Adaptive threshold algorithm for multi-marker augmented reality system
Xiaohu Ma, Gang Shi, Hongbo Tian · 2010
In recent years, ARToolKit has been widely used in the development of Augmented Reality (AR) system. It employs square markers, which are more accurate and reliable to locate the position than other planar markers, such as concentric rings and concentric circles. However, in the process of recognition, ARToolKit adopts fixed threshold segmentation method that is not in favor of complex environment. In this paper, we use an improved image segmentation algorithm based on Otsu method and design a Multi-marker Augmented Reality (MAR) system. The experiments indicate that MAR system has the advantage of certain anti-noise ability; therefore it can be applied into complex environment successfully.