%0 Conference Paper %B Image Processing, 2005. ICIP 2005. IEEE International Conference on %D 2005 %T Pedestrian classification from moving platforms using cyclic motion pattern %A Yang Ran %A Qinfen Zheng %A Weiss, I. %A Davis, Larry S. %A Abd-Almageed, Wael %A Liang Zhao %K analysis; %K angle; %K body %K classification; %K compact %K cyclic %K DETECTION %K detection; %K digital %K Feedback %K Gait %K human %K image %K information; %K locked %K loop %K loop; %K loops; %K module; %K MOTION %K object %K oscillations; %K pattern; %K pedestrian %K phase %K Pixel %K principle %K representation; %K sequence; %K sequences; %K SHAPE %K system; %X This paper describes an efficient pedestrian detection system for videos acquired from moving platforms. Given a detected and tracked object as a sequence of images within a bounding box, we describe the periodic signature of its motion pattern using a twin-pendulum model. Then a principle gait angle is extracted in every frame providing gait phase information. By estimating the periodicity from the phase data using a digital phase locked loop (dPLL), we quantify the cyclic pattern of the object, which helps us to continuously classify it as a pedestrian. Past approaches have used shape detectors applied to a single image or classifiers based on human body pixel oscillations, but ours is the first to integrate a global cyclic motion model and periodicity analysis. Novel contributions of this paper include: i) development of a compact shape representation of cyclic motion as a signature for a pedestrian, ii) estimation of gait period via a feedback loop module, and iii) implementation of a fast online pedestrian classification system which operates on videos acquired from moving platforms. %B Image Processing, 2005. ICIP 2005. IEEE International Conference on %V 2 %P II - 854-7 - II - 854-7 %8 2005/09// %G eng %R 10.1109/ICIP.2005.1530190