| Abstract | This paper describes a periodic motion based pedestriansegmentation algorithm for videos acquired from moving
platforms. Given a sequence of bounding boxes
containing the detected and tracked walking human, the
goal is to analyze the low dimension structure by
considering every object sample as a point in the high
dimensional manifold space and use the learned structure
for segmentation. In this work, unlike the traditional top-
down dimension reduction (manifold learning) methods
such as Isomap and locally linear embedding (LLE) [9],
we introduce a novel bottom-up learning approach. We
represent the human stride as a cascade of models with
increasing parameter numbers. These parameters
describe the dynamics of pedestrians from coarse to fine.
By applying the learned manifold structure, we can
predict the location of body parts, especially legs, with
high accuracy at every frame. The segmentation in
consecutive images is done by EM clustering. With the
accuracy for prediction using twin-pendulum model, EM
is more likely to converge to global maximums.
Experimental results for real videos are presented. The
algorithm has demonstrated a reliable performance for
videos acquired from moving platforms.
|
