PT Journal
AU Jordi Gonzalez
   Dani Rowe
   J. Varona
   Xavier Roca
TI Understanding Dynamic Scenes based on Human Sequence Evaluation
SO Image and Vision Computing
JI IMAVIS
PY 2009
BP 1433–1444
VL 27
IS 10
DI 10.1016/j.imavis.2008.02.004
DE Image Sequence Evaluation; High-level processing of monitored scenes; Segmentation and tracking in complex scenes; Event recognition in dynamic scenes; Human motion understanding; Human behaviour interpretation; Natural-language text generation; Realistic demonstrators
AB In this paper, a Cognitive Vision System (CVS) is presented, which explains the human behaviour of monitored scenes using natural-language texts. This cognitive analysis of human movements recorded in image sequences is here referred to as Human Sequence Evaluation (HSE) which defines a set of transformation modules involved in the automatic generation of semantic descriptions from pixel values. In essence, the trajectories of human agents are obtained to generate textual interpretations of their motion, and also to infer the conceptual relationships of each agent w.r.t. its environment. For this purpose, a human behaviour model based on Situation Graph Trees (SGTs) is considered, which permits both bottom-up (hypothesis generation) and top-down (hypothesis refinement) analysis of dynamic scenes. The resulting system prototype interprets different kinds of behaviour and reports textual descriptions in multiple languages.
ER