摘要： 针对增强现实中的三维注册问题，提出一种基于机器学习的图像自然特征点识别方法。基于高斯混合模型进行样本选择，利用模式识别中的分类方法替代特征向量的最近邻匹配，将计算负担从实时阶段转移到训练阶段，利用各匹配点对之间的相似度计算核密度估计的权值，实现相关平面目标的跟踪。实验结果表明，该方法实时性好、相机位姿估计精确，对光照、遮挡、透视等变化具有较强的鲁棒性。

关键词: 机器学习, 自然特征, 增强现实, 三维注册

Abstract: A natural feature recognition method based on machine learning is proposed for 3D registration in augmented reality application. This method increases the accuracy of key-points recognition and moves the computational burden from runtime matching to offline training by substituting specific classification for nearest-neighbor searching. Robust camera tracking and pose estimation can be obtained by the similarity of these matched key-points and the homography matrix. Experimental results demonstrate that this method is suitable for real-time application and is stable against illumination change, occlusion and perspective effect.

Key words: machine learning, natural feature, augmented reality, 3D registration

中图分类号: 

• TP18