Motion analysis and classification with directional Gaussian derivatives in image sequences

This work is intended to provide some ideas on the use of a Gaussian-derivative model for visual perception, called the Hermite transform, to extract motion information from an image sequence. Gaussian-derivative operators have long been used in computer vision for feature extraction and are relevant in visual system modeling. A directional energy is defined in terms of the 1-D Hermite transform coefficients of local projections. Each projection is described by the Hermite transform, resulting in a directional derivative analysis of the input at a given spatiotemporal scale. We demonstrate that the 1-D Hermite transform coefficients of local projections are readily computed as a linear mapping of the 3-D Hermite transform coefficients through some projecting functions. The directional response is used to detect spatiotemporal patterns that are 1-D or 2-D. Practical consideration and experimental results are also of concern.