Hybrid tracking model for multiple object videos using second derivative based visibility model and tangential weighted spatial tracking model
- DOI
- 10.1080/18756891.2016.1237188How to use a DOI?
- Keywords
- hybrid tracking; visibility model; spatial tracking; tangential weighed; second derivative
- Abstract
In the area of video surveillance, tracking model for multiple object video is still a challenging task since the objects are usually affected with inter-object occlusion, object confusion, different posing, environment with heavy clutter, small size of objects, similar appearance among objects, and interaction among the multiple objects In order to alleviate these challenges, literature presents different tracking models using spatial and visual information. Accordingly, in this paper, we have developed a hybrid tracking model for tracking the multiple objects from the videos using twofold architecture. At first, visibility model for tracking is proposed based on the second derivative model, which considers the second derivative function to predict the objects. Secondly, a spatial tracking model is proposed using tangential weighted function. Finally, these two contributions are effectively included in the hybrid tracking model for multiple object tracking and the performance analysis is carried out using two videos from UCSD dataset. From the results, we proved that the proposed hybrid tracking model achieves the Multiple Object Tracking Precision (MOTP) of 99% than the other exiting tracking models.
- Copyright
- © 2016. the authors. Co-published by Atlantis Press and Taylor & Francis
- Open Access
- This is an open access article under the CC BY-NC license (http://creativecommons.org/licences/by-nc/4.0/).
Download article (PDF)
View full text (HTML)
Cite this article
TY - JOUR AU - Felix M. Philip AU - Rajeswari Mukesh PY - 2016 DA - 2016/09/01 TI - Hybrid tracking model for multiple object videos using second derivative based visibility model and tangential weighted spatial tracking model JO - International Journal of Computational Intelligence Systems SP - 888 EP - 899 VL - 9 IS - 5 SN - 1875-6883 UR - https://doi.org/10.1080/18756891.2016.1237188 DO - 10.1080/18756891.2016.1237188 ID - Philip2016 ER -