Convergence Acceleration for Lucas-Kanade Algorithm via Discarding Strongly Concave/Convex Areas
Yueming Qin · Journal of Information and Computational Science · 2014
Image alignment is a useful technique in many important research fields of computer vision. Among all the image alignment algorithms, Lucas-Kanade algorithm is one of the most widely used algorithms. During the past 30 years, a wide variety of extensions have been made to the original formulation and an unabridged Lucas-Kanade algorithm series has been formed. In this paper, we propose a novel method which can accelerate the convergence of Lucas-Kanade algorithm series. Based on the theory of strongly concave/convex function, we define the Strongly Concave/Convex Areas (SC/CA) of images. Through discarding the SC/CA, the iteration number of Lucas-Kanade algorithm series can be reduced without decreasing the precision. Finally, we present various experimental results that validate our method. These results also show that the proposed method is robust with the parameter used in detecting the SC/CA.