Browsing by Author "Kitamura, Yoshifumi"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Random-Forest-Based Initializer for Real-time Optimization-based 3D Motion Tracking Problems
    (The Eurographics Association, 2019) Huang, Jiawei; Sugawara, Ryo; Komura, Taku; Kitamura, Yoshifumi; Kakehi, Yasuaki and Hiyama, Atsushi
    Many motion tracking systems require solving inverse problem to compute the tracking result from original sensor measurements, such as images from cameras and signals from receivers. For real-time motion tracking, such typical solutions as the Gauss-Newton method for solving their inverse problems need an initial value to optimize the cost function through iterations. A powerful initializer is crucial to generate a proper initial value for every time instance and, for achieving continuous accurate tracking without errors and rapid tracking recovery even when it is temporally interrupted. An improper initial value easily causes optimization divergence, and cannot always lead to reasonable solutions. Therefore, we propose a new initializer based on random-forest to obtain proper initial values for efficient real-time inverse problem computation. Our method trains a random-forest model with varied massive inputs and corresponding outputs and uses it as an initializer for runtime optimization. As an instance, we apply our initializer to IM3D, which is a real-time magnetic 3D motion tracking system with multiple tiny, identifiable, wireless, occlusion-free passive markers (LC coils). During run-time, a proper initial value is obtained from the initializer based on sensor measurements, and the system computes each position of the actual markers and poses by solving the inverse problem through an optimization process in real-time. We conduct four experiments to evaluate reliability and performance of the initializer. Compared with traditional or naive initializers (i.e., using a static value or random values), our results show that our proposed method provides recovery from tracking loss in a wider range of tracking space, and the entire process (initialization and optimization) can run in real-time.
  • Thumbnail Image
    Item
    A Study on AR Authoring using Mobile Devices for Educators
    (The Eurographics Association, 2018) Chu, Kinfung; Lu, Weiquan; Oka, Kiyoshi; Takashima, Kazuki; Kitamura, Yoshifumi; Bruder, Gerd and Yoshimoto, Shunsuke and Cobb, Sue
    Augmented Reality (AR) on consumer devices is now commonplace and it finds application in areas like online retail and gaming. Among which, school education can especially benefit from the interactivity and expressiveness provided by AR technology, facilitating the learning process of students. Although AR-enabled hardware and applications are becoming increasingly accessible to both students and teachers, the entry requirement for AR authoring is still prohibitively high for school teachers. Given the vast variation in the learning ability of students and school curricula, an AR authoring tool that allows the rapid and easy creation of educational content seems to be very desirable among teachers. This paper proposes a gesture-based control method that satisfies the need of educational AR authoring and presents prototypes that work well with smartphone VR head mounts. Through user studies we show that our proposed control method is simple but effective for basic authoring tasks. Our prototypes are also found to be useful in teaching different concepts that require a high degree of spatial comprehension.