TY  - JOUR
AU  - Jordi Gonzalez
AU  - Dani Rowe
AU  - J. Varona
AU  - Xavier Roca
PY  - 2009//
TI  - Understanding Dynamic Scenes based on Human Sequence Evaluation
T2  - IMAVIS
JO  - Image and Vision Computing
SP  - 1433–1444
VL  - 27
IS  - 10
KW  - Image Sequence Evaluation
KW  - High-level processing of monitored scenes
KW  - Segmentation and tracking in complex scenes
KW  - Event recognition in dynamic scenes
KW  - Human motion understanding
KW  - Human behaviour interpretation
KW  - Natural-language text generation
KW  - Realistic demonstrators
N2  - 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.
UR  - http://dx.doi.org/10.1016/j.imavis.2008.02.004
N1  - ISE
ID  - Jordi Gonzalez2009
ER  -