Computer vision process frequently include an modeling step whose parameters, obtained from a data set, are not easy to calculate due mainly to the presence of a high proportion of outliers. The most known method to overcome this problem is the random sampling consensus (RANSAC). Such technique, in combination with Harmony Search (HS), are used in this chapter for a robust estimation of multiple view relations from point correspondences in digital images. By using this evolutionary technique, the estimation method endorse a different sampling strategy to generate putative solutions: on one hand, RANSAC generate new candidate solutions in a random fashion; on the other hand, by using HS in combination with RANSAC, each new candidate solution is generated by considering the quality of previous candidate solutions. In other words, the solutions space is searched in an intelligent manner. The HS algorithm is inspired by the improvisation process of an orchestra that takes place when musicians search for a better state of harmony; as a result, the HS-RANSAC can substantially reduce the number of iterations still preserving the robust capabilities of RANSAC. The method is used in this chapter to solve the estimation of homographies, with an engineering application to solve the problem of position estimation in a humanoid robot. In this chapter, seven techniques are compared for the problem of robust homography estimation.
ASJC Scopus subject areas
- Artificial Intelligence