Senior Lecturer in February 2004 and received the title of Reader in digital imaging in 2008. He is a member of the College of Peers of the Engineering & Physical Sciences Research Council, UK. His research interests include image and signal processing, video coding, texture synthesis and nov el mobile applications. Helmut Bez received a first class honours degree in Mathematics from the University of Wales in 1972, and MSc and PhD degrees from Oxford University in 1973 and 1976, respectively. He joined Rolls Royce Aero Engines in 1976, and in 1980 was appointed to the academic staff of the Department of Computer Science at Loughborough University, where he now holds the title of Reader in geometric computation. Current research interests include: The determination and application of the invariant properties of path functions, rational parametrisation, image processing and parallel computation.