Abstract
Visual markers are useful assistive tools for object manipulation. Existing planar visual markers (AR markers) have poor accuracy in pose estimation, especially in frontal direction. Tanaka et al. solved this problem by a novel principle using two lenticular lenses and a microlens array. These two types of markers display a changing two-dimensional moire pattern according to the visual-line direction. We can extract pose information from patterns by a single camera. We developed two RT components based on common interface (I/F) for cameras to recognize these visual markers for the precise pose estimation. In this report, we describe the class constitution and interface design of each RT component, and show a test result by each sample RTC which we prepared for operation check.
