Real time image registration based on feature tracking using a Digital Signal Processor

Image registration is a stepwise process of overlaying various images of a scene. Accurate image registration in a real time environment has always been a challenge involving the detection of analogous features and then construction of mosaic within plausible accuracy range. Digital Signal Processor is an asset in this regard; its advanced versions equipped with multiple cores can handle many processes at the same time. In this paper we have implemented an efficient algorithm, proposed in our previous research work, for real time image registration on a Dual Core Digital Signal Processor ADSP-BF561. The key technique employed for image registration is based on feature tracking. Our work includes division of main tasks into two groups and then implementation of each group on a different core of dual core Digital Signal Processor. The proposed solution is then put to test in a real time environment on various sequences of images and its time variation is also analyzed.