Abstract
Face detection
on general embedded devices is fundamentally different from the conventional
approach on personal computer or consumer digital camera due to the limited
computation and power capacity. The resource-limited characteristic gives rise
to new challenges for implementing a real-time video surveillance system with
smart cameras. In this work, we present the design and implementation of
Pyramid-like FAce Detection (P-FAD), a real-time face detection system constructed
on general embedded devices. Motivated by the observation that the computation
overhead increases proportionally to its pixel manipulation, P-FAD proposes a
hierarchical approach to shift the complex computation to the promising
regions. More specifically, P-FAD present a three-stage coarse, shift, and
refine procedure, to construct a pyramid-like detection framework for reducing
the computation overhead significantly. This framework also strikes a balance
between the detection speed and accuracy. We have implemented P-FAD on
notebook, Android phone and our embedded smart camera platform. An extensive
system evaluation in terms of detailed experimental and simulation results is
provided. Our empirical evaluation shows that P-FAD outperforms V-J detector
calibrated color detector (VJ-CD) and color detector followed by a V-J detector
(CD-VJ), the state of the art real-time face detection techniques by 4.7 –8.6
on notebook and by up to 8.2 on smart phone in terms of the detection speed.
Domain : Image Processing
Contact Details
Ph.no : 7200555526
e-mail id : info.nanosoftwares@gmail.com
No comments:
Post a Comment