Ev ve Ofis taşıma sektöründe lider olmak.Teknolojiyi takip ederek bunu müşteri menuniyeti amacı için kullanmak.Sektörde marka olmak.
İstanbul evden eve nakliyat
Misyonumuz sayesinde edindiğimiz müşteri memnuniyeti ve güven ile müşterilerimizin bizi tavsiye etmelerini sağlamak.
Tracking
in Uncalibrated Multiple Cameras, and View Invariant Representation
and Recognition of Human Action
Presented by: Dr. Mubarak Shah
ABSTRACT: Automatically understanding human behavior from
video sequences is a very challenging problem. This involves
'extraction' of relevant visual information from a video sequence,
'representation' of that information in a s uitable form,
and 'interpretation' of visual information for the purpose
of recognition and learning human behavior.
In this talk, first we will present our approach for tracking
people in multiple cameras. We employ the novel appro ach
of finding the limits of field of view (FOV) of a camera as
visible in the other cameras. Using this informatio n, when
a person is seen in one camera, we are able to predict all
the other cameras in which this person will be vi sible. Moreover,
we apply the FOV constraint to disambiguate between possible
candidates for correspondence. Track ing in each individual
camera needs to be resolved before such an analysis can be
applied. We perform tracking in a single camera using background
subtraction, followed by region correspondence. This takes
into account the velocities, sizes and distance of bounding
boxes obtained through connected component labeling.
In the second part of the talk, we will discuss automatically
understanding human actions using motion trajectories derived
from video sequences. Since an action takes place in 3-D,
and is projected on 2-D image, depending on the v iewpoint
of the camera the projected 2-D trajectory may vary. This
may create a problem in interpretation of trajec tories at
the higher level. However, if the representation of actions
only captures characteristics, which are view -invariant,
then the higher-level interpretation can proceed without any
ambiguity. We will discuss a computational representation
of human action to capture dramatic changes in a motion trajectory
using spatio-temporal curvature o f 2-D trajectory. This representation
is compact, view-invariant, and is capable of explaining an
action in terms o f meaningful atomic units.
|