Hardware architecture for Fast 2D distance transformations
Vasiliki Giannakopoulou, Kostas Masselos · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2014
Distance transformation algorithms approximations use distance transformation with small neighborhood pixels, defined by masks. There are many different DT approximations applied, and some of them are proposed to be implemented in custom hardware, exploiting the possibilities offered for accelerating the actions required in the proposed algorithm. In this paper, a custom hardware architecture is proposed in order to implement fast 2D distance transformations that are independent of the distance function used. The current implementation concerns the Euclidean distance transform and Kintex7 evaluation board is used for this purpose. Area and synthesis results are presented for various image sizes, while it is observed a speed increase of 98% against the X86 architecture.