Evaluating gesture-based augmented reality annotation

Drawing annotations with 3D hand gestures in augmented reality are useful for creating visual and spatial references in the real world, especially when these gestures can be issued from a distance. Different techniques exist for highlighting physical objects with hand-drawn circle and arrow annotations from a distance, assuming an approximate 3D scene model (e.g., as provided by the Microsoft HoloLens). However, little is known about user preference and performance of such methods for annotating real-world 3D environments. In this paper, we compare different annotation methods using the HoloLens augmented reality development platform: Surface-Drawing and Air-Drawing, with either raw but smoothed or interpreted and beautified gesture input. For the Surface-Drawing method, users control a cursor that is projected onto the world model, allowing gesture input to occur directly on the surfaces of real-world objects. For the Air-Drawing method, gesture drawing occurs at the user's fingertip and is projected onto the world model on release. The methods have different characteristics regarding necessitated vergence switches and afforded cursor control. We performed an experiment in which users draw on two different real-world objects at different distances using the different methods. Results indicate that Surface-Drawing is more accurate than Air-Drawing and Beautified annotations are drawn faster than Non-Beautified; participants also preferred Surface-Drawing and Beautified.