Automated surveillance systems can use SentiVeillance for biometric face recognition and pedestrian / vehicle tracking in live video streams.
The possible uses can be security, law enforcement, visitors counting, attendance control.
Some applications may require to enroll the users in advance (such as list of employees or watch-list of unwanted persons or suspect criminals), whereas other just work on the general public passing by.
Also can be used to detect if passers-by draw attention to certain ads or billboards.
The SDK allows to create networked applications and systems on Windows and Linux platforms.
This demo video used the Chokepoint dataset[1, 2]. The permission to use it with this demo application was granted by the owners of the data.
References:
[1] http://arma.sourceforge.net/chokepoint/.
[2] Y. Wong, S. Chen, S. Mau, C. Sanderson, B.C. Lovell. Patch-based Probabilistic Image Quality Assessment for Face Selection and Improved Video-based Face Recognition. In IEEE Biometrics Workshop, Computer Vision and Pattern Recognition (CVPR) Workshops, pages 81-88. IEEE, June 2011. http://conradsanderson.id.au/pdfs/won...
