Abstracts:


 
This workshop will provide a scientific forum to present and discuss development aspects of multimodal (video, voice and sound, RFID, perimeter intrusion, infrared, chemical, etc) intelligent sensor technologies for geographical location and socio-cultural context-aware security risk assessment and decision support in human-crowd surveillance applications.
Contributions covering theoretical developments and practical applications, including but not limited to the following areas, are invited:

• algorithms for the integration of the heterogeneous information from the surveillance sensors into a coherent multimodal model of the human crowd behaviour;

• multi granularity-level feedback and human-computer interaction interfaces for the human users/agents who are the final threat assessors and decision makers in the specific security monitoring situation.

• image processing and computer-vision algorithms for tracking and recognition of relevant face and body-language patterns such as facial emotions, body gait and gestures of the humans in a crowd;

• the measurement and evaluation of the environmental parameters (background sound, ambient light, etc) that provide contextual information for specific surveillance task;

• multidisciplinary (human psychology, multicultural sociology, etc.) context-aware system for the real-time evaluation of threatening behavioural patterns of humans identified as potential security risk.

Deadline for abstract submission is Thursday, December 03, 2009. The workshop will consist of oral presentations of 30 minutes each. Submit a short abstract (1/2 page) by
e-mail to: petriu@site.uottawa.ca