ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-3/W5, 435-442, 2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.
20 Aug 2015
T. Klinger, F. Rottensteiner, and C. Heipke Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover, Hannover, Germany
Keywords: Bayes network, Classification, Pedestrians, Tracking, Online, Video Abstract. Tracking-by-detection is a widely used practice in recent tracking systems. These usually rely on independent single frame detections that are handled as observations in a recursive estimation framework. If these observations are imprecise the generated trajectory is prone to be updated towards a wrong position. In contrary to existing methods our novel approach uses a Dynamic Bayes Network in which the state vector of a recursive Bayes filter, as well as the location of the tracked object in the image are modelled as unknowns. These unknowns are estimated in a probabilistic framework taking into account a dynamic model, and a state-of-the-art pedestrian detector and classifier. The classifier is based on the Random Forest-algorithm and is capable of being trained incrementally so that new training samples can be incorporated at runtime. This allows the classifier to adapt to the changing appearance of a target and to unlearn outdated features. The approach is evaluated on a publicly available benchmark. The results confirm that our approach is well suited for tracking pedestrians over long distances while at the same time achieving comparatively good geometric accuracy.
Conference paper (PDF, 13121 KB)

Citation: Klinger, T., Rottensteiner, F., and Heipke, C.: PROBABILISTIC MULTI-PERSON TRACKING USING DYNAMIC BAYES NETWORKS, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-3/W5, 435-442,, 2015.

BibTeX EndNote Reference Manager XML