Augmented reality registration algorithm based on nature feature recognition
Augmented reality registration algorithm based on nature feature recognition
复制标题
DOI：
10.1007/s11432-010-4026-5
复制
发表时间：
2010-07
期刊：
影响因子：
--
通讯作者：
Jing Chen;Yongtian Wang;Junwei Guo;W. Liu;Jingdun Lin;K. Xue;Yue Liu;Gangyi Ding
中科院分区：
文献类型：
--
作者：
Jing Chen;Yongtian Wang;Junwei Guo;W. Liu;Jingdun Lin;K. Xue;Yue Liu;Gangyi Ding
提出了一种改进的基于关键帧的增强现实配准算法，用于室外环境下的实时运动跟踪。在这种应用中，宽基线特征匹配是一个关键问题。在本文中，我们采用随机树方法将从输入图像中提取的关键点与这些关键帧匹配作为分类问题。扩展卡尔曼滤波也用于抖动校正。针对圆明园的现场数字重建，构建了视频透明移动增强现实系统。实验结果表明，该算法实时性好，鲁棒性好，适合室外跟踪。
This paper presents an improved key frame based augmented reality registration algorithm for real-time motion tracking in outdoor environment. In such applications, wide-baseline feature matching is a critical problem. In this paper, we apply randomized tree method to match key points extracted from the input image to those key frames as a classification problem. Extended Kalman filter is also utilized for jitter correction. A video see-through mobile augmented reality system is built for the on-site digital reconstruction of Yuanmingyuan Garden. Experimental results demonstrate that this algorithm is real-time, robust and effective for outdoor tracking.