Three-way auto-correlation approach to motion recognition

This paper presents a feature extraction method for three-way data: the cubic higher-order local auto-correlation (CHLAC) method. This method is particularly suitable for analysis of motion-image sequences. Motion-image sequences can be regarded as three-way data consisting of x-, y- and t-axes. The CHLAC method is based on three-way auto-correlations of pixels in motion images. It effectively extracts spatio-temporal local geometric features characterizing the motion, such as gradients (velocities) and curvatures (accelerations). It has also several advantages for motion recognition. Firstly, neither a priori knowledge nor heuristics about the objects in question is required. Secondly, it is shift-invariant and thus segmentation-free. Thirdly, its computational cost is less than that of traditional methods, which makes it more suitable for real time processing. The experimental results on large datasets for gesture and gait recognition showed the effectiveness of the CHLAC method.