iii
Abstract
Visual motion carries information about the dynamics of a scene. Auto-
matic interpretation of this information is important when designing com-
puter systems for visual navigation, surveillance, human-computer interac-
tion, browsing of video databases and other growing applications.
In this thesis, we address the issue of motion representation for the purpose
of detecting and recognizing motion patterns in video sequences. We localize
the motion in space and time and propose to use local spatio-temporal image
features as primitives when representing and recognizing motions. To detect
such features, we propose to maximize a measure of local variation of the
image function over space and time and show that such a method detects
meaningful events in image sequences. Due to its local nature, the proposed
method avoids the influence of global variations in the scene and overcomes the
need for spatial segmentation and tracking prior to motion recognition. These
properties are shown to be highly useful when recognizing human actions in
complex scenes.
Variations in scale and in relative motions of the camera may strongly
influence the structure of image sequences and therefore the performance of
recognition schemes. To address this problem, we develop a theory of local
spatio-temporal adaptation and show that this approach provides invariance
when analyzing image sequences under scaling and velocity transformations.
To obtain discriminative representations of motion patterns, we also develop
several types of motion descriptors and use them for classifying and matching
local features in image sequences. An extensive evaluation of this approach is
performed and results in the context of the problem of human action recog-
nition are presented.
In summary, this thesis provides the following contributions: (i) it intro-
duces the notion of local features in space-time and demonstrates the suc-
cessful application of such features for motion interpretation; (ii) it presents
a theory and an evaluation of methods for local adaptation with respect to
scale and velocity transformations in image sequences and (iii) it presents
and evaluates a set of local motion descriptors, which in combination with
methods for feature detection and feature adaptation allow for robust recog-
nition of human actions in complex scenes with cluttered and non-stationary
backgrounds as well as camera motion.
评论1