Given a human walking cycle, images sequence consists of T frames, the features of this human gait images sequence can be described as
(1) Discrete Fourier transforms: by dividing the walking images into C walking cycles as shown in Figure 3, we can find the start (end) of a walking cycle by finding the minimum point in Figure 5.
Given person p, the normalized feature matrix for walking cycle c can be expressed as
Figure 7 shows these three vectors for one human walking cycle.
(2) Normalization: Considering that different walking cycles have different frame count ([N.sub.c]), we need to "align" [N.sub.c] to a fixed value.
Given C walking cycles, we use the normalized [OMEGA](p, c) as the final features.