2023 年 14 巻 1 号 p. 2-17
This paper proposes a technique for 360-degree panoramic video generating with multiple actual and virtual cameras in real-time. Our method acquires multiple images consisting of real images from physical cameras and virtual images from virtual cameras by GPU-based texture and encoding. Then, our method generates 360-degree panoramic images by ORB feature detection and matching to virtual and real images, automatic homography estimation based on the random absent consensus algorithm, multi-band blending and produces high-resolution video stream by Nvidia encoder based Hardware accelerated video encoding. From experimental results, we verified that our method takes at least 45fps at 2K resolution and 33fps at 4K resolution when transmitting the head mounted display stereo, enabling real-time 360-degree panoramic video generation as well as transmission.
