TY - CONF T1 - Towards a view invariant gait recognition algorithm T2 - Proceedings. IEEE Conference on Advanced Video and Signal Based Surveillance, 2003. Y1 - 2003 A1 - Kale, A. A1 - Chowdhury, A.K.R. A1 - Chellapa, Rama KW - (access KW - algorithm; KW - analysis; KW - Biometrics KW - biometrics; KW - Calibration KW - calibration; KW - camera KW - canonical KW - control); KW - equations; KW - flow; KW - Gait KW - gait; KW - human KW - image KW - invariant KW - model; KW - MOTION KW - optical KW - perspective KW - phenomenon; KW - projection KW - recognition KW - scheme; KW - sequences; KW - spatio-temporal KW - view KW - view; AB - Human gait is a spatio-temporal phenomenon and typifies the motion characteristics of an individual. The gait of a person is easily recognizable when extracted from a side-view of the person. Accordingly, gait-recognition algorithms work best when presented with images where the person walks parallel to the camera image plane. However, it is not realistic to expect this assumption to be valid in most real-life scenarios. Hence, it is important to develop methods whereby the side-view can be generated from any other arbitrary view in a simple, yet accurate, manner. This is the main theme of the paper. We show that if the person is far enough from the camera, it is possible to synthesize a side view (referred to as canonical view) from any other arbitrary view using a single camera. Two methods are proposed for doing this: (i) using the perspective projection model; (ii) using the optical flow based structure from motion equations. A simple camera calibration scheme for this method is also proposed. Examples of synthesized views are presented. Preliminary testing with gait recognition algorithms gives encouraging results. A by-product of this method is a simple algorithm for synthesizing novel views of a planar scene. JA - Proceedings. IEEE Conference on Advanced Video and Signal Based Surveillance, 2003. M3 - 10.1109/AVSS.2003.1217914 ER -