Parallel spatio-temporal convolution scheme oriented for hardware real-time implementation

In this paper, a new parallel approach to 3D convolution of series of grey-scale images is presented An original, hardware oriented, 2D convolution scheme is elaborated, and extended into the temporal domain. Complexity of the scheme is determined and analysed with respect to the number of non-zero coefficients in a convolution kernel. The parallelisation of convolution operations is analysed and results are presented Serial and parallel variants of 2D convolution engines are proposed and their time-cost trade-offs are given. Flexibility of the solution with regard to scalable size of the kernel is highlighted.