N. Pissinou et al., Spatio-temporal composition of video objects: Representation and querying in video database systems, IEEE KNOWL, 13(6), 2001, pp. 1033-1040
Citations number
15
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
A key characteristic of video data is the associated spatial and temporal s
emantics. It is important that a video model models the characteristics of
objects and their relationships in time and space. Allen's 13 temporal rela
tionships [2] are often used in formulating queries that contain the tempor
al relationships among video frames. For the spatial relationships, most of
the approaches are based on projecting objects on a two or three-dimension
al coordinate system. However, very few attempts have been made formally to
represent the spatio-temporal relationships of objects contained in the vi
deo data and to formulate queries with spatio-temporal constraints. The pur
pose of our work is to design a model representation for the specification
of the spatio-temporal relationships among objects in video sequences. The
model describes the spatial relationships among objects for each frame in a
given video scene and the temporal relationships (for this frame) of the t
emporal intervals measuring the duration of these spatial relationships. It
also models the temporal composition of an object, which reflects the evol
ution of object's spatial relationships over the subsequent frames in the v
ideo scene and in the entire video sequence. Our model representation also
provides an effective and expressive way for the complete and precise speci
fication of distances among objects in digital video. This model is a basis
for the annotation of raw video.