[Back]

O. Icoglu, A. Mahdavi:
"A vision-based sensing system for sentient building models";
in: "CIB W78 22nd Conference on Information Technology in Construction", R.J. Scherer, P. Katranuschkov, S. Schapke (ed.); 22nd Conference on Information Technology in Construction, Institute for Construction Informatics, Technical University of Dresden, Dresden, 2005, 559 - 566.

The quality and cost effectiveness of services in the building industry possess high potential for improvement. A possible approach to bringing out this potential is to conceive buildings as sentient entities that contiuously adapt to changes in environment and occupancy. To achieve real-time building operation support and to avoid bottleneck situations resulting from manual model input and updating activities, the underlying model must possess the capability to autonomously update itself. This requires a versatile sensing mechanism that provides real-time facility state information. The research described in this paper aims to demonstrate the potential of vision-based sensing solutions to support the operations of sentient buildings. Toward this end, a system prototype has been implemented that focuses on building systems control (lighting). The resulting arrangement of required hardware and software components (tied together via internet) provides a flexible and self-adapting structure, which is highly suited to the requirements of control applications for sentient buildings.