Title :
Person tracking-by-detection with efficient selection of part-detectors
Author :
Schumann, Andrew ; Bauml, Martin ; Stiefelhagen, Rainer
Author_Institution :
Inst. for Anthropomatics, Karlsruhe Inst. of Technol., Karlsruhe, Germany
Abstract :
In this paper we introduce a new person tracking-by-detection approach based on a particle filter. We leverage detection and appearance cues and apply explicit occlusion reasoning. The approach samples efficiently from a large set of available person part-detectors in order to increase runtime performance while retaining accuracy. The tracking approach is evaluated and compared to the state of the art on the CAVIAR surveillance dataset as well as on a multimedia dataset consisting of six episodes of the TV series The Big Bang Theory. The results demonstrate the versatility of the approach on very different types of data and its robustness to camera movement and non-pedestrian body poses.
Keywords :
computer graphics; multimedia systems; object tracking; particle filtering (numerical methods); CAVIAR surveillance dataset; TV series; The Big Bang Theory; appearance cues; camera movement; explicit occlusion reasoning; leverage detection; multimedia dataset; nonpedestrian body poses; part detectors; particle filter; person tracking by detection; runtime performance; Accuracy; Cameras; Computational modeling; Detectors; Histograms; Robustness; Tracking;
Conference_Titel :
Advanced Video and Signal Based Surveillance (AVSS), 2013 10th IEEE International Conference on
Conference_Location :
Krakow
DOI :
10.1109/AVSS.2013.6636614
