Real-Time Spatio-Temporal Analysis of Dynamic Scenes in 3D Soccer Simulation Export

@incollection{citeulike:5632913, abstract = {We propose a framework for spatio-temporal real-time analysis of dynamic scenes. It is designed to improve the grounding situation of autonomous agents in (simulated) physical domains. We introduce a knowledge processing pipeline ranging from relevance-driven compilation of a qualitative scene description to a knowledge-based detection of complex event and action sequences, conceived as a spatio-temporal pattern matching problem. A methodology for the formalization of motion patterns and their inner composition is introduced and applied to capture human expertise about domain-specific motion situations. We present extensive experimental results from the 3D soccer simulation that substantiate the online applicability of our approach under tournament conditions, based on 5 Hz a) precise and b) noisy/incomplete perception.}, author = {Warden, Tobias and Lattner, Andreas and Visser, Ubbo}, citeulike-article-id = {5632913}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-642-02921-9_32}, citeulike-linkout-1 = {http://www.springerlink.com/content/9281304l67l74214}, doi = {10.1007/978-3-642-02921-9_32}, journal = {RoboCup 2008: Robot Soccer World Cup XII}, keywords = {aip, event\_detection}, pages = {366--378}, posted-at = {2009-08-24 20:43:31}, priority = {2}, title = {Real-Time Spatio-Temporal Analysis of Dynamic Scenes in 3D Soccer Simulation}, url = {http://dx.doi.org/10.1007/978-3-642-02921-9_32}, year = {2009} }

TY - CHAP ID - citeulike:5632913 L3 - citeulike-article-id:5632913 N2 - We propose a framework for spatio-temporal real-time analysis of dynamic scenes. It is designed to improve the grounding situation of autonomous agents in (simulated) physical domains. We introduce a knowledge processing pipeline ranging from relevance-driven compilation of a qualitative scene description to a knowledge-based detection of complex event and action sequences, conceived as a spatio-temporal pattern matching problem. A methodology for the formalization of motion patterns and their inner composition is introduced and applied to capture human expertise about domain-specific motion situations. We present extensive experimental results from the 3D soccer simulation that substantiate the online applicability of our approach under tournament conditions, based on 5 Hz a) precise and b) noisy/incomplete perception. JF - RoboCup 2008: Robot Soccer World Cup XII EP - 378 TI - Real-Time Spatio-Temporal Analysis of Dynamic Scenes in 3D Soccer Simulation SP - 366 KW - aip KW - event_detection AU - Warden, Tobias AU - Lattner, Andreas AU - Visser, Ubbo PY - 2009/// UR - http://dx.doi.org/10.1007/978-3-642-02921-9_32 ER -