Activity Monitoring in Smart Environments

 

GOAL

 

The main objective of this work is to simultaneously track multiple users and estimate human activity in a smart environment.

 

DEMONSTRATION

 

Multi-person tracking: Demo

This video shows our multi-person tracking system estimating in real-time the number, location and configuration (sitting/standing) of people in a room. The output of the system is used to steer a PTZ camera towards the main presenter.

 

Environment control / Activity monitoring: Demo

This video shows our system used in a smart-office application. The system tracks people as they move in the smart room. Devices and software are triggered and controlled based on context as well as people’s location and activity

 

Speaker detection Demo Demo Demo

 

These videos show our algorithm for speaker detection using our multi-person tracking algorithm and a DOA (Direction-Of-Arrival)-based speaker detection

 

 

Oxygen demonstration: Demo

Tracking  Demo Demo

 

 

 

 REFERENCES

D. Demirdjian, L. Taycher, G. Shakhnarovich, K. Grauman and T. Darrell. Avoiding the ``Streetlight Effect'': Tracking by Exploring Likelihood Modes. In ICCV’05. [PDF].

D. Demirdjian, K. Tollmar, K. Koile, N. Checka and T. Darrell. Activity Maps for Location-Aware Computing. In Proceedings of IEEE Workshop on Applications of Computer Vision (WACV2002), December 2002, Orlando, Florida. [PDF]

Kevin Wilson, Neal Checka, David Demirdjian and Trevor Darrell. Audio-Video Array Source Separation for Perceptual User Interfaces. In Proceedings of Workshop on Perceptive User Interfaces, 2001.

T. Darrell, D. Demirdjian, N. Checka and P. Felzenszwalb. Plan-view trajectory estimation with dense stereo background models. In Proceedings of ICCV’01, Vancouver, Canada, July 2001, pages 628-635 , volume II. [PDF]