GPU Based Affine Linear Image Registration using Normalized Gradient Fields

We present a CUDA implementation of a complete registra-tion algorithm, which is capable of aligning two multimodal images, us-ing affine linear transformations and normalized gradient fields. Through the extensive use of different memory types, well handled thread man-agement and efficient hardware interpolation we gained fast executing code. Contrary to the common technique of reducing kernel calls, we significantly increased performance by rearranging a single kernel into multiple smaller ones. Our GPU implementation achieved a speedup of up to 11 compared to parallelized CPU code. Matching two 512 × 512 pixel images is performed in 37 milliseconds, thus making state-of-the-art multimodal image registration available in real time scenarios.