Active Learning from Relative Comparisons PROJECT TITLE :Active Learning from Relative ComparisonsABSTRACT:This work evaluates the applying of various state-of-the-art methods for interest point matching, aiming the robust and efficient projective reconstruction of 3-dimensional scenes. Projective reconstruction refers back to the computation of the structure of a scene from images taken with uncalibrated cameras. To achieve this goal, it is essential the usage of an effective purpose matching algorithm. Even though several point matching methods are proposed in the literature, their impacts within the projective reconstruction task haven't yet been fastidiously studied. Our analysis uses as criterion the estimated epipolar, reprojection and reconstruction errors, moreover as the running times of the algorithms. Specifically, we compare five different techniques: SIFT, SURF, ORB, BRISK and FREAK. Our experiments show that binary algorithms such as, ORB and BRISK, are therefore accurate as float point algorithms like SIFT and SURF, nevertheless, with smaller computational value. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Laser Micromachining and Characterization of Metal-on-Glass High Density Pitch Adapters Big Data and Privacy: Emerging Issues
