Making the home safer and more secure through visual surveillance
A. Prati2, R. Cucchiara1 and R. Vezzani1
1Department of Information Engineering, University of Modena
and Reggio Emilia, Modena, Italy
2Department of Sciences and Methods in Engineering, University
of Modena and Reggio Emilia, Modena, Italy
Video surveillance has a direct application in intelligent home automation
or domotics (from the Latin word domus, that means home, and
informatics). In particular, in-house video surveillance can provide good
support for people with some difficulties (e.g. elderly or disabled people)
living alone and with limited autonomy. New hardware technologies for
surveillance are now affordable and provide high reliability. Problems
related to reliable software solutions are not completely solved, especially
concerning the application of general-purpose computer vision techniques
in indoor environments. Indeed, assuming the objective is to detect the
presence of people, track them, and recognize dangerous behaviors by means
of abrupt changes in their posture, robust techniques need to cope with
nontrivial dificulties.
In particular, luminance changes, shadows and frequent posture changes
must be taken
into account. Long-lasting occlusions are common due to the proximity
of the cameras and
the presence of furniture and doors that can often hide parts of a persons
body. For these
reasons, we developed computer vision techniques based on probabilistic
and appearancebased
tracking, particularly conceivable for people tracking and posture classi.cation.
Despite its effectiveness for long-lasting and large occlusions, this
approach tends to fail whenever the person is monitored with multiple
cameras and he appears in one of them already occluded. Different views
provided by multiple cameras can be exploited to solve occlusions by warping
known object appearance into the occluded view. To this aim, this paper
describes an approach to posture classi.cation based on projection histograms,
reinforced by HMM for assuring temporal coherence of the posture. The
single camera posture classification is then exploited in the multi-camera
system to solve the cases in which the occlusions make the classi.cation
impossible.
These above-mentioned problems are analyzed and solutions based on background
suppression, appearance-based probabilistic tracking, and probabilistic
reasoning for
posture recognition are described. Experimental results with different
amounts and types of
occlusions are reported and demonstrate that the proposed approach is
capable of correctly
classifying the posture even in the case of large occlusions.
Paper presented
at Measuring Behavior 2005
, 5th International Conference on Methods and Techniques
in Behavioral Research, 30 August - 2 September 2005, Wageningen, The
Netherlands.
© 2005 Noldus
Information Technology bv
|