Resolving Conflicts in Object Tracking in Video Stream Employing Key Point Matching
A novel approach to resolving ambiguous situations in object tracking in video streams is presented. The proposed method combines standard tracking technique employing Kalman filters with global feature matching method. Object detection is performed using a background subtraction algorithm, then Kalman filters are used for object tracking. At the same time, SURF key points are detected only in image sections identified as moving objects and stored in trackers. Descriptors of these key points are used for object matching in case of tracking conflicts, for identification of the current position of each tracked object. Results of experiments indicate that the proposed method is useful in resolving conflict situations in object tracking, such as overlapping or splitting objects.
Keywordsvideo analysis object tracking Kalman filters image matching
Unable to display preview. Download preview PDF.
- 1.Czyżewski, A., Szwoch, G., Dalka, P., et al.: Multi-Stage Video Analysis Framework. In: Lin, W. (ed.) Video Surveillance, pp. 147–172. InTech, Rijeka (2011)Google Scholar
- 4.Lucas, B.D., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: Proc. of Imaging Understanding Workshop, pp. 121–130 (1981)Google Scholar
- 5.Stauffer, C., Grimson, W.E.L.: Adaptive Background Mixture Models for Real-time Tracking. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 246–252 (1999)Google Scholar
- 7.Welch, G., Bishop, G.: An Introduction to the Kalman Filter. Technical report TR 95-041. UNC-Chapel Hill (2006), http://www.cs.unc.edu/~welch/kalman/
- 8.Szwoch, G., Dalka, P., Czyżewski, A.: Resolving Conflicts in Object Tracking for Automatic Detection of Events in Video. Elektronika 52, 52–55 (2011)Google Scholar
- 10.PETS, Benchmark Data (2006), http://www.cvg.rdg.ac.uk/PETS2006/data.html