This Chapter focuses on the first type of object tracking algorithms, namely on Kalman and particle filters. A theory of these algorithms may be found in many publications, there are also reports on implementation of these approaches to object tracking in video. However, developers of VCA systems still face two important problems. The first one is related to obtaining accurate measurements of positions and sizes of the tracked objects, required for updating their tracker. It is easy to do if the object is clearly identified in the camera image, but in case of tracking conflicts, obtaining a valid measurement is not trivial The second problem is related to the parameters tuning in the object detection and tracking algorithms, in order to obtain accurate object tracks. Despite the abundance of publications on object tracking in video with these methods, it is not easy to find a clear solution to both problems. This Chapter has therefore two main aims. First, it attempts to fill the abovementioned gap, by describing the influence of the algorithm parameters on the obtained results, and also presenting the problem of obtaining accurate measurements for updating the tracking filter in presence of conflicts. Second, a novel approach that combines Kalman filters with particle filters, is proposed. This dual-type tracker uses the simpler Kalman filter when there are no conflicts, and the more demanding particle tracker only for resolving these conflicts.
Authors
Additional information
- Category
- Publikacja monograficzna
- Type
- rozdział, artykuł w książce - dziele zbiorowym /podręczniku w języku o zasięgu międzynarodowym
- Language
- angielski
- Publication year
- 2017
