This paper introduce the idea to use different interest point detectors so that each core can work on its own subset independently of the others. However, since the image pairs are the same, the homography will be essentially the same and can therefore be distributed by the process that first finds a solution. This will have an impact on how to implement a parallel version of RANSAC.
As shown in the top image pair, if choosing some specific number of top responses for the detectors we obtain less noisy points compared to require the same total amount of points for just one detector, as shown in the bottom, image pair.
The problem is of course to find several different key point detectors and therefore it is something I have been investigating in several papers.
Published by Anders
Anders Hast received a PhD in Computerised Image processing at Uppsala university in 2004. In 2011 he spent one year at IIT, CNR, Pisa in Italy as an ERCIM fellow and after that he received a full time position as associate professor and in 2019 he became professor in image processing, both at Uppsala University. He has been affiliated with UPPMAX super computer centre where he worked as an application expert in Scientific Visualisation and later in the field of digital humanities together with the Centre for digital humanities in Uppsala. His recent research has focused on image processing and computer vision, for applications in microscopy, aerial photography, object recognition and especially hand written text recognition and face recognition.
View all posts by Anders