• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.341-350
• /
• 2022

In this paper, we propose a deep learning based on-device augmented reality (AR) system in which multiple input images are used to implement the correct occlusion in a real environment. The proposed system is composed of three technical steps; camera pose estimation, depth estimation, and object augmentation. Each step employs various mobile frameworks to optimize the processing on the on-device environment. Firstly, in the camera pose estimation stage, the massive computation involved in feature extraction is parallelized using OpenCL which is the GPU parallelization framework. Next, in depth estimation, monocular and multiple image-based depth image inference is accelerated using the mobile deep learning framework, i.e. TensorFlow Lite. Finally, object augmentation and occlusion handling are performed on the OpenGL ES mobile graphics framework. The proposed augmented reality system is implemented as an application in the Android environment. We evaluate the performance of the proposed system in terms of augmentation accuracy and the processing time in the mobile as well as PC environments.

• Journal of Digital Contents Society
• /
• v.15 no.2
• /
• pp.197-207
• /
• 2014

Many people are now enjoying mobile games using various smartphone platforms. However, we have to develop games separately for each smart device platforms so far. Cocos2d-x, a game development framework is released to solve this problem. As a multiplatform version of the existing Cocos2d, Cocos2d-x can make one source code run on various platforms. It is an open software that is able to be used by everyone, and when using it, mobile games can be developed easily based on C++ and OpenGL. In this paper, we implemented a PC laboratory decorating game application, named ILove501, using Cocos2d-x. The 501 is a room number of our PC lab. ILove501 includes an educational feature of solving quizzes in order to highlight positive effects of game. For implementation of a multiplatform game, ILove501 was developed in Windows and iOS environment at the same time, and we verified the results of the execution by porting on a variety of devices such as Android, iPhone, iPad and Galaxy Tab.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1470-1473
• /
• 2013

본 논문에서는 안드로이드 플랫폼에서 3D 타이포그래피를 쉽게 표현할 수 있도록 지원하는 라이브러리를 설계 구현하였다. 현재까지 모바일 플랫폼에서 3D 타이포그래피를 지원하기 위한 라이브러리는 iOS에서 사용가능한 FTGL ES만이 공개되었고 이를 직접 안드로이드 플랫폼에서 사용할 수 없으며 제공되는 3D 표현 기능 또한 제한적이었다. 본 연구에서는 iOS용 FTGL ES를 안드로이드 플랫폼에서 사용할 수 있도록 변환하고 OpenGL ES기능을 활용하여 다양한 3D 폰트 표현을 지원할 수 있는 3D 폰트 라이브러리를 개발하였다. Freetype 라이브러리를 통해 폰트의 Glyph 정보들을 얻고 이를 이용해 테두리, 양각, 음각 등 다양한 3D 문자 표현 기능을 구현하였고, 공간상에서 문자들의 배치를 수학적으로 모델링하여 다양한 3D 문자 배치 기능을 구현하였다. 개발된 3D 폰트 라이브러리를 이용하여 다양하게 문자들을 3D 공간에 표현할 수 있으면서, 기존 3D 타이포그래피 표현 방법들에 비해 더 쉽고 빠르게 3D 타이포그래피를 표현할 수 있도록 지원한다.