Space-Time Interest Points
Ivan Laptev and Tony Lindeberg
In Proc. ICCV 2003, Nice, France, pp.I:432-439.
Abstract
Local image features or interest points provide compact and
abstract representations of patterns in the image.
In this paper we propose to extend the notion of spatial interest points
into the spatio-temporal domain and argue that the resulting features
often correspond to the interesting events in video and can be used for
the compact representation of video data as well as for its
interpretation.
To detect spatio-temporal events, we build on the idea of the Harris
and Förstner interest point operators and detect local structures
in space-time where the image values have significant local variations
in both space and time.
We then estimate the spatio-temporal extents of the detected events
and compute their scale-invariant spatio-temporal descriptors.
Using such descriptors we classify events and construct
video representation in terms of labeled space-time points.
On the problem of human motion analysis we illustrate how the
proposed method enables the detection of walking people in scenes
with occlusions and dynamic backgrounds.
PDF:
(1.0Mb)
Demonstractions:
handwavedemo.avi (4.6Mb)
walk07a_classharris.avi (2.6Mb)
walk07a_silhouette.avi (3.0Mb)
walk02a_classharris.avi (1.4Mb)
walk02a_silhouette.avi (1.5Mb)
Related projects:
Recognition of human actions
Related publications:
(Interest point detection and scale selection in space-time)
(Velocity-adaptation of spatio-temporal receptive fields for
direct recognition of activities: An experimental study)
(Time-recursive velocity-adapted spatio-temporal scale-space filters)
(Linear spatio-temporal scale-space)
(Separable scale-space with causal time direction)
(Automatic selection of temporal scales in time-causal scale-space)
(Monograph on scale-space theory)
Ivan Laptev