We present a novel approach to tracking 2D human motion in uncalibrated monocular videos. Human motion usually exhibits timevarying patterns, and we propose to use locally learnt ...
Abstract. In this paper, we introduce a novel evolution-based segmentation algorithm by using the heat flow analogy, to gain practical advantage. The proposed algorithm consists of...
A novel method for the simultaneous modeling and tracking (SMAT) of a feature set during motion sequence is proposed. The method requires no prior information. Instead the a poste...
We propose the use of 3D (2D+time) Shape Context to recognize the spatial and temporal details inherent in human actions. We represent an action in a video sequence by a 3D point ...
Franziska Meier, Irfan A. Essa, Matthias Grundmann
In previous work we have presented a prototype of an assistant system for the blind that can be used for self-localization and interactive object identification of static objects ...