Abstract

The Detection and Tracking of human objects is one among the significant tasks encountered in Computer Vision. Yet, numerous problems associated with it are developing even at present. Various monitoring systems involved in the automatic detection of human objects in motion is found to have difficulty in spotting the difference in brightness, while the brightness of the moving human objects and the background is indistinguishable. Target tracking mainly concern with the evaluation of object’s speed and position over time using one or multiple sensors. This study introduces the human object detection and tracking system, in which multiple objects are being detected without flaw. For a given video clip, the system does segmentation and tracking of similar video clips. The segmentation is done using the threshold method. After the segmentation process, we have introduced an optimization technique in order to refine the segmented results. The optimization used in our proposed work is a modified form of Particle Swarm Optimization (IPSO). Once the optimization of the segmented result is done the detection of human and moving object are performed The implementation is done in the working platform of MATLAB and the results shows that our proposed method delivers better detection of multiple objects than other existing methods.

Keywords:

Block matching, improved particle swarm optimization, object detection, shot segmentation, thresholding,

References

1. Bhattacharya, S., H. Idrees, I. Saleemi, S. Ali and M. Shah, 2011. Moving Object Detection and Tracking in Forward Looking Infra-red Aerial Imagery. In: Hammoud, R. et al. (Eds.), Machine Vision Beyond Visible Spectrum. Augmented Vision and Reality, 1, Springer-Verlag, Berlin, Heidelberg.
   CrossRef    
2. Fablet, R. and M.J. Black, 2002. Automatic detection and tracking of human motion with a view-based representation. Proceeding of the 7th European Conference on Computer Vision, pp: 476-491.
   CrossRef    
3. Jepson, A., D.J. Fleet and T.F. Elmaraghi, 2003. Robust online appearance models for visual tracking. IEEE T. Pattern Anal., 25(10): 1296-1311.
   CrossRef    
4. Kalpesh, R.J., M.A. Lokhandwala and A.P. Gharge, 2011. Vision based moving object detection and tracking. Proceeding of the National Conference on Recent Trends in Engineering and Technology.
   
5. Khan, M.U.G. and A. Saeed, 2009. Human detection in videos. J. Theor. Appl. Inform. Technol., 5(2): 212-220.
   
6. Li, L., Z. Xianglin, L. Xi, H. Weiming and Z. Pengfei, 2009. Video shot segmentation using graph-based dominant-set clustering. Proceeding of the 1st International Conference on Internet Multimedia Computing and Service. New York, USA.
   CrossRef    
7. Niu, W., J. Long, D. Han and Y.F. Wang, 2004. Human activity detection and recognition for video surveillance. Proceeding of IEEE International Conference on Multimedia and Expo, 1: 719-722.
   
8. Patel, H. and M.P. Wankhade, 2011. Human tracking in video surveillance. Int. J. Emerg. Technol. Adv. Eng., 1(2).
   
9. Paul, M., S. Haque and S. Chakraborty, 2013. Human detection in surveillance videos and its applications-a review. EURASIP J. Adv. Sig. Pr., 176: 1-16.
   CrossRef    
10. Ramoser, H., T. Schlogl, C. Beleznai, M. Winter and H. Bischof, 2003. Shape-based detection of humans for video surveillance applications. Proceeding of the International Conference on Image Processing.
    CrossRef    
11. Seo, H.J. and P. Milanfar, 2009. Detection of human actions from a single example. Proceeding of 12th IEEE International Conference on Computer Vision.
    
12. Sreedevi, M., Y.K. Avulapati, G.A. Babu and S.R. Kumar, 2012. Real time movement detection for human recognition. Proceeding of the World Congress on Engineering and Computer Science, Vol. 1.
    
13. Vineet, V., J. Warrell, L. Ladicky and P.H. Torr, 2011. Human instance segmentation from video using detector-based conditional random fields. Proceeding of the 22nd British Machine Vision Conference.
    CrossRef    
14. Wang, J., G. Bebis and R. Miller, 2006. Robust video-based surveillance by integrating target detection with tracking. Proceeding of the Conference on Computer Vision and Pattern Recognition Workshop, pp: 137.
    
15. Wu, B. and R. Nevatia, 2007. Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors. Int. J. Comput. Vision, 75(2).
    CrossRef    
16. Zhang, Z., P.L. Venetianer and A.J. Lipton, 2008. A robust human detection and tracking system using a human-model-based camera calibration. Proceeding of the 8th International Workshop on Visual Surveillance.
    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.