Moving object detection and tracking

Picture Summary

An Edge Segment Based Approach

mo4

 

Detection of moving edges

mo3

 

Full description

mo2

Edge Motion Verification using GHT
We need edge lists obtained from frame-1 and frame-2 to compute edge motion at frame-2. Fig. 3 illustrates Edge Motion computation procedure. For all the edges extracted from frame-1 we do the followings: Generate and store R-table for each edge segment. Take the center point of the boundary as the reference point. For each edge pixel (\(X_{ep}\), \(Y_{ep}\)) do the following
1. Compute \(\Omega\) as the tangential orientation of the segment.
2. Compute length \(r\) as the radial vector joining the reference point \((X_\text{Ref}, Y_\text{Ref})\) and the edge point \((X_{ep}, Y_{ep})\).
3. Compute orientation  as the angle of the radial vector with respect to the horizontal line.
4. Using \(\Omega\) as an index into the R-table we store a tuple \(r\) and  at the index position.

5. When all the edge points are indexed, the R-table will fully represent the candidate edge segment.
 mo1

 

References

SCI/SCIE Indexed Journals:

▷ Mahbub Murshed, Adin Ramirez, Jaemyun Kim, Oksam Chae, “Statistica Binary edge frequency accumulation model for moving object detection”, International Journal of Innovative Computing, Information and Control (ISSN 1349-4198) Volume 8, Number 6, June 2012

▷ M. Julius Hossain, M. Ali Akber Dewan, Oksam Chae, “A flexible edge matching technique for object detection in dynamic environment”, Appl Intell, 2011

▷ Mahbub Murshed, Adin Ramirez, Jaemyun Kim and Oksam Chae, “Statistica Binary edge frequency accumulation model for moving object detection”, Accepted, International Journal of Innovative Computing, Information and Control (ISSN 1349-4198), Volume 8, Number 6, June 2012.9(SCIE)

▷ Mahbub Murshed, Md. Hasanul Kabir, Oksam Chae, “Moving Object Tracking – An Edge Segment-based Approach”, International Journal of Innovative Computing, Information and Control (ISSN 1349-4198), Volume 7, Number 7(A), July 2011. (IJICIC) [SCIE], Impact Factor 2.932

▷ M. Ali Akber Dewan, M. Julius Hossain, Oksam Chae, “Background Independent Moving Object Segmentation for Video Surveillance”, IEICE Transaction on Communications, vol.E92-B, No.02, pp. 1-14, February 2009, ISSN: 0916-8516, Impact Factor:  0.252. (SCI)

Comments are closed.