Sentient computing has been a term mainly used for location-aware computing and mobile sensor networks. However, “sentient” literally means “aware” ore more specifically “responsive to or conscious of sense impressions”, or “finely sensitive in perception or feeling”. Sentient computing not only needs to be location-aware, but also identity-aware and context-aware. Here, what is termed "multimodal sentient computing" is to enable a computing system to perceive the world and relate to it in much the same way as people do using multimodal perceptions (seeing, hearing, touching, etc).
Surveillance and security are probably the best applications for sentient computing because here a surveillance or security system needs to be “finely sensitive in perception or feeling” for locations, identities and environments. Therefore, this workshop discusses issues on the emerging new area of sentient computing using multimodal sensing units, including visual, audio, thermal, vibration, and various kinds of other sensing approaches, particularly for surveillance and security applications in both civilian and military scenarios.The workshop will consist of oral presentations in the following three sessions:
(1) multimodal sensors and novel sensing approaches (visible/IR, audio/visual, thermal, acoustic, magnetic, seismic, etc.) for signature detection of humans and other subjects;
(2) multimodal data fusion algorithms for location-awareness (tracking), identity awareness (biometrics) and other human-signature-awareness (e.g., speech recognition)
(3) multimodal system issues for context-awareness (frameworks, communication, environment modeling, sentient computing spaces).