A New Approach to Improve Tracking Performance of Moving Objects with Partial Occlusion.

Document Type : Original Research (Full Papers)

Authors

1 MSc Student of Computer and Information Technology Engineering, Qazvin Branch, Islamic Azad University

2 Faculty of Computer and Information Technology Engineering, Qazvin Branch, Islamic Azad University, Qazvin

Abstract

< p>Tracking objects in video images has attracted much attention by machine vision and image processing researchers in recent years. Due to the importance of the subject, this paper presents a method for improving object tracking tasks with partial occlusion, which increases the efficiency of tracking. The proposed approach first performs a pre-processing and extracts the tracking targets from the image. Then the salient feature points are extracted from the targets that are moving objects. In the next step, the particle filter is used for tracking. The final steps are modifying points and updates. A new approach is used to determine the speed of the feature points because the speed of some points can be out of range and this causes errors in tracking especially when there is occlusion. The location of the new points is corrected and updated using the threshold values in modifying the process as needed. The experiments performed on the video sequence of PETS2000 database show that the precision and recall of the proposed approach are higher than other compared approaches.

Keywords


[1] Yilmaz, A.; Javed, O.; Shah, M., "Object tracking: A survey",  Acm  computing surveys (CSUR), vol. 38, p. 13  (2006). 
[2] Watanabe, G.; Fukui, S.; Iwahori, Y.; Bhuyan, M K.; Woodham, R J.;  Adachi,  Y.;  "Tracking  Method  in  Consideration  of  Existence  of  Similar Object around Target Object", Procedia Computer Science,  vol. 22, pp. 366-374 (2013). 
[3] Cancela, B.; Ortega, M.; Fernandez, A.; Penedo, M G., "Hierarchical  framework for robust and fast multiple-target tracking in surveillance  scenarios", Expert Systems with Applications, vol. 40, pp. 1116-1131  (2013). 
[4] Liu, H.; Sun, F., "Efficient visual tracking using particle filter with  incremental likelihood calculation", Information Sciences, vol. 195,  pp. 141-153 (2012). 
[5] Naushad Ali, M. M.; Abdullah-Al-Wadud, M.; Lee, S. L., "Multiple  object tracking with partial occlusion handling using salient feature  points", Information Sciences, vol. 278, pp. 448-465 (2014). 
[6] Harris,  C.;  Stephens,  M.,  "A  combined  corner  and  edge  detector",   Alvey vision conference , pp. 10-5244 (1988). 
[7] Dalal, N.; Triggs, B., "Histograms of oriented gradients for human  detection", IEEE, Computer Vision and Pattern Recognition (CVPR).  pp. 886-893 (2005). 
[8] Xu, R.; Nikouei, S. Y.; Chen, Y.; Polunchenko, A.; Song, S.; Deng, 
C.;  Faughnan,  T.  R.,  "Real-time  human  objects  tracking  for  smart surveillance  at  the  edge",  IEEE,  International  Conference  on  Communications (ICC), pp. 1-6 (2018). 
[9] Zhou, S.; Ke, M.; Qiu, J.; Wang, J., "A Survey of Multi-object Video  Tracking Algorithms", International Conference on Applications and  Techniques in Cyber Security and Intelligence. pp. 351-369 (2018). 
[10] Xiao,  J.;  Oussalah,  M.,  "On  the  use  of  contextual  information  for  robust  colour-based  particle  filter  tracking",  Eighth  International  Conference  on  Image  Processing  Theory,  Tools  and  Applications  (IPTA) , pp. 1-6 (2018). 
[11] f. f. p. r. a. u. p. PETS2000/. [12]  Sobti, A.; Arora, C.; Balakrishnan, M., "Object detection in real-time  systems:  Going  beyond  precision",  IEEE.  Winter  Conference  on  Applications of Computer Vision (WACV), pp. 1020-1028 (2018). 
[13]  Li,  X.;  Wang,  K.;  Wang,  W.;  Li,  Y.,  "A  multiple  object  tracking  method  using  Kalman  filter",  IEEE.  International  Conference  on  Information and Automation (ICIA). pp. 1862-1866 (2010). 
[14]  Comanici,  D.  u.;  Ramesh,  V.;  Meer,  P.,  "Kernel-based  object  tracking",  IEEE.  Transactions  on  pattern  analysis  and  machine  intelligence, vol. 25, pp. 564-577 (2003). 
[15]  Ning, J.; Zhang, L.; Zhang, D.; Wu, C., "Robust mean-shift tracking  with  corrected  background-weighted  histogram",  IET  computer  vision, vol. 6, pp. 62-69 (2012).