Human Perambulation as a Self Calibrating Biometric

Abstract

Abstract. This paper introduces a novel method of single camera gait reconstruction which is independent of the walking direction and of the camera parameters. Recognizing people by gait has unique advantages with respect to other biometric techniques: the identification of the walking subject is completely unobtrusive and the identification can be achieved at distance. Recently much research has been conducted into the recognition of frontoparallel gait. The proposed method relies on the very nature of walking to achieve the independence from walking direction. Three major assumptions have been done: human gait is cyclic; the distances between the bone joints are invariant during the execution of the movement; and the articulated leg motion is approximately planar, since almost all of the perceived motion is contained within a single limb swing plane. The method has been tested on several subjects walking freely along six different directions in a small enclosed area. The results show that recognition can be achieved without calibration and without dependence on view direction. The obtained results are particularly encouraging for future system development and for its application in real surveillance scenarios.

Front-view Gait Recognition

“…Therefore, an automatic gait recognition system which does not depend on camera calibration and is able to recognise individuals walking towards the camera is attractive. 2D view-independent gait identification is a relatively new research area and the approaches found in literature tend to synthesise the sagittal view of the human body from other arbitrary views [12], [18], [35] or to extract gait parameters which are independent from the human pose [4], [38]. The first choice is justified by the fact that the lateral view has demonstrated the recognition capability in many works [27], [43].…”

Performance analysis for gait in camera networks

“…The method proposed by the authors in [16] is based on four main assumptions: the nature of human gait is cyclic; subjects walk along a straight line; the distances between the bone joints are constant; and the articulated leg motion is approximately planar. Therefore, multiple periods of linear gait motion appear analogous to a single period viewed from many cameras related by linear translation and the positions of the legs joints lie in an auto-epipolar configuration.…”

“…Therefore, starting from a video sequence from a single camera and without any calibration, the proposed markerless system, in junction with [16], estimates the gait parameters projected on the lateral plane.…”

“…In real surveillance scenarios, however, we need a system that operates in an unconstrained environment where maybe there is no information regarding the relative position between the camera and the walking subject [44]. 2D view independent gait identification is a recent research area and the approaches found in literature extract some gait parameters which are independent of the human pose [3,42] by analysing the silhouette shape over time or aim at synthesising the sagittal view of the human body from any other arbitrary views [16,24]. The latter choice is justified by the fact that the lateral view has proven recognition capability in a great number of works [20,33,45].…”

“…The latter choice is justified by the fact that the lateral view has proven recognition capability in a great number of works [20,33,45]. However, they need information on the camera parameters [24] or rely on the use of reflective markers on the body [16].…”