<![CDATA[Plane detection is a key component of markerless augmented reality (AR) systems, as it determines the system’s ability to recognize surfaces for virtual object placement. However, plane detection performance is influenced by surface characteristics and lighting intensity, which can affect the quality and stability of feature points during the tracking process. This study aims to evaluate the performance of plane detection in a Unity-based markerless AR system using AR Foundation under varying surface characteristics and lighting intensities. The experiments were conducted using three surface types: highly textured, low-textured, and reflective surfaces, under three lighting conditions: bright, dim, and dark. Each scenario was tested five times using four evaluation parameters: tracking time, detection success rate, drift distance, and coverage area. The results show that highly textured surfaces provided the best overall performance across all evaluation parameters, with the fastest tracking time ranging from 2.82 to 6.66 seconds, a detection success rate of 100%, the lowest drift distance ranging from 0.04 to 1.55 cm, and a wider coverage area of 81.04% compared with the other conditions. In contrast, low-textured surfaces presented the most challenging condition, particularly under dark lighting, which resulted in detection failure across all trials. Meanwhile, reflective surfaces were still able to detect planes in most trials but exhibited reduced performance due to the instability of feature points caused by light reflections. Overall, the findings demonstrate that plane detection performance varies across different combinations of surface characteristics and lighting intensities.]]>
