An Object-Oriented Approach Using a Top-Down and Bottom-Up Process for Manipulative Action Recognition
- Cite this paper as:
- Li Z., Fritsch J., Wachsmuth S., Sagerer G. (2006) An Object-Oriented Approach Using a Top-Down and Bottom-Up Process for Manipulative Action Recognition. In: Franke K., Müller KR., Nickolay B., Schäfer R. (eds) Pattern Recognition. DAGM 2006. Lecture Notes in Computer Science, vol 4174. Springer, Berlin, Heidelberg
Different from many gesture-based human-robot interaction applications, which focused on the recognition of the interactional or the pointing gestures, this paper proposes a vision-based method for manipulative gesture recognition aiming to achieve natural, proactive, and non-intrusive interaction between humans and robots. The main contributions of the paper are an object-centered scheme for the segmentation and characterization of hand trajectory information, the use of particle filtering methods for an action primitive spotting, and the tight coupling of bottom-up and top-down processing that realizes a task-driven attention filter for low-level recognition steps. In contrast to purely trajectory based techniques, the presented approach is called object-oriented w.r.t. two different aspects: it is object-centered in terms of trajectory features that are defined relative to an object, and it uses object-specific models for action primitives. The system has a two-layer structure recognizing both the HMM-modeled manipulative primitives and the underlying task characterized by the manipulative primitive sequence. The proposed top-down and bottom-up mechanism between the two layers decreases the image processing load and improves the recognition rate.
Unable to display preview. Download preview PDF.