Groups of Adjacent Contour Segments for Object Detection
V. Ferrari, L. Fevrier, F. Jurie, and C. Schmid
We present a family of scale-invariant local shape features formed by
pairs of connected, roughly straight contour segments (PAS), and
their use for object class detection. PAS are able to cleanly encode
pure fragments of an object boundary, without including nearby
clutter. Moreover, they offer an attractive compromise between
information content and repeatability, and encompass a wide variety of
local shape structures. We also define a translation and scale
invariant descriptor encoding the geometric configuration of the
segments within a PAS.
We demonstrate the high performance of PAS within a simple but
powerful sliding-window object detection scheme. Through extensive
evaluations, involving eight diverse object classes and more than 1400
images, we 1) study the performance as the parameters vary; 2) show
that PAS substantially outperform interest points for detecting
shape-based classes; 3) compare our object detector to the recent,
state-of-the-art system by Dalal and Triggs.