Abstract | ||
---|---|---|
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 its 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. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICIP.2005.1530190 | 2005 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), VOLS 1-5 |
Keywords | Field | DocType |
feedback loop,gait analysis,oscillations,image classification,human body,classification system | Phase-locked loop,Computer vision,Object detection,Pattern recognition,Computer science,Feedback loop,Artificial intelligence,Pixel,Contextual image classification,Detector,Pedestrian detection,Minimum bounding box | Conference |
ISSN | Citations | PageRank |
1522-4880 | 4 | 0.54 |
References | Authors | |
6 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yang Ran | 1 | 87 | 6.72 |
Qinfen Zheng | 2 | 453 | 56.42 |
Isaac Weiss | 3 | 4 | 0.54 |
Larry S. Davis | 4 | 14201 | 2690.83 |
Wael Abd-Almageed | 5 | 248 | 24.52 |
Liang Zhao | 6 | 4 | 0.54 |