NANO SCIENTIFIC RESEARCH CENTRE PVT.LTD., AMEERPET, HYD
WWW.NSRCNANO.COM, 09640648777, 09652926926
DOT NET PROJECTS LIST--2013
DOT NET 2013 IEEE PAPERS
Combining Head Pose and Eye Location Information for
Gaze Estimation
Abstract:
Head
pose and eye location for gaze estimation has been separately studied in
numerous works in the literature. Previous research shows that satisfactory
accuracy in head pose and eye location estimation can be achieved in
constrained settings. However, in the presence of non-frontal faces, eye
locators are not adequate to accurately locate the center of the eyes. On the
other hand, head pose estimation techniques are able to deal with these conditions;
hence, they may be suited to enhance the accuracy of eye localization.
Therefore, in this paper, a hybrid scheme is proposed to combine head pose and
eye location information to obtain enhanced gaze estimation. To this end, the
transformation matrix obtained from the head pose is used to normalize the eye
regions, and in turn, the transformation matrix generated by the found eye
location is used to correct the pose estimation procedure.
The
scheme is designed to enhance the accuracy of eye location estimations, particularly
in low-resolution videos, to extend the operative range of the eye locators,
and to improve the accuracy of the head pose tracker. These enhanced
estimations are then combined to obtain a novel visual gaze estimation system,
which uses both eye location and head information to refine the gaze estimates.
From the experimental results, it can be derived that the proposed unified scheme
improves the accuracy of eye estimations by 16% to 23%. Furthermore, it
considerably extends its operating range by more than 15 by overcoming the
problems introduced by extreme head poses. Moreover, the accuracy of the head
pose tracker is improved by 12% to 24%. Finally, the experimentation on the
proposed combined gaze estimation system shows that it is accurate (with a mean
error between 2 and 5 ) and that it can be used in cases where classic
approaches would fail without imposing restraints on the position of the head.
Existing System:
Head pose estimation often requires multiple cameras, or complex face
models, which requires accurate initialization. Ba and Odobez improve the
accuracy of pose estimates and of the head tracking by considering these as two
coupled problems in a probabilistic setting within a mixed-state particle filter
framework. They refine this method by the fusion of four camera views. Huang
and Trivedi propose to integrate a skin-tone edge-based detector into a Kalman-filter-based
robust head tracker and hidden-Markov-model-based pose estimator. Hu et al.
describe a coarse-to-fine pose estimation method by combining facial appearance
asymmetry and 3-D head model.
Proposed System:
we propose a unified framework for head pose and eye location estimation
for visual gaze estimation. The head tracker is initialized using the location
and the orientation of the eyes, whereas the latter ones are obtained by
pose-normalized eye patches obtained from the head tracker. A feedback mechanism
is employed in the evaluation of the tracking quality. When the two modules do
not yield concurring results, both are adjusted to get in line with each other,
aiming to improve the accuracy of both tracking schemes. The improved head pose
estimation is then used to define the field of view, while displacement vectors
between the pose-normalized eye locations and their resting positions are used
to adjust the gaze estimation obtained by the head pose only. In this way, a
novel multimodal visual gaze estimator is obtained.
Software
and Hardware Requirements
Hardware Required:
System : Pentium IV
Hard Disk : 80
GB
RAM : 512 MB
Software Required:
Operating
System : Windows
XP
Language : C#
Modules:
·
Access Image
·
Detect face And Image
·
Draw Rectangles
No comments:
Post a Comment